A systematic review on colon cancer classification by convolutional neural networks: Architecture,accuracy,and research directions

Abstract

Introduction

Recent studies indicated the advancement of Convolutional Neural Networks (CNNs) have facilitated the colon cancer diagnosis process via medical image processing and multi-modality prediction analysis. This paper aims to systematically review the recent notable studies of CNN-based colon cancer classification using histopathological WSI and compare their strengths and limitations as inspirations for future research directions.

Method

This systematic review was conducted under a PRISMA analysis framework. The PICO selection and PROBAST bias assessment tools were used in data selection and validation. The systematic review compared accuracy from notable studies in benchmark architectures (Res-Net, Inception, VGG-Net, Dense-Net, and Efficient-Net) regarding the bi- and multi-classification tasks (2020-2025).

Results

The result showed that Res-Net architecture demonstrated the highest accuracy in both bi- (99.97%) and multi-classification (99.96%) tasks over the past five years. Newer architectures (Efficient-Net, Dense-Net) outperformed older models (VGG-Net, Res-Net) by optimizing depth and feature reuse while minimizing biases. Low computational model were more suitable for real-world deployment and clinical interaction.

Conclusion

This review contributes to the systematic synthesis of knowledge regarding advancements in CNN-based colon cancer classification. Also, this paper provided future research guidelines for further directions (quantum AI, advanced analytics, and lightweight integrations) and implementation in clinical settings.

Keywords

colon cancer classification medical image processing CNN architecture residual net VGG net inception dense net efficient net clinical integration

1. Introduction

Colon cancer causes morbidity and mortality worldwide. Emerging Artificial Intelligence (AI) offers significant benefits for patients through more accurate diagnosis.¹ Convolutional neural networks (CNNs) have revolutionized medical image processing and imaging in oncology practices.^2,3 In colon cancer histopathological image processing tasks, bi-classification (i.e., adenocarcinoma/benign) and multi-classification (i.e., subtypes of WSI) are the most researched topics. The hierarchical architecture of CNN can identify underlying patterns and structures to facilitate more accurate classification,^4,5 segmentation,⁶ and registration^7,8 than the traditional machine learning approach.⁹ By reducing the complexity in manual feature engineering, CNNs accelerate the development of automated tools for a smart and reliable performance in colon cancer diagnosis process.^7,10

With the rapid development of CNN applications, Bhatt et al.¹¹ reviewed CNN architectures, applications, and future scope in general computer vision studies. The Figure 1 indicates a year-by-year increasing research interests in medical CNNs for colon cancer diagnosis from 2000 to 2025. 94,990 out of 481,930 (19.7%) CNN research papers published in IEEE Xplore, ScienceDirect, and Springer Nature underscores the innovative importance of medical image processing techniques boosted by CNNs over the past 25 years.¹² In the recent 5 years, the CNN-based applications leads to promising results in image processing tasks of colon cancer.^7,10,13

Figure 1.

Survey results based on related studies.

However, only 3,147 (0.7%) of CNN studies particularly looked into colon cancer classification. Specifically, during the last 5 years, 2,567 papers studied state-of-the-art variants of CNN (e.g., Res-Net, Efficient-Net, VGG-Net, Dense-Net, transformer-CNN hybrids, etc.) have been used for the colon cancer diagnosis.³ In fact, there is a lack of a systematic review with a comparison of the performance of CNN in colon cancer classification tasks.¹⁴ Hence, the aim of the paper is to review the use of various CNN state-of-the-art architectures in colon cancer detection (bi-classification) and multi-classification tasks over the past 5 years.

2. Methodology

2.1. Search strategy

In this systematic review, the PRISMA method adopted a search strategy to retrieve metadata from related publication articles from IEEE Xplore, ScienceDirect, and Springer Nature databases. The search period was defined as January 2020 to the first quarter of 2025. The search strategy adopted boolean operators OR and AND combined keywords using the expression - ((Convolutional Neural Network) OR (CNN)) AND ((Medical Image Processing) OR (Medical Imaging) OR (WSI) OR (Histopathology)) AND (Colon Cancer) for screening papers. The target of the screening included title, abstract, and keywords. Afterwards, the PICOS framework selected qualified samples with eligibility criteria (in Table 1) by 3 reviewers for the data synthesis and further discussion.

Table 1.

Eligibility criteria for PRISMA review on CNNs applied to colon cancer.

Category	Criteria
Study Design (PICOS)	Population: Colon cancer classification using WSI histopathology data.
	Intervention: CNN-based models.
	Comparator: Accuracy
	Outcome: Benchmark accuracy result
	Study Type: Articles, conferences (Science Direct, IEEE, Springer Nature).
Inclusion	Population: Medical, WSI, or histopathological.
	Intervention: CNN-based.
	Comparator & Outcome: Primary (Accuracy ≥ 0.85) with secondary metrics.
	Study Type: Peer-reviewed journal and full conference papers with experimental results.
Exclusion	Population: Non-histopathological or WSI data.
	Intervention: Non-CNN approaches (e.g., SVM, random forest, pure transformers without CNN components) .
	Comparator & Outcome: Accuracy < 0.85.
	Study Type: Low-evidence studies (abstracts, editorials) or not peer-reviewed.
Additional Filters	Biases: High bias risk (PROBAST-assessed).
	Time Interval: 2020 to 2025 (Q1).
	Availability: Open-access data/code availability.
	Language: English-language studies.
	Ethics: Statement of interest conflict with DOI.

2.2. Data collection, sampling, and selection

We used a stratified two-phase screening process for sampling. First, we investigated the total quantity of related publications from 2000 to 2025. For each included study, we extracted accuracy metrics from text, tables, or figures. Afterwards, this study emphasized the in-depth synthesis. To select qualified sample studies, research title, abstract, and keywords were screened by 2 independent reviewers for relevance, which is the evidence for the further full-text selection in terms of finalization. After the full-text review, the selection was based on the inclusion and exclusion settings in Table 1. The third reviewer validates the results at the end of the selection process.

2.3. Eligibility standard

As shown in Table 1, for the selection of sample articles, the PICOS protocol supervised the process on Population (Medical imaging and image processing data), Intervention (CNN models), Comparator(traditional ML, other DL models, and manual curation), Outcome (Model performance), and Study Type (peer-reviewed journal and conference articles). Inclusion and Exclusion criteria pointed constraint of selection. First, the review processed CNN applications explicitly linking to the PICOS workflow with the PROBAST bias assessment tool.

2.4. Risk of bias and reporting bias assessment

Based on the PICOS design, the PROBAST (Prediction model Risk of Bias Assessment Tool) framework was adopted to systematically evaluate the methodological quality and potential biases of the samples (ResNet, Inception, VGG-Net, Dense-Net, and Efficient-Net) in levels of low, unclear, and high. Each sample was rigorously assessed across four key domains: Participants (representativeness of architecture), Predictors (accuracy in image processing), Outcome (experimental results of accuracy), and Analysis (comparison results). This approach ensured the comparative analysis of CNN architectures accounted for reliable results.¹²

2.5. Inclusion and exclusion

The Table 1 outlines clear inclusion and exclusion criteria under the PICOS framework for selecting studies in a systematic review. This selection specifically targets peer-reviewed research published between 2020 and 2025 that uses histopathological whole slide images (WSI) with CNN-based models (including hybrids) to perform classification tasks. Included studies must report a primary accuracy of at least 85%.

2.6. Additional filter

The additional filters (in Table 1) allow the review to prioritize studies with higher quality (using PROBAST evaluation) and relevance beyond the baseline PICOS criteria. The additional filters include restricting the search timeframe of 2020 to early 2025 to capture the latest advancements. The filter include studies with open-access data or code to support transparency and reproducibility to ensure the research specifically addresses tissue classification. Additionally, the filter includes a selection of English-language publications ensures accurate comprehension by the reviewers, while requiring a formal ethics or conflict of interest statement with a DOI ensures the included studies adhere to professional standards of integrity and accountability.

2.7. Reviewer workflow

A three-reviewer workflow is implemented. Reviewer A and B independently conducted the initial screening of titles and abstracts, as well as the subsequent full-text review, based on the predefined PICOS inclusion and exclusion criteria. Then, Reviewer C validated the results at the end of the selection process with PROBAST evaluation (i.e., model development, dataset declaration, result, and validation), additional filters, and disagreements between the two primary reviewers through independent adjudication. The data synthesis was completed by all the reviewers.

2.8. Data synthesis

In this research, quantitative comparisons facilitated data synthesis. Using the most recent five years of research from IEEE Xplore, ScienceDirect, and Springer Nature databases, this research systematically reviewed deeper insights into CNNs architecture designs and applications based on PROBAST evaluation. Reviewers assessed quality of sample studies under the PICOS framework with PROBAST exclusion criteria.

A = \frac{T P + T N}{T P + T N + F P + F N} \times 100 %

(1)

Data synthesis includes accuracy comparison for all 5 state-of-the-art architectures (Res-Net, Inception, VGG-Net, Dense-Net, and Efficient-Net) using a unified formula (in equation (1)). Accuracy $(A)$ was compared to selected the highest in both detection and classification tasks. Their secondary (applicable) metrics, including sensitivity, specificity, F1 score, and Area Under the Curve (AUC), as well as dataset(s) used, were considered for the heterogeneity and sensitivity of the synthesized result (solely on $A$ ) to understand the advantages and limitations and the possibility of future research in CNN-based colon cancer diagnostics.

3. Results

3.1. Search results

As shown in Figure 2, the PRISMA flowchart outlines the systematic process of study selection for the review. The process began with the identification of 2,567 records from three databases: IEEE Xplore (344), ScienceDirect (1,124), and Springer Nature (1,099) from 2020 to the first quarter of 2025 without duplicates removed.

Figure 2.

Flowchart of study selection according to the PRISMA diagram.

In screening results, 2,186 records were collected, of which 381 were excluded as not relevant. A full-text assessment of 85 records was conducted after the exclusion of non-experimental and non-peer-reviewed design (n = 520), low accuracy below 85% (n = 605), non WSI histopathological (n = 489), and non-CNN-based methods (n = 410). Notably, the sum of these exclusions of full text exceeds the reported 162. After applying the PROBAST tool to evaluate risk of bias, 77 studies with low or unclear risk reliability were ultimately excluded in this review, which is 3.3% of the initially identified sample studies with the consideration of the additional filters (in Table 1). Hence, only the low-risk samples (n=85) were selected in the in-depth review process.

In search results, bi-classification has been achieved at a high level of accuracy using Res-Net, Inception, VGG-Net, Dense-Net, and Efficient-Net architectures. Over the past 5 years, LC25000 (N_colon = 10, 000) and Warwick-QU (N = 165) were the most commonly used open datasets for adenocarcinoma/benign issue identification, whereas the multi-classs tasks were realized using NCT-100K (N = 100, 000), CRC-7K (N = 7, 180), TCGA-COAD (N = 192, 312), and EBHI (N = 2, 228) public datasets.

3.2. Residual net

Residual Net (Res-Net) has been successfully applied to medical image classification tasks.¹⁵ Res-Net has been widely adopted for medical image classification tasks, including early work in colon cancer detection.¹⁶ It uses weight layers to train very deep networks that are more accurate in medical image classification, and implemented for colon cancer classification.¹⁷ Res-Net introduced the residual connections or skip connections, allowing information to bypass layers, as shown in Figure 3, H(x) is the output of deep neural network layers based on the residual learning principle (in equation (2)) with x is the original input.

F_{ResNet} (x) = y = H (x) = F (x) + x

(2)

Figure 3.

Architectural overview of res-net architecture.

BN stands for batch normalization transformation in equation (3). In deep neural layers, μ is mean of the batch with variance (σ²), and the rescaling of the BN requires the learnable parameters γ and β.

\begin{aligned} y^{'} & = B N (x) = \frac{x - μ}{\sqrt{σ^{2} + ε}} \\ y'' & = γ y^{'} + β \\ y'' & = \frac{x - μ}{\sqrt{σ^{2} + ε}} \cdot γ + β \end{aligned}

(3)

The ReLU activation derivatively functions neural networks to improve computational efficiency based on the input x. The key characteristic is in equation (4):

\frac{d}{d x} ReLU (x) = \{\begin{cases} 0 & if x < 0 \\ 1 & if x > 0 \end{cases}

(4)

The advantage of Res-Net is driven from its regularizer application. As shown in equation (5), the identity matrix (W^T) becomes to 0, so it simplifies the workflow and decreases workload of image processing to a_l.

\begin{aligned} a_{l + 1} & = ReLU (W_{l}^{T} a_{l} + b_{l}) \\ a_{l + 2} & = ReLU (W_{l + 1}^{T} ReLU (W_{l}^{T} a_{l} + b_{l}) + b_{l + 1}) \\ a_{l + 2} & = ReLU (a_{l}) = a_{l} \end{aligned}

(5)

The addictive feature extraction follows the Residual function (Conv → BN → ReLU stack: $H_{l} (x_{l - 1})$ ) integrates Input from previous layer (x_l−1) to solve the vanishing gradient problem in deep networks.

x_{l} = H_{l} (x_{l - 1}) + x_{l - 1}

(6)

For the Global Average Pooling l (GAP) ayer, the input x is processed according to equation (7) below:

G A P (X) = \frac{1}{H \times W} \sum_{i = 1}^{H} \sum_{j = 1}^{W} X_{i, j}

(7)

The final output applied SOFTMAX classification function (in equation 8), Y_c is the output for channel c (scalar value), β is an inverse temperature parameter (β → ∞ becomes max pooling). The softmax weights sum to 1: $\sum_{i, j} e^{β X_{i, j, c}} / \sum_{m, n} e^{β X_{m, n, c}} = 1$ .

Y_{c} = \sum_{i = 1}^{H} \sum_{j = 1}^{W} \frac{e^{β X_{i, j, c}}}{\sum_{m = 1}^{H} \sum_{n = 1}^{W} e^{β X_{m, n, c}}} \cdot X_{i, j, c}

(8)

Thus, Res-Net was introduced in its advantage of skipping connections to solve vanishing gradients, enabling much deeper networks. Average pooling occurs when β = 0, Max pooling means β → ∞, and intermediate β means learned importance weighting.

The Table 2 summarizes benchmark studies of Res-Net architecture over the past 5 years. For the multi-classification task, Res-Net 50 variant was utilized by Sarwinda et al.¹⁸ with acceptable level of results (88.00%). Yang, et al.¹⁹ came up with a Res-Net 50 model to predict the cancer development based on WSI datasets (SYSU1, SYSU2, TCGA, and SZPH) and their accuracy showed 54.00 to 86.00% in cross dataset validation. Paing et al.²⁰ used the FCC variant achieved 94.00% accuracy in a 6-subtype classification. ResNet-101 and Res-Net 152 with Self-Attention achieved an accuracy of 92.94% and 92.74%.²¹ Karthik et al.²² showed 92.02% accuracy. With an overall accuracy score of 95.00%, Muneer, et al.²³ improved the performance of the 50 variant in the multi-classification task. Peng and Lee²⁴ improved the accuracy of 50 variant for colon cancer tissue classification to 99.77%.

Table 2.

Performance summary of res-based architectures for bi-/multi- classification.

Architecture	Study	Variant	Dataset	Classification task	Accuracy
Res-Net	²⁵	16	LC25000 (N = 10, 000)	Adenocarcinoma/benign	98.90%
	¹⁵	18	LC25000 (N = 10, 000)	Adenocarcinoma/benign	98.82%
	¹⁶	18	Private (N=889)	Adenocarcinoma/benign/HGD/LGD	98.50%
	¹⁷	CasNet	TCGA-CRC (N = 519)	MSI/TMB	91.00%
	¹⁹	50	SYSU+SZPH(N = 530)	LUAD/LUSC/SCLC/PTB/OP/NL	86.00%
	¹⁹	50	TCGA(N = 422)	LUAD/LUSC/SCLC/PTB/OP/NL	86.00%
	²¹	50	CRC-5K (N = 5, 000)	8 Types of Cancer Cells	92.94%
	²³	18	CRC-5K (N = 5, 000)	8 Types of Cancer Cells	95.00%
	¹⁸	50	Warwick-QU (N = 165)	Adenocarcinoma/benign	88.00%
	²⁰	FFC-Res	UniTepatino (N = 9, 536)	Normal, HP, TA.HG,
				TA.LG, TVA.HG,	94.00%
				TVA.LG
	²⁴	50	NCT-100K(N = 100, 000)	ADI/BACK/DEB/LYM
	²⁴	50	NCT-100K(N = 100, 000)	MUC/MUS/NORM/STR/TUM	99.77%
	²⁶	Hybrid	LC25000 (N = 10, 000)	Adenocarcinoma/benign	98.96%
	²⁷	50	LC25000(N = 10, 000)	Adenocarcinoma/benign	96.00%
	²²	50	EBHI(N = 2, 228)	Tumor/Stroma/Complex/
	²²	50	EBHI(N = 2, 228)	Lympho/Debris/Muc	92.02%
	²⁸	18	Private (N = 566)	Adenocarcinoma/benign	98.70%
	²⁹	110	Warwick-QU (N = 165)	Adenocarcinoma/benign	99.67%
	³⁰	CVC50	LC25000 (N = 10, 000)	Adenocarcinoma/benign	99.55%
	³¹	101	LC25000 (N = 10, 000)	Adenocarcinoma/benign	99.06%

On the other hand, researchers deployed the Res-Net 50 model to realize bi-classification task and improved the accuracy of the model by combining VGG-Net from 83.90% to 96.00%.²⁷ Another study applied Res-Net 16 and received 98.90% accuracy for lung and colon cancer classification.²⁵ Res-Net enabled to develop a hybrid model with Xception which surpassed alternative state-of-the-art methods to achieve 98.96% accuracy in cancer classification.²⁶ In 2024, Haq et al.²⁸ came up with Res-Net 18 and 50 to deal with colon cancer classification and received 98.70% and 96.66% accuracy. Meanwhile, Alzubaidi et al.²⁹ received 99.67% accuracy using Res-Net 110 in colon cancer classification. A hybrid model based on the 50 variant achieved 99.50% accuracy.³⁰ In 2025, research by Deiva et al.³¹ used Res-Net achieved the accuracy of classification to 99.06%.

As the result of our PRISMA review, the state-of-the-art multi-classification was from a 50 variant application by Peng and Lee.²⁴ Their study used NCT-100K reaching 99.77% of accuracy in colon cancer multi-classification with F1 from 99.69% to 100.00% and sensitivity (99.56%). A 110 variant application by Alzubaidi et al.²⁹ used CLAHE preprocessing to Warwick-QU with 99.67% accuracy in detection (adenocarcinoma/benign) with a specificity of 99.56%, sensitivity of 99.57%, and F1-score of 98.34%, respectively.

3.3. Inception net

Inception architecture looks for wider fitness and feasibility in filter layer of neural models. Inception Net employs inception modules comprising of convolutional layers of varying sizes to determine what is interesting in the incoming images. Inception Net is particularly useful for tasks requiring fine-grained feature extraction, where multi-scale patterns matter.³² As shown in Figure 4 below, the Inception model adopted the network-in-network concept with multi-scale feature processing to effectively extract features from input data. The distinct characteristic of Inception is the use of local response layer, which works as a normalization tool, in equation (9):

b_{x, y}^{t} = \frac{a_{x, y}^{1}}{{(k + α \sum_{j = \max (0, i - \frac{N}{2})}^{\min (N - 1, i + \frac{N}{2})} a_{x, y}^{j})}^{β}}

(9)

Where kernel (i) at the pixel position

(x, y), b_{x, y}^{t}

is denoted as regularized output,

a_{x, y}^{j}

is the source output, N is the number of kernels, n represents size of the normalization neighborhood, and k, α, β are hyperparameters. Comparing to batch normalization in equation (3), local response normalization performs across adjacent channels for each spatial position whereas the BN normalizes across the batch for each channel.

Figure 4.

Architectural overview of inception baseline.

The key characteristic of the Inception model accentuates the use of an auxiliary classifier, which is for loss reduction from the vanishing gradient problem. In equation (10), the L_aux is the primary loss, N is the batch size, C is the number of classes, y_i,c is the ground truth label (1 if sample i belongs to class c, 0 otherwise), with the p_i,c is the predicted probability for sample i and class c.

L_{aux} = - \frac{1}{N} \sum_{i = 1}^{N} \sum_{c = 1}^{C} y_{i, c} \log (p_{i, c})

(10)

The feature extraction shown in the architecture diagram (Figure 4) of Inception adopted concatenation filter (Eg.11):

F_{Incept 3} (x) = Concat [3 \times 1 (z), 1 \times 3 (x), 1 \times 1 (x), Pool (x)]

(11)

As shown in Table 3, numerous studies have used Inception V3 with encouraging results in bi-classification task. A study featured an Inception V3 model showed 96% - 99% accuracy in classifying colon cancer histology images.³³ Another model with normalized WSI dataset showed 93.48% using Xception while 95.65% accuracy using V3 in classification.³⁴ With an accuracy of 97.00%, a further proposed model fared better than any other CNN architectures examined, the Inception V3 was adopted in the research by Omar et al.³⁵ using a LC25000. Their results reached a 98.00% accuracy in the prediction of multiple classes.

Table 3.

Performance summary of inception-based architectures for Bi-/multi- classification.

Architecture	Study	Variant	Dataset	Classification task	Accuracy
Inception	³³	V3	TCGA+Haradoi (N = 4, 128)	Adenocarcinoma/benign	99.00%
	³⁴	Xception/V3	Extended CRC (N = 300)	Normal/low/high grade	95.65%
	³⁵	V3	LC25000 (N = 10, 000)	Adenocarcinoma/benign	98.00%
	³⁶	V3	LC25000 (N = 10, 000)	Adenocarcinoma/benign	99.49%
	³⁷	V3	Warwick-QU (N = 165)	Adenocarcinoma/benign	94.55%
	³⁸	V3	KVASIR+ETIS(N = 3, 200)	Adenocarcinoma/benign	94.00%
	³⁹	V3	NCT100K(N = 100, 000)	ADI/BACK/DEB/LYM	96.07%
	³⁹	V3	NCT100K(N = 100, 000)	MUC/MUS/NORM/STR/TUM	96.07%
	⁴⁰	V3	LC25000 (N = 10, 000)	Adenocarcinoma/benign	98.98%
	⁴¹	V3	LC25000 (N = 10, 000)	Adenocarcinoma/benign	99.15%
	⁴²	V3	LC25000 (N = 10, 000)	Adenocarcinoma/benign	99.27%
	⁴³	V3/Xception	LC25000 (N = 10, 000)	Adenocarcinoma/benign	99.95%
	⁴⁴	V3	LC25000 (N = 10, 000)	Adenocarcinoma/benign	89.96%
	⁴⁵	V3+MRINet	LC25000 (N = 10, 000)	Adenocarcinoma/benign	99.67%
	⁴⁶	V4	CRC-7K (N = 7, 180)	ADI/BACK/DEB/LYM
	⁴⁶	V4	CRC-7K (N = 7, 180)	MUC/MUS/NORM/STR/TUM	93.27%
	⁴⁷	V3	CRC-7K (N = 7, 180)	ADI/BACK/DEB/LYM	89.80%
				MUC/MUS/NORM/STR/TUM
				ADI/BACK/DEB/LYM
	⁴⁸	V4	NCT100K (N = 100, 000)	MUC/MUS/NORM/STR/TUM	97.70%
	⁴⁸	V4	NCT100K (N = 100, 000)	ADI/BACK/DEB/LYM	97.70%
	⁴⁹	Xception	NCT100K (N = 100, 000)	MUC/MUS/NORM/STR/TUM	94.18%
	⁵⁰	Xception	LC25000 (N = 10, 000)	Adenocarcinoma/benign	99.97%

Researchers utilized the V3 variant for bi-classification. The model outperformed multiple competing CNN models with an accuracy of 99.49%³⁶ on the WSI dataset. Swarna and Hashi³⁷ designed a model using Inception V3 that achieved 94.55% - 99.40% accuracy on different datasets, while the model³⁸ resulted in 94.00% accuracy in extensive experiments. Appavu⁴⁰ used V3 for colon cancer classification and received a comparatively high accuracy of 98.98%. Ochoa-Ornelas et al.⁴¹ proposed a model for colon cancer classification using the Inception and Res-Net models resulting in 99.15% accuracy, and Merabet, et al.⁴² achieved 99.27% accuracy using the same model. Kumar, et al.⁴³ adopted Inception V3 and their classification result was 99.95%. A hybrid model handling multi-modal data showed 89.96% accuracy for the lung and colon cancer classification.⁴⁴ The V3 variant was adopted with MIRNET in 99.67% accuracy.⁴⁵ In 2025, the Xception variant outperformed the others with an accuracy of 99.97% by Uyar, et al.

Lastly, Inception V4 model was adopted for colon cancer classification task in 2022 by with 93.27% accuracy.⁴⁶ The variant was further improved with 97.70% accuracy by Patnaik, et al.⁴⁸ Wang, et al.³⁹ applied Inception V3 model for colon cancer classification resulting in 96.07% accuracy based on NCT-100K dataset. Gupta, et al.⁴⁷ compared Rer-Net, Inception V3, and VGG 16 and 19 variant. Their results showed the best accuracy was achieved by Inception V3 model in 89.80%. Kumar, et al.⁴⁹ used Xception achieved 94.18% accuracy in colon cancer classification using the NCT-100K dataset.

As the result of the PRISMA analysis, Kumar, et al.⁴⁹ achieved 94.18% accuracy with sensitivity of 92.74%, specificity of 94.80%, F1 of 93.75%, and AUC of 94.48% using the Xception based on NCT-100K dataset for the multi-classification task. Although, Xception model outperformed the traditional Inception variants with 99.97% accuracy,⁵⁰ the dataset information is missing without a demonstration of the secondary metrics in terms of low reproducibility. As the result of detection tasks, the most promising accuracy of Inception was observed in the research by Kumar et al.,⁴³ who extensively combined Inception with Res-Net on the LC25000 dataset, resulting in 99. 95% accuracy and a 99.95% F1 score and 100% sensitivity.

3.4. Visual geometry group net

Visual Geometry Group (VGG) works impressively at colon cancer classification tasks. The VGG-Net model was launched in 2014 by academics at Oxford University to outperform AlexNet, the previous state-of-the-art CNN architecture.⁵¹ As shown in Figure 5, VGG-Net stacks multiple convolutional layers in sequence, unlike Inception or Res-Net, which use parallel or skip connections. Comparing to the previous architecture, the distinguishing feature of VGG is the application of chain rule (in equations (12) and (13)) for vanishing gradients in deep layers without cross-layer feature reuse (in equation (14)), where gradients ∏_l∂f_l/∂f_l−1 → 0 for large L.

F_{VGG 16} (x) = y = f_{L} (W_{L}, f_{L - 1} (W_{L - 1}, \dots, f_{1} (W_{1}, x), \dots))

(12)

\frac{\partial L}{\partial W_{k}} = \frac{\partial L}{\partial y} \cdot \prod_{l = k + 1}^{L} \frac{\partial f_{l}}{\partial f_{l - 1}} \cdot \frac{\partial f_{k}}{\partial W_{k}}

(13)

x_{l + 1} = σ (W^{(l)} x^{(l)} + b^{(l)})

(14)

In Table 4, VGG-Net 16 model for multiclasses histopathology image recognition by Alhazmi and Turki⁵² using 5,400 independent images. The results demonstrate that the 16 and 19 achieved accuracy of 86.80%. Further the accuracy of using VGG-Net was improved to 95.60% using the 16 variant model.⁵³ For multi-classification task, Bakht, et al.⁵⁴ applied the 19 variant using features extraction through a feed-forward neural network for multi-class tissue classification an accuracy of 95.46% using the Karther dataset.⁵⁵ Hamida et al.⁵⁶ compared various architectures of CNN in colon cancer classification, and the result of VGG-Net showed 98.42±0.08% after argumentation. Karbulut, et al.⁵⁷ also used VGG-Net to build a model that achieved an accuracy at 94.13% level. Khazaee et al.⁵⁸ used ensemble VGG architecture and achieved the multiclassification with an accuracy of 99.76%.

Figure 5.

VGG-net baseline (16) architectural overview.

Table 4.

Performance summary of VGG-based architectures for bi-/multi- classification.

Architecture	Study	Variant	Dataset	Classification task	Accuracy
VGG	⁵⁹	19+ANN	LC25000 (N = 10, 000)	Adenocarcinoma/benign	99.85%
	⁵²	16/19	Selected (N = 5, 400)	ADI/BACK/DEB/LYM	86.80%
	⁵²	16/19	Selected (N = 5, 400)	MUC/MUS/NORM/STR/TUM	86.80%
	⁵³	16	NCT-100K+7K (N = 107, 180)	ADI/BACK/DEB/LYM	95.60%
	⁵³	16	NCT-100K+7K (N = 107, 180)	MUC/MUS/NORM/STR/TUM	95.60%
	⁶⁰	19	LC25000 (N = 10, 000)	Adenocarcinoma/benign	98.00%
	⁵⁴	19	Karther (N = 4, 995)	DEB/LYM	95.46%
	⁵⁴	19	Karther (N = 4, 995)	MUC/MUS/NORM/STR/TUM	95.46%
	⁵⁶	16	NCT-100K+5K(N = 105, 000)	ADI/BACK/DEB/LYM	98.42%
	⁵⁶	16	NCT-100K+5K(N = 105, 000)	MUC/MUS/NORM/STR/TUM	98.42%
	⁶¹	19	LC25000 (N = 10, 000)	Adenocarcinoma/benign	99.04%
	⁶²	19/16	LC25000 (N = 10, 000)	Adenocarcinoma/benign	98.00%
	⁶³	NA	LC25000 (N = 10, 000)	Adenocarcinoma/benign	97.40%
	⁶⁴	Hybrid	LC25000 (N = 10, 000)	Adenocarcinoma/benign	99.34%
	⁵⁷	19	Private (N = 515)	Villos/Tubuler/Norm	94.17%
	⁶⁵	19	LC25000 (N = 10, 000)	Adenocarcinoma/benign	98.96%
	⁶⁶	16	LC25000(N = 10, 000)	Adenocarcinoma/benign	99.00%
	⁶⁷	16	LC25000(N = 10, 000)	Adenocarcinoma/benign	96.60%
	⁶⁸	19	LC25000(N = 10, 000)	Adenocarcinoma/benign	99.84%
	⁵⁸	19	NCT-100K+5K (N = 105, 000)	ADI/BACK/DEB/LYM	99.17%
	⁵⁸	19	NCT-100K+5K (N = 105, 000)	MUC/MUS/NORM/STR/TUM	99.17%

A benchmark on bi-classification reported strong results (99.85% accuracy) by adopting the VGG-Net 19 with ANN structure.⁵⁹ Rawashdeh, et al.⁶¹ compared VGG-Net 16 and 19 variant. Their results showed the best accuracy was achieved by the 19 in 99.04%. Yildiz, et al.⁶² tested VGG in handling input histopathological data to recognize colon cancer with 98.00% accuracy. Hossain 63 proposed a VGG model to identify lung cancer cells with 97.40% accuracy. Hasan and Oraibi⁶⁴ classified colon cancer histopathology photos with a VGG-Net 19 model and published their results in accuracy of 99.34%, more accurate than many competing CNN models. In 2023, a promising result of using VGG-Net to detect colon cancer tissues was obtained by Hadiyoso, et al.⁶⁵ in 98.96% using VGG-Net 16. Singh and Singh⁶⁶ used VGG-Net 16 achieved 98.00% in the same year with WSI dataset. In 2024, Akar, et al.⁶⁷ claimed that the adoption of VGG resulted in 96.60%accuracy, while Singh et al.⁶⁰ achieved an accuracy of 98% through the utilization of VGG-Net 19 in colon cancer detection. Lastly, Fahadipour and Aref 68 applied the 19 variant and achieved 99.84% accuracy for colon cancer classification using WSI dataset.

As the PRISMA result, the hybrid ANN + VGG-19 variant⁵⁹ achieved the highest accuracy (99.85%) and F1 = 99.92% of the bi-classification among the samples, with a sensitivity of 99.85%, a specificity of 100%, and an AUC of 99.86% using LC25000. The highest accuracy of multi-classification was achieved by the 19 variant model by Khazaee et al.⁵⁸ in 99.76% accuracy with F1 ≥ 99.60% using NCT-100K and CRC-5K datasets. Hamida et al.⁵⁶ tested the 16 variant, and their result showed 98.42% accuracy with sensitivity $\geq 99.00 %$ and specificity $\geq 98.00 %$ using the same combination of datasets.

3.5. Dense net

Dense-Net is a CNN model that has been prevalently used in the detection of colon cancer.⁶⁹ Being different from the abovementioned CNN architectures, Dense-Net employs multiple dense-blocks to boost non-linear transformational feature learning by adding new features from each concatenation. Meanwhile, Dense-Net addresses vanishing gradients and overfitting through its design, which was intended to optimize CNN architectures (See Figure 6). Densely-linked blocks in this model enhance accuracy by maximizing feature reuse across convolutional layers while optimizing gradient propagation in densely-connected Convolutional Networks.^8,70

Figure 6.

Architectural overview of dense-net baseline (121) architecture.

Despite the similar architecture design from previous review, equation (15) interprets the feature transformation at a macro network level of reuse:

F_{DenseNet 121} (x) = [F_{1} (x), F_{2} (F_{1} (x)), \dots, F_{n} (F_{i} (x))]

(15)

Also, Dense-Net differs from other CNNs and has a dense connectivity pattern with a composite function for concatenative feature reuse in equation (16) different from the design of each layer.

\begin{aligned} x_{l} & = H_{l} ([x_{0}, x_{1}, \dots, x_{l - 1}]), \\ where & [x_{0}, \dots, x_{l - 1}] \in R^{(k_{0} + \dots + k_{l - 1}) \times H \times W} \end{aligned}

(16)

Further equation (17) explains Gradient of loss $(\partial L / \partial x_{l})$ based on Jacobian matrix ∂x_i/∂x_l of layer i’s output, meaning the gradient at layer l accumulates contributions from every subsequent layer that depends on it.

\frac{\partial L}{\partial x_{l}} = \sum_{i = l + 1}^{L} \frac{\partial L}{\partial x_{i}} \cdot \frac{\partial x_{i}}{\partial x_{l}}

(17)

Similar logic as Res-Net and VGG-Net, Dense-Net employs global average pooling layer (equation (7)), fully connected layer, and SOFTMAX (equation (8)) for the final linear prediction. The main characteristic of Dense-Net is the feature reuse, which significantly boosts its informational efficiency. However, the size of the architecture varies based on the number of dense blocks in feature reuse.

Regarding multi-classification task (in Table 5), an examined accuracy of 97.2% on Zenodo 100k colorectal histopathology dataset has been reported using the 121 variant of Dense-Net.⁷¹ Khazaee and Rezaee⁷² analyzed different WSI datasets resulted 99.13% accuracy respectively to CRC-5K and NCT-100K dataset. Hamida, et al.⁵⁶ developed a new Dense-Net 122 model consisting of LS50, 45 and LS51 layers, which achieved 95.86% accuracy. The 169 variant was further tested in a MINST dataset showing 88.56% accuracy.⁶⁹ In 2024, Uddin et al.⁷³ adopted the 201 variant, achieving 99.99% accuracy in 10-fold experimental settings. In 2025, the trend of quantum computing reinforced development of CNN. Eliwa et al.⁷⁴ tested 121 variant and their result showed 99.76% accuracy. An attention-driven DenseNet was proposed in the light of quantum computing and examined with result of 98.92% accuracy⁷⁵ with a comparison study to DenseNet-169 with accuracy of 95.70%.

Table 5.

Performance summary of dense-based architectures for bi-/multi- classification.

Architecture	Study	Variant	Dataset	Classification task	Accuracy
Dense-Net	⁵⁶	Baseline	NCT-100K+5k (N = 105, 000)	ADI/BACK/DEB/LYM	95.86%
	⁵⁶	Baseline	NCT-100K+5k (N = 105, 000)	MUC/MUS/NORM/STR/TUM	95.86%
	⁷¹	121	Zenodo-100K(N = 100, 000)	ADI/BACK/DEB/LYM	97.20%
	⁷¹	121	Zenodo-100K(N = 100, 000)	MUC/MUS/NORM/STR/TUM	97.20%
	⁷²	121	NCT-100K+5k (N = 105, 000)	ADI/BACK/DEB/LYM	99.13%
	⁷²	121	NCT-100K+5k (N = 105, 000)	MUC/MUS/NORM/STR/TUM	99.13%
	⁷⁶	121	LC25000/PCPAm (N = 10, 194)	Adenocarcinoma/benign	95.78%
	⁶⁹	169	MNIST(N = 5, 000)	Multi-classes (8)	88.56%
	⁷⁷	201	LC25000(N = 10, 000)	Adenocarcinoma/benign	99.15%
	⁷⁸	121	EBHI(N = 759)	Adenocarcinoma/benign	90.21%
	⁷⁹	121	LC25000 (N = 10, 000)	Adenocarcinoma/benign	98.60%
	²⁷	Hybrid	LC25000/GlaS(N = 10, 165)	Adenocarcinoma/benign	98.90%
	⁷⁰	169+SVM	UMCM (N = 5, 000)	Adenocarcinoma/benign	92.08%
	⁸⁰	121	LC25000(N = 10, 000)	Adenocarcinoma/benign	99.60%
	⁸¹	Hybrid	LC25000(N = 10, 000)	Adenocarcinoma/benign	99.00%
	⁷³	201	NCT-100K+7K (N = 107, 180)	ADI/BACK/DEB/LYM	99.96%
	⁷³	201	NCT-100K+7K (N = 107, 180)	MUC/MUS/NORM/STR/TUM	99.96%
	⁷⁴	121	NCT-100K+7K (N = 107, 180)	ADI/BACK/DEB/LYM	99.76%
	⁷⁴	121	NCT-100K+7K (N = 107, 180)	MUC/MUS/NORM/STR/TUM	99.76%
	⁷⁵	QCNN+169	EBHI(N = 759)	Normal/Polyp/	98.92%
				Low-gradeIN/High-gradeIN/
				Adenocarcinoma

For bi-classification task, a design of Dense-Net 201 model showed 99.15% accuracy.⁷⁷ A 4-stage CNN model with a RNN classifier for hyperspectral image processing employed a hybrid model that contained Dense-Net 121 to classify colon cancer histological slides⁷⁸ with 90.21% accuracy. Another benchmark study conducted by Kumar et al.⁷⁹ showed that 98. 60% in 2022 used histopathological WSI data for the detection of colon cancer. Dense-Net was a widely used in histopathology visualization, such as colon cancer detection. Gowthamy et al.²⁷ found that their Dense-Net hybrid model for colon cancer histopathology image classification achieved a test accuracy of 98.90%. An application of the hybrid deep and machine learning approach by Dense-Net 169 with SVM was examined by Ohata et al.,⁷⁰ and their result showed 92.08% accuracy. The same variant was tested by Lauande, et al.⁷⁶ resulting in 95.78% accuracy. Sarwinda et al.¹⁸ designed a Dense-Net 121 model as a colon cancer detection tool that had an accuracy of 98.95%. Considering all the aspects described in the previous section, Dense-Net can be considered as a robust architecture for detecting colon cancer. A model based on Dense-Net 121 was examined in colon cancer detection using 10,000 histopathological image, and the result showed 99.60% accuracy in detection.⁸⁰ Due to its dense connection structure that favors better gradient flow and re-using features, it may perform well with only a fraction of the parameters. Di Giammarco et al.⁸¹ proposed an experimental model that achieved 99.30% accuracy in colon cancer detection. The performance of Dense-Net still has areas for improvement, and its application in medical image analysis scenarios can be further expanded by extending to other CNN layouts or RNNs.

The results with the potentially near-perfect accuracy were obtained from the research by Hasan et al.⁸⁰ with a 99.60% accuracy with 99.44% F1 score in a 121 variant model using the LC25000 dataset in detection tasks. Uddin et al.⁷³ achieved an accuracy of 99.96% via a self-designed Dense-Net as their noval framework for the multi-classification task with AUC of 1.00, Recall:99.96%, Specificity: 99.99%, and F1 score: 99.96%, alternatively using the datasets of NCT-100K and CRC-7K.

3.6. Efficient net

As shown in Figure 7, rather than scaling only one dimension (like depth in VGG-Net or width in Res-Net), Efficient-Net uses a compound scaling method to simultaneously scale to optimize the network architecture depth, width, and resolution concerning accuracy⁸² in stem block. The Efficient-Net family of CNN architectures is faster and performs better on the Bidirectional Encoder Representations from Transformers (BERT) machine learning model with fewer parameters.⁸³ The key characteristic of Efficient-Net is the design of Mobile Inverted Bottleneck Convolutions (MBConv). The Efficient-Net model starts with input normalization (equation (3)) to use RGB standard deviation (σ) and mean (μ) to normalize the input x as x = x − μ/σ. Further, Efficient-Net has a compound scaling layer to calculate the depth (α), width(β), and resolution (γ) of input data in a constraint shown in equations (18) and (19), in the STEM Block shown in Figure 7.

F_{EfficientNet} (x) = MBConv (x; ϕ), ϕ = (α^{ϕ}, β^{ϕ}, γ^{ϕ})

(18)

α * β^{2} * γ^{2} = 2, where β, γ \geq 1

(19)

Figure 7.

Efficient-net baseline (B0) architectural overview.

Then, the STEM block consists multiple MBConv blocks process input x into features $x \in R^{H \times W \times C_{in}}$ .

First, a 1 × 1 convolution with weights $W_{1 \times 1}^{e} \in R^{1 \times 1 \times C_{in} \times t C_{in}}$ expands the channel dimension producing intermediate features $z \in R^{H \times W \times t C_{in}}$ . These undergo depthwise spatial convolution via $W_{k \times k}^{d w} \in R^{k \times k \times t C_{in} \times 1}$ (typically k ∈ {3, 5}), followed by channel attention through Squeeze-Excitation: global average pooling reduces spatial dimensions, followed by two FC layers ( $W_{1} \in R^{(t C_{in} / r) \times t C_{in}}$ and $W_{2} \in R^{t C_{in} \times (t C_{in} / r)}$ with reduction ratio r = 4) and sigmoid activation σ for dynamic channel reweighting. A final 1 × 1 projection convolution $(W_{1 \times 1}^{p} \in R^{1 \times 1 \times t C_{in} \times C_{out}})$ restores the channel dimension, while the skip connection $T (x)$ either adds the input directly (when dimensions match) or through a 1 × 1 convolution. As shown in equation (20), the complete operation, $MBConv (x) = SE (Depthwise (Expand (x))) + T (x)$ , achieves the goal of reducing computational efficiency while preserving gradient flow through both the depth and width of the network.

\begin{aligned} MBConv (x) & = SE (Depthwise (Expand (x))) + T (x) \\ where: \\ Expand (x) & = W_{1 \times 1}^{e} * x (W^{e} \in R^{1 \times 1 \times C_{i} \times t C_{i}}) \\ Depthwise (z) & = W_{k \times k}^{d w} ⊛ z (W^{d w} \in R^{k \times k \times t C_{i}}) \\ SE (z) & = z ⊙ σ (W_{2} ReLU (W_{1} GAP (z))) \\ T (x) & = \{\begin{cases} x & if C_{i} = C_{o}, H_{i} = H_{o} \\ W_{1 \times 1}^{p} * x + b & otherwise \end{cases} \end{aligned}

(20)

For the multi-classification tasks, Prezja, et al.⁸⁴ used V2 model with ViT achieved 99.89% accuracy using the NCT-100K dataset. Another benchmark model adopted the B0 variant⁸⁵ achieved 99.87% accuracy using the same dataset. Li, et al.⁸⁶ applied V2 with Swin architecture for the multi-classification task achieved 96.00% accuracy also with the NCT-100K dataset.

As shown in Table 6, Efficient-Net demonstrated state-of-the-art performance in bi-classification tasks as well.^82,87 Saba, et al.⁸⁸ and Taher et al.⁸⁹ both achieved 99.97% benchmark accuracy based on the LC25000 dataset. Kallipolitis⁹⁰ used models of Efficient-Net B0-B7 variants to enhance breast and colon cancer detection with 99% or above accuracy. Moreover, B3 variant was used to categorize colon cancer histopathology images with 91.30% accuracy.⁹¹ The B6 variant was used by Singh et al.⁶⁰ with 93.12% accuracy in classification task. Shouries et al.⁹² adopted B7 model and outperformed various alternative CNN designs with an accuracy of 98.40%. A hybrid model that included B0 variant with ViT structure for colon cancer histopathology images classification⁹³ achieving accuracy of 98.90%. By using the same variant, Girepunje, et al. achieved accuracy in 94.00%.⁹⁴ The accuracy of the variant was examined by Harish et al.⁹⁵ as 98.61%. The B3 variant was the most popular variant and its accuracy result for colon cancer classification from 94.70%⁹⁶ to 99.00%.⁹⁷ Experiment by Ochoa-Ornelas et al.⁹⁸ also applied B3 variant and improved the result to 99.39%. Sathyanarayana et al.⁹⁹ adopted the B7 variant and achieved accuracy of classification at the 98.00% level. Shanto et al.¹⁰⁰ optimized the model of B3 and achieved the highest accuracy (99.78%) of B3 variant samples. Lastly, Bharath, et al.¹⁰¹ adopted hybrid B2 variant with Inception transfer learning method (V2L) achieved 99.90% accuracy.

Table 6.

Performance summary of efficient-based architectures for bi-/multi- classification.

Architecture	Study	Variant	Dataset	Classification task	Accuracy
Efficient-Net	⁸⁴	V2+ViT	NCT-100K (N = 100, 000)	ADI/BACK/DEB/LYM	99.89%
	⁸⁴	V2+ViT	NCT-100K (N = 100, 000)	MUC/MUS/NORM/STR/TUM	99.89%
	⁸⁸	B0	Kvasir/LC25000(N = 130, 279)	Adenocarcinoma/benign	99.97%
	⁸⁹	B0	LC25000 (N = 10, 000)	Adenocarcinoma/benign	99.97%
	⁸⁷	B7	LC25000 (N = 10, 000)	Adenocarcinoma/benign	97.00%
	⁹⁰	B0-7	BreakHis(N = 7, 909)	Adenocarcinoma/benign	96.97%
	⁹¹	B3	LC25000 (N = 10, 000)	Adenocarcinoma/benign	91.30%
	⁹²	B7	LC25000 (N = 10, 000)	Adenocarcinoma/benign	98.40%
	⁹³	B0+ViT	UniToPatho (N = 9, 536)	Adenocarcinoma/benign	98.90%
	⁹⁴	B0	Kather/LC25000(N = 15, 000)	Adenocarcinoma/benign	99.40%
	⁹⁵	Effi+Trans	LC25000 (N = 10, 000)	Adenocarcinoma/benign	98.61%
	⁹⁶	B3	LC25000 (N = 10, 000)	Adenocarcinoma/benign	94.70%
	⁹⁷	B3	LC25000 (N = 10, 000)	Adenocarcinoma/benign	99.00%
	¹⁰²	B3	LC25000/NCIGDC (N = 11, 000)	Adenocarcinoma/benign	94.80%
	⁹⁸	B3	LC25000/NCIGDC (N = 11, 000)	Adenocarcinoma/benign	99.39%
	⁹⁹	B7	LC25000 (N = 10, 000)	Adenocarcinoma/benign	98.00%
	¹⁰⁰	B3	LC25000 (N = 10, 000)	Adenocarcinoma/benign	99.66%
	¹⁰¹	V2L	TCGA-DX (n = 502)	Adenocarcinoma/benign	99.90%
	⁸⁶	V2+Swin	NCT-100K(N = 100, 000)	ADI/BACK/DEB/LYM	96.00%
	⁸⁶	V2+Swin	NCT-100K(N = 100, 000)	MUC/MUS/NORM/STR/TUM	96.00%
	⁸⁵	B0	NCT-100K/CRC-7K(N = 107, 180)	ADI/BACK/DEB/LYM	99.87%
	⁸⁵	B0	NCT-100K/CRC-7K(N = 107, 180)	MUC/MUS/NORM/STR/TUM	99.87%

As a result of PRISMA analysis, Efficient-Net demonstrates remarkable effectiveness in classification through its innovative compound scaling approach. The most promising bi-classification result was observed in the application of V2L hybrid variant by Saba, et al.⁸⁸ (Recall = 100.00%, F1 =99.93%, AUC = 100.00%) and Taher et al.⁸⁹ (Recall =100.00%, F1 = 100.00%) both achieved 99.97% benchmark accuracy based on the LC25000 dataset, while maintaining lower computational requirements compared to traditional CNNs. The highest multi-classification accuracy (99.87%) was achieved by the B0 model⁸⁵ (Recall = 94.52% and F1 =94.41%) using NCT-100K and CRC-7K datasets.

4. Discussion

4.1. Benchmark comparison

The review matrix is shown in Tables 7 and 8 summarized a systematic comparison among the state-of-the-art architectures based on their strengths, limitations with benchmark studies. Meanwhile, LC25000 and NCT-100K (extensively with CRC-5K and 7K) have been the most commonly used datasets for bi- and multi-classification over the past years.

Table 7.

Performance comparison of CNN architectures for colon cancer classification.

Architecture	Study	Acc. (%)	F1 (%)	Other metrics (%)	Dataset
Res-Net	Bi²⁹: (110)	99.67	98.34	Sen: 99.57, Spe: 99.56	Warwick-QU
Res-Net	Multi²⁴: (50)	99.77	99.69	Sen: 99.56	NCT-100K
Inception	Bi⁴³: (V3)	99.95	99.95	Sen: 100.00	LC25000
Inception	Multi⁴⁹: (X)	92.74	93.75	Sen: 92.74, Spe: 94.80	NCT-100K
VGG-Net	Bi⁵⁹: (19)	99.85	99.92	Spe: 100.00, Sen: 99.85, AUC: 99.86	LC25000
VGG-Net	Multi⁵⁸: (19)	99.76	99.60	—	NCT-100K+5K
Dense-Net	Bi⁸⁰: (121)	99.60	99.44	Sen: 99.16, AUC:99.60	LC25000
Dense-Net	Multi⁷³: (201)	99.96	99.96	Sen: 99.96, Spe: 99.99, AUC: 100.00	NCT-100K+7K
Efficient-Net	Bi⁸⁸: (B0)	99.97	99.93	Sen: 100.00, AUC:100.00	LC25000
	Bi⁸⁹: (B0)	99.97	100.00	Sen: 100.00	LC25000
	Multi⁸⁵: (B0)	99.87	94.41	Spe: 99.45, Sen: 94.52	NCT-100K+7K

Table 8.

Summary and quantitative comparison of CNN architectures for classification tasks.

Variant	Strength	Limitations	Included studies	Benchmark
Res-Net	Deep feature extraction; high accuracy; reliable performance.	Heavy weight; risk of overfitting; implementation complexity.	^10,15–31	Bi²⁹: Multi:²⁴
Inception	Improved diagnostic accuracy; high performance; robust feature extraction.	Computational complexity; data dependency; interpretability issues.	^33–50	Bi⁴³: Multi:⁴⁹
VGG-Net	Simple architecture; strong feature extraction; consistent performance.	Computational overhead; resource-intensive; technical limits.	^{51–54,56–68}	Bi⁵⁹: Multi:⁵⁸
Dense-Net	Higher accuracy; fewer parameters; efficient feature propagation; better gradient flow.	Computational complexity; overfitting risk; longer inference time; data dependency.	^{27,43,56,69–81}	Bi⁸⁰: Multi:⁷³
Efficient-Net	High accuracy; efficient resource utilization; reduced computational overhead; reliable performance.	Large training data requirement; hyper-parameter complexity; potential overfitting.	^60,84–102	Bi^88,89: Multi:⁸⁵

In Table 7, the 110 variant showed the highest accuracy (99.67%) with a remarkable F1 (98.34%) for the bi-classification using the Warwick-QU dataset.²⁹ Peng and Lee²⁴ applied the 50 variant model, achieving the highest accuracy (99.77%) with 99.69% F1 and 99.56% sensitivity using the NCT-100K dataset. These remarkable performance metrics indicate the Res-Net excels in deep feature extraction due to its feature of skip connection and mitigates vanishing gradients (equation (6)) for classification tasks. The major limitation of Res-Net application emphasizes on the heavy parameterization, which increases computational costs with overfitting risk, especially in smaller datasets.^20,28 Research by Raseena et al.¹⁰³ demonstrated that while ResNet50 achieves robust performance across colorectal polyp datasets, regularization techniques are essential to address overfitting concerns, with their proposed model (recall ≥87%) across 4 benchmark datasets.

The benchmark study for bi-classification by Kumar et al.⁴³ used the V3 variant achieved top-tier accuracy (99.95%), F1 (99.95%), sensitivity (100.00%). For the multi-classification task, Kumar, et al.⁴⁹ adopted Xception achieved 94.18% marked as the highest accuracy with 93.75% F1, 92.74% sensitivity, and 94.80% specificity. These performance metrics are lower than its counterparts’ in multi-classification task. The most significant strength of the Inception architecture is its filter design, which optimizes multi-scale feature extraction (see in equation (9)). However, its high computational complexity and dependency on large datasets limit performance in multi-classification.^38,47 Recent comparative analyses by Raseena et al.¹⁰⁴ revealed that V3 exhibited relatively poor performance compared to VGG and Res-Net variants, with InceptionResNetV2 ranking as the least effective performer in terms of recall and precision. This finding underscores the need for architectural refinement and optimization for colon cancer image classification.

The state-of-the-art VGG-Net study by Al-Jabbar et al.⁵⁹ achieved the highest accuracy (99.85%) with F1 (99.92%), specificity(100.00%), sensitivity(99.85%), and AUC (99.86%) in bi-classification tasks using the 19 variant. For the multi-classification task, 99.76% accuracy was achieved by Khazaee, et al.⁵⁸ using the 19 variant with 99.60% F1. The advantage of the architecture is its uniform 3*3 convolutional layers that simplify the architecture but remain effective in feature extraction due to the applied chain rule (in equations (12) and (13)) for vanishing gradients in deep layers without cross-layer feature reuse (in equation (14)). Nevertheless, the limitation of the architecture accentuates the excessive resource consumption due to high parameter count and computational cost.^56,58 The performance hierarchy established by Raseena et al.^103,104 confirmed VGG19 as the top-performing model and demonstrated superior accuracy across benchmark datasets. However, this superior performance comes with substantial computational demands, as documented in comparative complexity analyses.⁵⁸

The benchmark study in Dense-Net used the 121 variant by Hasan et al.⁸⁰ achieved highest accuracy (99.60%) in bi-classification with sensitivity in 99.16%, F1 in 99.44%, and AUC in 99.60%. Uddin et al.⁷³ in multi-classification resulted 99.96% accuracy with 99.96% F1, 99.96% sensitivity, 99.99% specificity, and 100.00% AUC. The strength of Dense-Net is feature reuse (in Equation (16)), which improves parameter efficiency and gradient flow, achieving the near-perfect accuracy (99.99%) among all the samples reviewed. However, the limitation of Dense-Net is obvious in memory-intensive training and slower inference times.^76,78 Haryanto et al.¹⁰⁵ successfully optimized DenseNet121 through hyperparameter tuning, achieving 98% accuracy with 19.5 seconds training time using NVIDIA A100 accelerator. Hence, careful parameter selection can partially mitigate computational demands. Their research concluded that Dense-Net 121 with a 75% freeze rate, zero hidden layers, a learning rate of 0.001, and the RMSProp optimizer achieves optimal performance.

Lastly, the Efficient-Net highlights suitability for resource-constrained environments. In bi-classification tasks, Saba et al.⁸⁸ and Taher et al.⁸⁹ both achieved 99.97% benchmark accuracy based on the LC25000 dataset. Both of them demonstrated remarkable F1 and sensitivity. For the multi-classification task, the B0 model achieved 99.87% with 99.45% specificity and 94.52% sensitivity.⁸⁵ The advantage of using the architecture is the depthwise separable convolutions with compound scaling optimize accuracy with minimal computational cost (in equation (20)). However, its limitation indicates the architecture sensitivity to hyperparameter and requires extensive data augmentation.^91,93 Novel lightweight architectures continue to emerge, with Dabass et al.¹⁰⁶ proposing a clinically comparable CNN framework incorporating Enhanced Convolutional Learning Modules (ECLMs) and attention learning modules that achieved 97.7% accuracy on NCT-100k and 98.83% on Kather-5k datasets, with validation scores exceeding 9.0 from expert pathologists. Similarly, EL-CNN architectures¹⁰⁷ with spatial pyramid pooling and enhanced convolutional block attention modules (ECBAM) have demonstrated 99.48% accuracy on NCT-CRC-HE-100K with only 3.72 million parameters, proving that robust performance and low complexity can coexist for clinical applications.

4.2. Result synthesis

Further summarization indicated Dense-Net architecture achieved the highest accuracy in both bi- and multi-classification tasks. The Figure 8 further synthesized findings based on the analysis results into a comparative matrix on the dimensions of depth of feature extraction, simplicity, efficiency, robustness, and resource intensity.

Figure 8.

Comparison matrix.

Res-Net demonstrates high depth and robustness due to its skip connections enabling deep networks, but suffers from low simplicity and high resource intensity.²⁹ Inception offers medium depth and simplicity through its multi-scale branches,⁴³ with high robustness but also high computational costs.³⁷ VGG-Net stands out for its high simplicity from uniform 3× 3 convolutions,⁶⁵ yet has low efficiency and medium robustness.⁶⁰ Dense-Net achieves high depth and robustness via dense connections,⁷⁴ though its medium efficiency comes with high resource demands.¹⁸ Efficient-Net excels with high depth, efficiency, and robustness,⁷³ balancing these with medium resource intensity despite requiring large datasets. Together, these results highlight the trade-offs between architectural complexity, computational efficiency, and performance, with newer models like Efficient-Net and Dense-Net offering superior balances for colon cancer classification tasks. The synthesis highlighted two critical trends, which are Clinical Readiness and Efficiency Improvement. For bi-classification tasks, several state-of-the-art architectures have achieved benchmark accuracies of 99.6% or highe accuracy using histopathological data, and newer architectures (Efficient-Net, Dense-Net) outperformed older models (VGG-Net, Res-Net) by optimizing depth and feature reuse while minimizing biases.

However, the review’s reliance on accuracy as the primary comparative metric, necessitated by inconsistent reporting of secondary metrics across benchmark studies, points to a broader issue of reproducibility in the field. A significant portion of the high-performing studies identified in this review, particularly those utilizing the LC25000 dataset, risk overfitting to dataset-specific artifacts rather than learning genuine disease morphology. The LC25000 dataset, while large and well-annotated, consists of carefully curated, tiled images from a limited number of sources. As highlighted in studies on domain shift,^7,13 models trained on such homogeneous data often fail to generalize to external clinical populations. For instance, a model achieving 99.9% accuracy on LC25000 might see its performance drop precipitously when tested on whole-slide images from a different hospital system using a different scanner or staining protocol—a challenge underscored by the cross-dataset validation issues in Yang et al.,¹⁹ where ResNet-50 accuracy varied widely from 54% to 86% across different datasets (SYSU1, SYSU2, TCGA, and SZPH). The reliance on a few public datasets (LC25000, NCT-100K, Warwick-QU) creates a risk of ”benchmark overfitting,” where the research community collectively optimizes for performance on these specific data distributions, potentially neglecting the vast heterogeneity of real-world clinical data.¹³

5. Implications

5.1. Architecture design

Selecting an appropriate CNN architecture remains essential in shaping performance in classification tasks.¹⁰⁸ The Table 9 shows the factors which determine architecture design. A CNN model’s performance depends strongly on its design while the transformation of input data and implementation of convolutional and pooling layers, along with activation layers, depend entirely on its architectural design.¹⁰⁹ How well a model learns beneficial characteristics and patterns from input data depends mainly on its number of levels, types of layers,¹¹⁰ order of layers, and connectivity between layers.¹¹¹

Table 9.

CNN architecture and hyperparameter optimization strategies.

Component/hyperparameter	Key considerations and strategies
Architectural Components
Filter Design ¹¹²	Kernel size (3× 3 to 7× 7) defines receptive field and feature granularity. Stride controls the down-sampling rate.
Pooling Configuration ^109,110,113	Manages feature map down-sampling and spatial hierarchy (typical size: 2× 2 to 4× 4). Larger pools increase invariance but reduce resolution.
Channel Depth ^114,115	Number of filters often doubles per downsampling stage. Balances model capacity and computational cost.
Connectivity ^110,116	Skip connections (e.g., ResNet) enable deeper networks. Attention mechanisms dynamically weight feature relevance.
Activation Function ^117,118	ReLU: Standard, efficient. Leaky ReLU prevents dead neurons. GeLU: Smooth alternative for transformers.
Hyperparameters
Learning Rate ^119,120	Critical initial value (1e-3 to 1e-5). Schedules (Cosine Annealing) and warmup are essential.
Batch Size ^121,122	Small batches (32-64): Better generalization. Large batches (128-256): Faster training. Gradient accumulation mimics large batches.
Regularization ^112,123	Dropout (0.2-0.5): Prevents overfitting. L2 Weight Decay (1e-4 to 1e-6): Penalizes large weights. Batch Norm: Stabilizes training.
Stopping Criteria ^124,125	Early Stopping (patience 10-20 epochs) prevents overfitting by halting training when validation loss plateaus.

Among these factors, the convolutional filter settings determine the model’s complexity levels as well as the total number of feature learned.¹¹⁴ The size and resolution of output feature maps depend on pooling layers that use stride and size parameters to compress data over space.^111,117 Through the insertion of activation functions, models become nonlinear, which enhances their ability to detect subtle characteristics within the data.^113,118 The colon cancer image classification requires distinct combinations of convolutional, pooling, activation, dropout, and fully-connected layers.¹¹⁶

The efficiency of a CNN model depends on the correct activation selection¹¹⁸ during both training and validation processes. An appropriate choice of activation function enables neural networks to execute continuous function approximation, so as to realize medical image processing with tumor classification.¹²⁶ During the learning process, the training and updating methods employed for the model determine its ability to achieve solution convergence and its algorithm for optimal performance.^115,127 Lastly, the number of convolutional filters within architecture serves as a critical element feature extraction from input data.¹²⁸

In summary, architecture design of CNN models requires balancing complexity of task with available resources, as well as a mechanism to extract meaningful data patterns (features) from input histopathological images for classification tasks.

5.2. Hyperparameter finetuning

After the architecture design, a CNN model achieves its best results based on the quality and extent of the training data it receives.^121,124 The CNN model requires diverse and representative training datasets which include different colon cancer types at multiple status. In this case, a proper finetuning strategy on the hyperparameters, which are listed in Table 9, is equally critical as architecture design in terms of performance improvement.

To be specific, a minimum number of epochs leads to the model underfitting, but an excessive number of epochs increases the risk of overfitting.¹²⁵ Batch size is the number of samples combined for processing in each training iteration. Larger batch sizes applied during model training accelerates the learning process but also consume memory resources increasingly. The approach leads to higher memory needs and potentially weakens gradient precision.¹²¹ Furthermore, dropout rate (i.e., percentage of inhibitory nodes) selected for random removal from the network for overfitting reduction purposes.¹²³ The training process with this technique helps the model learn stronger features that show improved generalization potential for new and unknown data points in medical image processing tasks with high data variability.¹¹²

Models uses dropout method to attain superior test-retest results than models without dropout regardless of Monte Carlo testing.¹²⁹ Accurate disease detection and prediction becomes essential during medical image processing tasks. A model learning rate determines the speed of weight updates during training. The stability of a model stands in opposition to training speed of convergence while applying a high learning rate. Lower learning rate values create both slower convergence and worse model results.^119,120 The process of tuning CNN model hyperparameter remains equally important to CNN architecture development when developing efficient CNN models. These methods, like grid search, random search, and even Bayesian optimization, are often automated or done by hand to fine-tune the hyperparameters.¹²²

6. Recommendations to future research

This section provides a load of recommendations to future research (Figure 9). As indicated in the discussion, model architectures, data quality, and model optimization determine the performance of a CNN model. Further, the integration of a model regarding particular clinical setting also challenges onsite performance of a model. Lastly, as a supportive tool in diagnosis, the predictive result needs to be reinforced in the current diagnosis process by clinicians in terms of result visualization and interpretability improvement.

Figure 9.

Future research.

6.1. Quantum computing

In this review paper, the importance of model architecture design and hyperparameter finetuning were discused. From 2020, scholars^130,131 have discussed the revolutionary emerging quantum computing in model development.

For imaging and image processing tasks, quantum-based innovation (e.g, QCNN) has been used for certain image processing tasks. In the case of QCNN, models are able to overcome the challenges from small-sized datasets.¹³² Limited size and high variety in clinical sample influence the performance of model application. Quantum computing has shown its potential performance in corresponding medical imaging and image processing tasks by improving learning efficiency.

For the classification task, the potential improvement could occur from data pre-processing to the end of hyperparameter fine-tuning. Parameterized quantum circuits can represent certain complex decision boundaries more compactly than classical CNNs. Some studies^131,133 suggest quantum models can be more resilient to certain types of noise or adversarial perturbations. In this case, quantum computing could help with major challenges faced by pathologist in terms of variability across scanners, staining protocols, and sites.

6.2. Advanced analytics

Recent studies^134,135 identified the need for better interpretability in CNN models, an area of research that is likely to be fulfilled in future work. The inability to interpret the functioning of these models is a major problem for their therapeutic use. There is a need to develop CNN models along with interpretation methods that clinicians can understand so that they can better understand the model with prediction reasoning in a supportive decision-making process. Regarding result visualization, future efforts should focus on developing sophisticated visualization tools that can effectively display detection results through interactive heatmaps, region-specific confidence scores, and annotated overlays that highlight suspicious areas in real-time during colonoscopy and histopathological procedures.^5,136

Cross-validation for CNNs is essential for several critical reasons. First, it ensures the robustness and generalizability of AI models across diverse patient populations and clinical settings. Through rigorous cross-validation across different medical centers, patient cohorts, and time periods, researchers can validate that their models maintain consistent performance beyond their initial training environment. A model with high overall accuracy might still have clinically unacceptable false-negative rates, which misclassify malignant cases as benign. Focusing solely on accuracy overlooks other clinically vital measures (sensitivity, specificity, precision, and the AUC). True reproducibility requires not only open data and code, but also comprehensive documentation of all preprocessing steps (e.g., CLAHE augmentation in Ref. 29, hyperparameter tuning processes (as detailed in Table 9 regarding learning rates, batch sizes, and regularization strategies), precise architecture definitions, and the clinical measures.

6.3. Lightweight clinical integrations

Colon cancer outcomes are highly dependent on the stage at which the disease is diagnosed. For the proper integration of CNN-based CDSS into clinical settings, linking them to existing healthcare systems is required for smart medication development.¹³⁶ Studies^108,109 suggested that researchers should modify CNN variant model structures to improve early-stage detection performance. However, early-stage lesions are often small, subtle, and easily missed by both human observers and current automated systems. The identification of tiny and early-stage colon cancer lesions remains challenging for CNN models. Small lesions in low-resolution images can escape both human and CNN model detection because current models either overlook them or issue false positive identifications. Early detection aligns with the broader trend in medicine toward preventive care and minimally invasive intervention. By catching cancer earlier, clinicians can intervene sooner, often with less aggressive treatments, reducing patient morbidity and healthcare costs.

The lightweight CNN models delivered a 99.6% accuracy rate in diagnosing lung and colon cancer images while showing their capacity to process histopathological image.¹⁰² Future work should focus on developing lightweight architectures that maintain high diagnostic performance while reducing computational demands, enabling real-time analysis and deployment in resource-limited settings. Lightweight CNN architectures such as Mobile-Net, Efficient-Net, and Shuffle-Net demonstrate powerful performances in identifying colon cancer. The models excel in performance efficiency and accuracy levels suitable for mobile utilization and real-time applications.

Future end-to-end solutions should encompass the entire pipeline from image acquisition through automated analysis to result visualization and clinical decision support.⁴ Research efforts should focus on creating unified systems that automatically handle preprocessing steps, apply optimized CNN models for detection and classification, and present results in an interpretable format directly within existing hospital information systems. The end-to-end approach should emphasize real-time processing capabilities, robust error handling, and automatic quality control measures to ensure reliable performance in clinical settings.

7. Conclusion

Key findings of the paper contribute the following points. First, the paper survey statistically pointed to an increasing research interest in CNN applications to medical imaging and image processing and further in colon cancer classification from 2000 to early 2025 (Figure 1).

Using the PRISMA framework, 85 studies were included in the final review (Figure 2). Comparison revealed bi-and multi-classification benchmark studies among state-of-the-art CNN architectures (Table 8) with their best accuracy results. For bi-classification tasks: Res-Net (99.77%) in Ref. 24, Xception (99.95%) in Ref. 43, VGG-Net (99.85%) in Ref. 59, Dense-Net (99.60%) in Ref. 80, and Efficient-Net (99.97%) in Ref. 88 and 89. For the multi-classification task, Res-Net (99.67%),²⁹ Inception (92.74%),⁴⁹ VGG-Net (99.76%),⁵⁸ Dense-Net (99.96%),⁷³ and Efficient-Net (99.87%).⁸⁵

Furthermore, the potential challenges in current CNN development were summarized as aiming for a simple and efficient architecture and effective hyperparameter fine-tuning (Table 9). Lastly, the future research recommendations were proposed including quantum AI advancement, lightweight model design, and advanced analytics (Figure 9).

This review has several limitations. First, restricting the search to three databases may have excluded relevant studies. Second, due to the inconsistency of the secondary metrics adopted in benchmark studies over the past years, accuracy was the only widely used metric for comparison. However, focusing primarily on accuracy as the comparative metric overlooks other clinically important measures. The heterogeneous reporting of these metrics across the literature highlights the need for standardized evaluation protocols in future research. Third, the inclusion threshold of $\leq 85 %$ accuracy may have excluded methodologically novel but lower-performing studies. In the future, the authors aim to come up with a quantum-based lightweight CNN architecture for colon cancer with imaging techniques (data cleaning, image segmentation, and object registration), aiming for excelling interpretable result in clinical contexts.

Footnotes

Acknowledgement

This study is supported by TIRGS-ILG/1/2023/SCS/001 Taylor’s Internal Research Grant Scheme - Impact Lab Grant. Special thanks to Hebei Academy of Fine Arts for the collaborative support.

ORCID iDs

Jie Li

N. Z. Jhanjhi

Ethical considerations

This study is a systematic review of previously published literature. Therefore, direct ethical approval from an institutional review board was not required. The review was conducted in accordance with established scholarly principles for systematic reviews.

Funding

The authors disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: This research is funded by Taylor’s Internal Research Grant Scheme - Impact Lab Grant (TIRGS-ILG/1/2023/SCS/001).

Declaration of conflicting interests

The authors declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

Data Availability Statement

The PROBAST protocol and result in PRISMA review can be accessed via: https://doi.org/10.7910/DVN/ZQYLAL ()

Contributorship

Jie Li collected data and composed the manuscript. Weiwei Goh and Noor Zaman Jhanjhi validated PROBAST review result and proofread the manuscript. Ting Li coordinated the references.

Guarantor

Jie Li (jie.li@taylors.edu.my).

Weiwei Goh (weiwei.goh@taylors.edu.my).

Noor Zaman Jhanjhi (noorzaman.jhanjhi@taylors.edu.my).

School of Computer Science, Taylor’s University.

References

Opee

Eva

Noor

, et al. ELW-CNN: An extremely lightweight convolutional neural network for enhancing interoperability in colon and lung cancer identification using explainable AI. *Healthcare Technology Letters* 2025; 12(1): e12122. https://doi.org/10.1049/htl2.12122

Zangana

Mohammed

Mustafa

. Advancements and applications of convolutional neural networks in image analysis: A comprehensive review. *Jurnal Ilmiah Computer Science* 2024; 3(1): 16–29. https://doi.org/10.58602/jics.v3i1.30

Nambiar

Bhat

Achar

. Advancements in hematologic malignancy detection: A comprehensive survey of methodologies and emerging trends. *The Scientific World Journal* 2025; 2025(1): 1671766. https://doi.org/10.1155/tswj/1671766

Klang

Brill

Soffer

, et al. Deep learning and gastric cancer: Systematic review of AI-assisted endoscopy. *Diagnostics* 2023; 13(24): 3613. https://doi.org/10.3390/diagnostics13243613

Hasan

Islam

Uddin

, et al. An end-to-end lightweight multi-scale CNN for the classification of lung and colon cancer with XAI integration. *Technologies* 2024; 12(4): 56. https://doi.org/10.3390/technologies12040056

Tanwar

Singh

Shree

, et al. [Retracted] Detection and classification of colorectal polyp using deep learning. *BioMed Research International* 2022; 2022(1): 2805607. https://doi.org/10.1155/2022/2805607

Ben Saad

Facciolo

Davy

. On the importance of large objects in CNN based object detection algorithms. In: *Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision*, Waikoloa, HI, USA, 03-08 January 2024.

Gao

Mosalam

. Deep learning visual interpretation of structural damage images. *Journal of Building Engineering* 2022; 60: 105144. https://doi.org/10.1016/j.jobe.2022.105144

Zhi

Sun

Wang

, et al. Support vector machine classifier for prediction of the metastasis of colorectal cancer. *International Journal of Molecular Medicine* 2018; 41(3): 1419–1426. https://doi.org/10.3892/ijmm.2018.3359

10.

Jiang

Wang

Liu

, et al. Deep learning for medical image-based cancer diagnosis. *Cancers* 2023; 15(14): 3608. https://doi.org/10.3390/cancers15143608

11.

Bhatt

Patel

Talsania

, et al. CNN variants for computer vision: History, architecture, application, challenges and future scope. *Electronics* 2021; 10(20): 2470. https://doi.org/10.3390/electronics10202470

12.

. Survey data on CNN, medical imaging, and colon cancer publication in IEEE, Science Direct, and Springer Nature. Harvard Dataverse, 2025, Version V2. https://doi.org/10.7910/DVN/ZQYLAL.

13.

Peek

Capurro

Rozova

, et al. Bridging the gap: Challenges and strategies for the implementation of artificial intelligence-based clinical decision support systems in clinical practice. *Yearbook of Medical Informatics* 2024; 33(01): 103–114. https://doi.org/10.1055/s-0044-1800729

14.

Wang

Chen

Zhang

, et al. Quantum-inspired neural architecture search for clinical decision support systems. *Nature Digital Medicine* 2024; 7(1): 1–15.

15.

Wahid

Nisa’

Amaliyah

, et al. Lung and Colon Cancer Detection with Convolutional Neural Networks on Histopathological Images. *AIP Conference Proceedings*. AIP Publishing, 2023, vol 2654, no. 1, p. 020020. https://doi.org/10.1063/5.0114327

16.

Kim

Tomita

Suriawinata

, et al. Detection of colorectal adenocarcinoma and grading dysplasia on histopathologic slides using deep learning. *The American Journal of Pathology* 2023; 193(3): 332–340. https://doi.org/10.1016/j.ajpath.2022.12.003

17.

Wang

Shi

Nie

, et al. Prediction of colorectal cancer microsatellite instability and tumor mutational burden from histopathological images using multiple instance learning. *Biomedical Signal Processing and Control* 2025; 104: 107608. https://doi.org/10.1016/j.bspc.2025.107608

18.

Sarwinda

Paradisa

Bustamam

, et al. Deep learning in image classification using residual network (ResNet) variants for detection of colorectal cancer. *Procedia Computer Science* 2021; 179: 423–431. https://doi.org/10.1016/j.procs.2021.01.025

19.

Yang

Chen

Cheng

, et al. Deep learning-based six-type classifier for lung cancer and mimics from histopathological whole slide images: a retrospective study. *BMC Medicine* 2021; 19(1): 80. https://doi.org/10.1186/s12916-021-01953-2

20.

Paing

Pintavirooj

. Adenoma dysplasia grading of colorectal polyps using fast fourier convolutional ResNet (FFC-ResNet). *IEEE Access* 2023; 11: 16644–16656. https://doi.org/10.1109/access.2023.3246730

21.

Mulyadi

Utaminingrum

. Comparative analysis of ResNet architecture enhanced with self-attention for colorectal cancer detection. In: *Proceedings of the 2024 International Conference on Intelligent Cybernetics Technology & Applications (ICICyTA)*, Bali, indonesia, 17-19 December 2024, pp. 1089–1094. IEEE.

22.

Karthik

Thalanki

Yadav

. Deep learning-based histopathological analysis for colon cancer diagnosis: a comparative study of CNN and transformer models with image preprocessing techniques. In: *Proceedings of the International Conference on Intelligent Systems Design and Applications*, 24 July 2024, pp. 90–101. Springer.

23.

Muneer

Taib

Hasan

, et al. Colorectal cancer recognition using deep learning on histopathology images. In: *Proceedings of the 2023 13th International Conference on Information Technology in Asia (CITA)*, Kuching, Malaysia, 2023, August, pp. 25–30. IEEE.

24.

Peng

C-C

Lee

B-R

. Enhancing colorectal cancer histological image classification using transfer learning and ResNet50 CNN model. In: *Proceedings of the 2023 IEEE 5th Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability (ECBIOS)*, Tainan, Taiwan, 02-04 June 2023, pp. 36–40. IEEE.

25.

Bhattacharya

Saha

Chattopadhyay

, et al. Deep feature selection using adaptive β-Hill Climbing aided whale optimization algorithm for lung and colon cancer detection. *Biomedical Signal Processing and Control* 2023; 83: 104692. https://doi.org/10.1016/j.bspc.2023.104692

26.

Venkatachalam

Shah

. Hybrid deep learning model combining Xception and ResNet with backpropagation and SGD for robust lung and colon cancer classification. *IEEE Access* 2025; 13: 131483.

27.

Gowthamy

Ramesh

. A novel hybrid model for lung and colon cancer detection using pre-trained deep learning and KELM. *Expert Systems with Applications* 2024; 252: 124114. https://doi.org/10.1016/j.eswa.2024.124114

28.

Haq

Zhang

Sun

, et al. YOLO and residual network for colorectal cancer cell detection and counting. Heliyon 2024; 10(2): e24403.

29.

Alzubaidi

Al-Sabaawi

Fadhel

, et al. ResNet110 and mask recurrent convolutional neural network based detection and classification of colorectal cancer. In: *Proceedings of the 2024 International Conference on Distributed Computing and Optimization Techniques (ICDCOT)*, Bengaluru, India, 15-16 March 2024. IEEE.

30.

Vinod Kumar

Suresh

Srinivasan

, et al. CoC-ResNet-classification of colorectal cancer on histopathologic images using residual networks. *Multimedia Tools and Applications* 2024; 83(19): 56965–56989.

31.

Deiva Nayagam

Selvathi

Selvaraj

. Transfer learning approach with ResNet architecture for colon cancer classification using histopathological images. In: *Models and Methods for Systems Engineering*. Springer, 2025, pp. 143–153.

32.

Chen

. Grouped multi-scale vision transformer for medical image segmentation. *Scientific Reports* 2025; 15(1): 11122. https://doi.org/10.1038/s41598-025-95361-8

33.

Iizuka

Kanavati

Kato

, et al. Deep Learning Models for Histopathological Classification of Gastric and Colonic Epithelial Tumours. *Scientific Reports* 2020; 10(1): 1504. https://doi.org/10.1038/s41598-020-58467-9

34.

Shaban

Awan

Fraz

, et al. Context-aware convolutional neural network for grading of colorectal cancer histology images. *IEEE Transactions on Medical Imaging* 2020; 39(7): 2395–2405. https://doi.org/10.1109/TMI.2020.2971006

35.

Omar

Hussein

Omer

, et al. Lung and colon cancer detection using weighted average ensemble transfer learning. In: *2023 11th International Symposium on Digital Forensics and Security (ISDFS)*, Chittagong, Bangladesh, 23-25 February 2023, pp. 1–7. IEEE.

36.

Belciug

. Learning Deep Neural Networks Architectures Using Differential Evolution: Case Study—Medical Imaging Processing. *Computers in Biology and Medicine* 2022; 146: 105623. https://doi.org/10.1016/j.compbiomed.2022.105623

37.

Swarna

Hashi

. Detection of colon cancer using inception v3 and ensembled CNN model. In: *2023 International Conference on Electrical, Computer and Communication Engineering (ECCE)*, Chittagong, Bangladesh, 23-25 February 2023. IEEE.

38.

Rupesh

Goutham

Senthur

, et al. Enhanced Colon Cancer Screening with Endoscopic Images Using Deep Learning Techniques. In: *2024 5th International Conference on Communication Computing & Industry 6.0 (C2I6)*, Bengaluru, India, 06-07 December 2024, pp. 1–6.

39.

Wang

K-S

, et al. Accurate diagnosis of colorectal cancer based on histopathology images using artificial intelligence. *BMC Medicine* 2021; 19(1): 76. https://doi.org/10.1186/s12916-021-01942-5

40.

Appavu

. AI Deep Learning Techniques for Automating Cancer Detection and Classifying Pictures of Various Cancers. In: *2025 6th International Conference on Recent Advances in Information Technology (RAIT)*, Dhanbad, India, 06-08 March 2025, pp. 1–6. https://doi.org/10.1109/RAIT65068.2025.11089317

41.

Ochoa-Ornelas

Guzmán-Marín

Rangel-Peraza

. A hybrid deep learning and machine learning approach with Mobile-EfficientNet and Grey Wolf Optimizer for lung and colon cancer histopathology classification. *Cancers* 2024; 16(22): 3791. https://doi.org/10.3390/cancers16223791

42.

Merabet

Saighi

Ferradji

, et al. Enhancing colon cancer prediction in histopathology with integrated deep learning models: A comparative study on the lc25000 dataset. In: *2024 6th International Conference on Pattern Analysis and Intelligent Systems (PAIS)*, EL OUED, Algeria, 24-25 April 2024, pp. 1–7. IEEE.

43.

Kumar

Misra

. Colon cancer classification and detection by novel CMNV2 model and methods of deep learning. *Neural Computing and Applications* 2025; 37(1): 25–41. https://doi.org/10.1007/s00521-024-10563-x

44.

Radhakrishnan

DPP

Aravind

Nambiar

, et al. Detection of Non-small cell Lung Cancer using Histopathological Images by the approach of Deep Learning. In: *2022 2nd International Conference on Intelligent Technologies (CONIT)*, Hubli, India, 24-26 June 2022, pp. 1–11.

45.

Ribeiro

Teles

FRS

Diniz

JOB

, et al. Improving Colorectal Cancer Diagnosis Using MIRNet and InceptionV3 on Histopathological Images. In: *Proceedings of the Brazilian Conference on Intelligent Systems*, Belém – PA, Brazil, November 17 to 21, 2024, pp. 321–334. Springer.

46.

Aydin

Ölçer

. Classification of Histopathological Images of Colorectal Cancer with Deep Learning Models: A Comparative Study. In: *Proceedings of the 2024 Medical Technologies Congress (TIPTEKNO)*, Mugla, Turkiye, 10-12 October 2024, pp. 1–4. IEEE.

47.

Gupta

Kumar

, et al. Multi-class classification of colorectal cancer tissues using pre-trained CNN models. In: *TENCON 2022-2022 IEEE Region 10 Conference (TENCON)*, Hong Kong, 01-04 November 2022, pp. 1–6.

48.

Patnaik

Rath

Padhy

, et al. Histopathological colorectal cancer image classification by using inception V4 CNN model. In: *International Conference on Robotics, Control, Automation and Artificial Intelligence*, Manipal, India, November 24-26, 2022, pp. 1003–1014. Springer.

49.

Kumar

Vishwakarma

Bajaj

. Crccn-net: Automated framework for classification of colorectal tissue using histopathological images. *Biomedical Signal Processing and Control* 2023; 79: 104172. https://doi.org/10.1016/j.bspc.2022.104172

50.

Uyar

Dirilenoglu

Mirzaei

, et al. Colon adenocarcinoma diagnosis on histopathological images using deep learning. In: *Artificial Intelligence of Things (AIoT)*. Elsevier, 2025, pp. 247–254.

51.

Tweedale

. Ship Detection Using Machine Learning and Optical Imagery in the Maritime Environment. In: *Machine Learning Paradigms: Applications of Learning and Analytics in Intelligent Systems*. Springer International Publishing, 2019, pp. 461–474.

52.

Alhazmi

Turki

. Applying deep transfer learning to assess the impact of imaging modalities on colon cancer detection. *Diagnostics* 2023; 13(10): 1721. https://doi.org/10.3390/diagnostics13101721

53.

Anju

Vimala

. Finetuned-VGG16 CNN model for tissue classification of colorectal cancer. In: *International Conference on Intelligent Sustainable Systems*, KL, Malaysia, 7-8, Sept, 2023, pp. 73–84. Springer.

54.

Bakht

Javed

AlMarzouqi

, et al. Colorectal cancer tissue classification using semi-supervised hypergraph convolutional network. In: *Proceedings of the 2021. IEEE 18th International Symposium on Biomedical Imaging (ISBI)*, Nice, France, 13-16 April 2021, pp. 1306–1309. IEEE.

55.

Kather

Weis

C-A

Bianconi

, et al. Multi-class texture analysis in colorectal cancer histology. *Scientific Reports* 2016; 6: 27988. https://doi.org/10.1038/srep27988

56.

Hamida

Devanne

Weber

, et al. Deep Learning for Colon Cancer Histopathological Images Analysis. *Computers in Biology and Medicine* 2021; 136: 104730. https://doi.org/10.1016/j.compbiomed.2021.104730

57.

Karabulut

Selen

Yaganoglu

, et al. Recognition of colon polyps (tubular adenoma, villous adenoma) and normal colon epithelium histomorphology with transfer learning. *The Eurasian Journal of Medicine* 2024; 56(1): 35–41. https://doi.org/10.5152/eurasianjmed.2024.23130

58.

Khazaee Fadafen

Rezaee

. Ensemble-based multi-tissue classification approach of colorectal cancer histology images using a novel hybrid deep learning framework. *Scientific Reports* 2023; 13(1): 8823. https://doi.org/10.1038/s41598-023-35431-x

59.

Al-Jabbar

Alshahrani

Senan

, et al. Histopathological analysis for detecting lung and colon cancer malignancies using hybrid systems with fused features. *Bioengineering* 2023; 10(3): 383. https://doi.org/10.3390/bioengineering10030383

60.

Singh

Kashyap

Singh

. Lung and colon cancer classification of histopathology images using convolutional neural network. *SN Computer Science* 2024; 5(2): 223. https://doi.org/10.1007/s42979-023-02546-x

61.

Rawashdeh

Obaidat

Abouali

, et al. A deep learning-driven approach for detecting lung and colon cancer using pre-trained neural networks. In: *2024 IEEE 21st International Conference on Smart Communities: Improving Quality of Life using AI, Robotics and IoT (HONET)*, Doha, Qatar, 03-05 December 2024, pp. 183–188.

62.

Yıldız

Yakut

. Diagnostic decision making on medical images using deep learning models. *Euroasia Journal of Mathematics, Engineering, Natural & Medical Sciences* 2023; 10(28): 130–142.

63.

Oubaalla

Elmoubtahij

Elakkad

. Detection of lung and colon cancer using transfer and ensemble learning. In: *Proceedings of the 7th International Conference on Networking, Intelligent Systems and Security*, Meknes, AA, Morocco, April 18 - 19, 2024, pp. 1–7.

64.

Hasan

Oraibi

. Lung and Colon Cancer Classification Based on a Hybrid Deep Convolutional Neural Networks of Xception, VGG-16, and VGG-19 Using Histopathological Images. In: *World Congress in Computer Science, Computer Engineering & Applied Computing*. Springer, 2024, pp. 349–358.

65.

Hadiyoso

Aulia

Irawati

. Diagnosis of Lung and Colon Cancer Based on Clinical Pathology Images Using Convolutional Neural Network and CLAHE Framework. *International Journal of Applied Science and Engineering* 2023; 20(1): 1–7. https://doi.org/10.6703/ijase.202303_20(1).006

66.

Singh

. An approach to classify lung and colon cancer of histopathology images using deep feature extraction and an ensemble method. *International Journal of Information Technology* 2023; 15(8): 4149–4160. https://doi.org/10.1007/s41870-023-01487-1

67.

Akar

Abou Diab

Sbeity

, et al. A comparative study for lung, colon and breast cancer diagnosis using different convolutional neural networks. In: *2023 Seventh International Conference on Advances in Biomedical Engineering (ICABME)*, Beirut, Lebanon, 12-13 October 2023, pp. 75–78.

68.

Farhadipour

. Lung and colon cancer detection with convolutional neural networks and adaptive histogram equalization. *Iran Journal of Computer Science* 2024; 7(2): 381–395. https://doi.org/10.1007/s42044-023-00161-w

69.

Annaiah

NAKJ

Thirupathi Rao

Omkar Lakshmi Jagan

. An integrated model for colon cancer detection from histopathology images. In: *International Conference on Advances in Distributed Computing and Machine Learning*, Taipei, Taiwan, 9th to 10th January 2025, pp. 157–168. Springer Nature Singapore.

70.

Ohata

Chagas

JVS

Bezerra

, et al. A novel transfer learning approach for the classification of histological images of colorectal cancer. *The Journal of Supercomputing* 2021; 77(9): 9494–9519. https://doi.org/10.1007/s11227-020-03575-6

71.

Sarkar

Hazra

Das

. Classification of colorectal cancer histology images using image reconstruction and modified DenseNet. In: *Proceedings of the International Conference on Computational Intelligence in Communications and Business Analytics*, West Bengal, India, 7-9, Jan, 2021, pp. 259–271. Springer.

72.

Ghosh

Bandyopadhyay

Sahay

, et al. Colorectal histology tumor detection using ensemble deep neural network. *Engineering Applications of Artificial Intelligence* 2021; 100: 104202. https://doi.org/10.1016/j.engappai.2021.104202

73.

Uddin

Chen

Akter

, et al. Colon and Lung Cancer Classification from Multi-Modal Images Using Resilient and Efficient Neural Network Architectures. *Heliyon* 2024; 10(9): e30625. https://doi.org/10.1016/j.heliyon.2024.e30625

74.

Eliwa

Mohamed El Koshiry

Abd El-Hafeez

, et al. Secure and Transparent Lung and Colon Cancer Classification Using Blockchain and Microsoft Azure. *Advances in Respiratory Medicine* 2024; 92(5): 395–420. https://doi.org/10.3390/arm92050037

75.

Ajay

Karthik

Bisht

, et al. QDeepColonNet: a quantum-based deep learning network for colorectal cancer classification using attention-driven DenseNet and shuffled dynamic local feature extraction network. *Artificial Intelligence Review* 2025; 58(10): 304. https://doi.org/10.1007/s10462-025-11295-7

76.

Lauande

MGM

Braz Junior

de Almeida

JDS

, et al. Building a DenseNet-based neural network with transformer and MBConv blocks for penile cancer classification. *Applied Sciences* 2024; 14(22): 10536. https://doi.org/10.3390/app142210536

77.

Narasimha Raju

Jayavel

Rajalakshmi

. Histopathology exploratory evidence of discrepancy detection of carcinoma in the colorectal region using integrated CNN-GradCAM. In: *AIP Conference Proceedings*, Hyderabad, India, 22–24 April 2022, vol 2754, p. 070001. AIP Publishing LLC. https://doi.org/10.1063/5.0161070

78.

Sengupta

Chyrmang

Bora

, et al. Assessment of different U-Net backbones in segmenting colorectal adenocarcinoma from H&E histopathology. *Pathology-Research and Practice* 2025; 266: 155820. https://doi.org/10.1016/j.prp.2025.155820

79.

Kumar

Sharma

Singh

, et al. An empirical study of handcrafted and dense feature extraction techniques for lung and colon cancer classification from histopathological images. *Biomedical Signal Processing and Control* 2022; 75: 103596. https://doi.org/10.1016/j.bspc.2022.103596

80.

Hasan

Islam

Ahmed

, et al. Prediction of colon cancer using densenet121, cnn, and resnet50 machine learning models and using image processing techniques. In: *2023 International Conference on Artificial Intelligence Robotics, Signal and Image Processing (AIRoSIP)*, Yogyakarta, Indonesia, 09-10 August 2023, pp. 296–301. IEEE.

81.

Di Giammarco

Martinelli

Santone

, et al. Colon Cancer Diagnosis by Means of Explainable Deep Learning. *Scientific Reports* 2024; 14(1): 15334. https://doi.org/10.1038/s41598-024-63659-8

82.

Izzaty

AMK

Cenggoro

Elwirehardja

, et al. Multiclass Classification of Histology on Colorectal Cancer Using Deep Learning. *Communications in Mathematics, Biology and Neuroscience* 2022; 2022: 1, Article-ID.

83.

Anagun

Isik

Seke

. SRLibrary: Comparing Different Loss Functions for Super-Resolution over Various Convolutional Architectures. *Journal of Visual Communication and Image Representation* 2019; 61: 178–187. https://doi.org/10.1016/j.jvcir.2019.03.027

84.

Prezja

Annala

Kiiskinen

, et al. Improving performance in colorectal cancer histology decomposition using deep and ensemble machine learning. *Heliyon* 2024; 10(18): e11925. https://doi.org/10.1016/j.heliyon.2024.e37561

85.

Abd El-Ghany

Mahmood

Abd El-Aziz

. Adaptive dynamic learning rate optimization technique for colorectal cancer diagnosis based on histopathological image using EfficientNet-B0 deep learning model. *Electronics* 2024; 13(16): 3126. https://doi.org/10.3390/electronics13163126

86.

. Transformer-Based Self-Supervised Learning and Distillation for Medical Image Classification: Improving Colorectal Cancer Detection on NCT-CRC-HE-100K with Swin-T V2. In: *2024 3rd International Conference on Cloud Computing, Big Data Application and Software Engineering (CBASE)*, Hangzhou, China, 11-13 October 2024, pp. 644–648. IEEE.

87.

Maheshwari

Kiranmayee

Suresh

. Diagnose colon and lung cancer histopathological images using pre-trained machine learning model. In: *2022 5th International Conference on Contemporary Computing and Informatics IC3I)*, Uttar Pradesh, India, 14-16 December 2022, pp. 1078–1082.

88.

Saba

Zafar

Suleman

, et al. A synergistic approach to colon cancer detection: Leveraging EfficientNet and NSGA-II for enhanced diagnostic performance. *IEEE Access* 2024; 12: 192264.

89.

Taher

Ayon

WIZ

Hossain

MDS

. Histopathological image-based classification of lung and colon cancer using deep learning architectures with preprocessing enhancements. In: *2024 27th International Conference on Computer and Information Technology (ICCIT)*, Cox's Bazar, Bangladesh, 20-22 December 2024, pp. 1986–1991.

90.

Kallipolitis

Revelos

Maglogiannis

. Ensembling EfficientNets for the Classification and Interpretation of Histopathology Images. *Algorithms* 2021; 14(10): 278. https://doi.org/10.3390/a14100278

91.

Ahuja

Dhiman

Singh

, et al. Deep learning for cancer detection: efficiency of EfficientNetB3 vs CNN in histopathological image classification. In: *2025 6th International Conference for Emerging Technology (INCET)*, BELGAUM, India, 23-25 May 2025, pp. 1–6.

92.

Shourie

Anand

Gupta

. Colon and lung cancer classification of histopathological images using efficientnetb7. In: *2023 3rd Asian Conference on Innovation in Technology (ASIANCON)*, Ravet IN, India, 25-27 August 2023, pp. 1–5.

93.

Sathyanarayana

Alampally

Akella

, et al. ColoViT: a synergistic integration of EfficientNet and vision transformers for advanced colon cancer detection. *Journal of Cancer Research and Clinical Oncology* 2025; 151(7): 1–19. https://doi.org/10.1007/s00432-025-06199-6

94.

Kaaviyakanth

Begam

, et al. AI Driven Dual Modal Diagnostic Tool for Colon Cancer Detection. In: *2025 10th International Conference on Communication and Electronics Systems (ICCES)*, Coimbatore, India, 28-30 October 2025, pp. 1695–1702.

95.

Ramesh

Anbukaruppusamy

Dineshkumar

. Performance improvement of lung cancer multiclass classification on transformer convolution neural networks using histopathological images. In: *2025 6th International Conference for Emerging Technology (INCET)*, Karnataka, India, May 23-25, 2025, pp. 1–6.

96.

Mehta

Kaur

. Histopathological image classification: EfficientNetB3 vs custom CNN for cancer detection. In: *2025 IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI)*, Gwalior, India, 06-08 March 2025, vol 3, pp. 1–5. IEEE. https://doi.org/10.1109/iatmsi64286.2025.10985155

97.

Jain

Kaur

. Deep learning for accurate histopathological classification of lung and colon cancer using CNN and EfficientNetB3 models. In: *2024 2nd International Conference on Advances in Computation, Communication and Information Technology (ICAICCIT)*, Faridabad, India, 28-29 November 2024, vol 1, pp. 419–424. IEEE. https://doi.org/10.1109/icaiccit64383.2024.10912433

98.

Ochoa-Ornelas

Gudiño-Ochoa

García-Rodríguez

, et al. A robust transfer learning approach with histopathological images for lung and colon cancer detection using EfficientNetB3. *Healthcare Analytics* 2025; 7: 100391. https://doi.org/10.1016/j.health.2025.100391

99.

Singh

Sharma

Gupta

. Lung and colon cancer classification using efficientnet b3 transfer learning model. In: *2023 World Conference on Communication & Computing (WCONF)*, RAIPUR, India, 14-16 July 2023, pp. 1–5.

100.

Shanto

Reza

Islam

, et al. From pixels to diagnosis: An innovative EfficientNetB3 approach for interpreting lung and colon cancer histopathology. In: *2024 27th International Conference on Computer and Information Technology (ICCIT)*, Cox's Bazar, Bangladesh, 20-22 December 2024, pp. 357–362. IEEE.

101.

Bharath

Raja

Kalaivanan

, et al. Accurate colorectal cancer detection using a random hinge exponential distribution coupled attention network on pathological images. *Abdominal Radiology* 2025; 50: 1–30. https://doi.org/10.1007/s00261-024-04770-2

102.

Ochoa-Ornelas

Gudiño-Ochoa

García-Rodríguez

. A Hybrid Deep Learning and Machine Learning Approach with Mobile-EfficientNet and Grey Wolf Optimizer for Lung and Colon Cancer Histopathology Classification. *Cancers* 2024; 16(22): 3791. https://doi.org/10.3390/cancers16223791

103.

Raseena

Kumar

Balasundaram

. A Residual Learning Approach Towards the Diagnosis of Colorectal Disease Effectively In: Santosh, K., et al. Recent Trends in Image Processing and Pattern Recognition. RTIP2R 2023 Communications in Computer and Information Science, vol 2027. Springer, Cham. 2024. https://doi.org/10.1007/978-3-031-53085-2_14

104.

Raseena

Kumar

Balasundaram

. Exploring the Effectiveness of Deep Learning Architectures for Colorectal Polyp Detection: Performance Analysis and Insights. *SN Computer Science* 2024; 5(452): 452. https://doi.org/10.1007/s42979-024-02825-1

105.

Haryanto

Al Farel

Suhartanto

, et al. A robust transfer learning approach for colorectal cancer identification based on histopathology images. *Research on Biomedical Engineering* 2024; 40: 753–767. https://doi.org/10.1007/s42600-024-00375-2

106.

Dabass

Vashisth

Vig

. A convolution neural network with multi-level convolutional and attention learning for classification of cancer grades and tissue structures in colon histopathological images. *Computers in Biology and Medicine* 2022; 147: 105680. https://doi.org/10.1016/j.compbiomed.2022.105680

107.

Sichuan University of Science and Engineering . EL-CNN: an Enhanced Lightweight Classification Method for Colorectal Cancer Histopathological Images. *Biomedical Signal Processing and Control* 2025; 100: Forthcoming.

108.

Yin

Qin

Hou

, et al. A Convolutional Neural Network–Based Model for Supply Chain Financial Risk Early Warning. *Computational Intelligence and Neuroscience* 2022; 2022(1): 7825597. https://doi.org/10.1155/2022/7825597

109.

Wang

Chen

Chakraborty

, et al. Orthogonal Convolutional Neural Networks. In: *Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition*, Seattle, WA, USA, 13-19 June 2020.

110.

Ayadi

Elhamzi

Charfi

, et al. Deep CNN for Brain Tumor Classification. *Neural Processing Letters* 2021; 53: 671–700. https://doi.org/10.1007/s11063-020-10398-2

111.

Tang

Jing

Zeng

, et al. Adaptive CU Split Decision with Pooling-Variable CNN for VVC Intra Encoding. In: *2019 IEEE Visual Communications and Image Processing (VCIP)*, Sydney, NSW, Australia, 01-04 December 2019. IEEE.

112.

Raiaan

MAK

Sakib

Fahad

, et al. A Systematic Review of Hyperparameter Optimization Techniques in Convolutional Neural Networks. *Decision Analytics Journal* 2024; 11: 100470. https://doi.org/10.1016/j.dajour.2024.100470

113.

Zhao

Zhonglin

. An Improved Pooling Method for Convolutional Neural Networks. *Scientific Reports* 2024; 14(1): 1589.

114.

Abed

Akrout

Amous

. Semantic Heads Segmentation and Counting in Crowded Retail Environment with Convolutional Neural Networks Using Top View Depth Images. *SN Computer Science* 2022; 4(1): 61. https://doi.org/10.1007/s42979-022-01467-5

115.

Lateef

Abbas

. Tuning the Hyperparameters of the 1D CNN Model to Improve the Performance of Human Activity Recognition. *Engineering and Technology Journal* 2022; 40(4): 547–554. https://doi.org/10.30684/etj.v40i4.2054

116.

Habib

Qureshi

. Optimization and Acceleration of Convolutional Neural Networks: A Survey. *Journal of King Saud University–Computer and Information Sciences* 2022; 34(7): 4244–4268. https://doi.org/10.1016/j.jksuci.2020.10.004

117.

Duan

Chapeau-Blondeau

Abbott

. Optimized Injection of Noise in Activation Functions to Improve Generalization of Neural Networks. *Chaos, Solitons & Fractals* 2024; 178: 114363. https://doi.org/10.1016/j.chaos.2023.114363

118.

Dubey

Jain

. Comparative Study of Convolution Neural Network’s ReLU and Leaky-ReLU Activation Functions. In: *Applications of Computing, Automation and Wireless Systems in Electrical Engineering: Proceedings of MARC 2018*, Xi'an, China, May 31, 2019. Springer Singapore.

119.

Luo

Xiong

Liu

, et al. Adaptive Gradient Methods with Dynamic Bound of Learning Rate. Proceedings of the 7th International Conference on Learning Representations, New Orleans, Louisiana. 2019 2019.

120.

Cutkosky

Defazio

Mehta

. Mechanic: A Learning Rate Tuner. In: *Advances in Neural Information Processing Systems 36*. Curran Associates Inc., 2023, pp. 47828–47848.

121.

Zhang

Nado

, et al. Which Algorithmic Choices Matter at Which Batch Sizes? Insights from a Noisy Quadratic Model. In: *Advances in Neural Information Processing Systems 32*. Curran Associates Inc., 2019, p. 8196.

122.

Rimal

Sharma

Alsadoon

. The Accuracy of Machine Learning Models Relies on Hyperparameter Tuning: Student Result Classification Using Random Forest, Randomized Search, Grid Search, Bayesian, Genetic, and Optuna Algorithms. *Multimedia Tools and Applications* 2024; 83(30): 74349–74364. https://doi.org/10.1007/s11042-024-18426-2

123.

Gao

Zhou

, et al. CLSA: A Novel Deep Learning Model for MOOC Dropout Prediction. *Computers & Electrical Engineering* 2021; 94: 107315. https://doi.org/10.1016/j.compeleceng.2021.107315

124.

Wojciuk

Swiderska-Chadaj

Siwek

, et al. Improving Classification Accuracy of Fine-Tuned CNN Models: Impact of Hyperparameter Optimization. *Heliyon* 2024; 10(5): e26586. https://doi.org/10.1016/j.heliyon.2024.e26586

125.

Liu

Schiele

Sun

. An Ensemble of Epoch-Wise Empirical Bayes for Few-Shot Learning. In: Computer Vision—ECCV 2020, Proceedings Part XVI*. Springer International Publishing, 2020, p. 404.

126.

Suganyadevi

Seethalakshmi

Balasamy

. A Review on Deep Learning in Medical Image Analysis. *International Journal of Multimedia Information Retrieval* 2022; 11(1): 19–38. https://doi.org/10.1007/s13735-021-00218-1

127.

Aszemi

Dominic

PDD

. Hyperparameter Optimization in Convolutional Neural Network Using Genetic Algorithms. *International Journal of Advanced Computer Science and Applications* 2019; 10(6): 269. https://doi.org/10.14569/ijacsa.2019.0100638

128.

Salehi

Khan

Gupta

, et al. A Study of CNN and Transfer Learning in Medical Imaging: Advantages, Challenges, Future Scope. *Sustainability* 2023; 15(7): 5930. https://doi.org/10.3390/su15075930

129.

Bonnet

Belanger

Mancusi

, et al. The Effect of Branchless Collisions and Population Control on Correlations in Monte Carlo Power Iteration. *Nuclear Science and Engineering* 2024; 198(11): 2120–2147. https://doi.org/10.1080/00295639.2023.2288328

130.

Choi

Kim

. A tutorial on quantum convolutional neural networks (QCNN). In: *Proceedings of the 2020 International Conference on Information and Communication Technology Convergence (ICTC)*, Jeju, Korea (South), 21-23 October 2020, IEEE, pp. 236–239.

131.

Hur

Kim

Park

. Quantum convolutional neural network for classical data classification. *Quantum Machine Intelligence* 2022; 4(1): 3. https://doi.org/10.1007/s42484-021-00061-x

132.

Oviesi

Tarokh

Momeni

. Quantum neural network-assisted learning for small medical datasets: a case study in emphysema detection. *The Journal of Supercomputing* 2025; 81(1): 308. https://doi.org/10.1007/s11227-024-06740-3

133.

Duan

L-M

Deng

D-L

. Quantum adversarial machine learning. *Physical Review Research* 2020; 2(3): 033212. https://doi.org/10.1103/physrevresearch.2.033212

134.

Diamant

Chatterjee

Vallières

, et al. Deep Learning in Head & Neck Cancer Outcome Prediction. *Scientific Reports* 2019; 9(1): 2764. https://doi.org/10.1038/s41598-019-39206-1

135.

Antoniadi

Guendouz

, et al. Current Challenges and Future Opportunities for XAI in Machine Learning-Based Clinical Decision Support Systems: A Systematic Review. *Applied Sciences* 2021; 11(11): 5088. https://doi.org/10.3390/app11115088

136.

Jagadamba

Ravi

, et al. Design of Interoperable Electronic Health Record (EHR) Application for Early Detection of Lung Diseases Using a Decision Support System by Expanding Deep Learning Techniques. *The Open Respiratory Medicine Journal* 2024; 18: e18743064296470. https://doi.org/10.2174/0118743064296470240520075316