Colon Cancer Detection Using Deep Learning Algorithm

Abstract

Colon cancer is among the most prevalent and deadly forms of cancer globally, often progressing silently until reaching advanced stages. Early and accurate detection is critical for improving prognosis and survival rates. Traditional diagnostic methods such as colonoscopy and histopathological examination, while effective, are often invasive, time-consuming, and subject to human error. This study proposes a comprehensive machine learning-based framework for the automated detection and grading of colon cancer using multi-modal imaging data, including colonoscopy visuals, MRI scans, and histopathological slides. A combination of deep learning models, including Convolutional Neural Networks (CNN), Residual Networks (ResNet), and U-Net, alongside traditional machine learning algorithms like Support Vector Machines (SVM) and Random Forests (RF), is employed to perform classification and segmentation tasks. The dataset is sourced from The Cancer Imaging Archive (TCIA), Genomic Data Commons (GDC), and hospital records, ensuring diverse and annotated images representing various stages of colon cancer. The data undergoes rigorous pre-processing and augmentation to enhance quality and address class imbalances. The hybrid model achieves high accuracy, precision, recall, and F1-score, with superior performance in tumor segmentation using Dice Similarity Coefficient and Intersection over Union. Interpretability is enhanced using Grad-CAM and SHAP to visualize model decisions and feature importance. Evaluation results demonstrate that the proposed system not only achieves expert-level diagnostic accuracy but also significantly reduces processing time, offering potential for real-time clinical deployment.

Introduction

Colon cancer (colorectal cancer, CRC) is a leading global cause of cancer morbidity and mortality, often developing silently from benign polyps to malignant tumors. Despite screening methods like colonoscopy and histopathology, late diagnosis remains common due to invasiveness, cost, and subjectivity in interpretation.

To improve early detection and grading, this study proposes an AI-driven diagnostic system leveraging machine learning (ML) and deep learning (DL) applied to multi-modal imaging data—colonoscopy, histopathological slides, and radiological scans (MRI, CT). A large, annotated dataset was compiled from public repositories and clinical sources, preprocessed through noise reduction, normalization, and augmentation to enhance model robustness.

The methodology integrates traditional ML algorithms (SVM, Random Forest, k-NN) with advanced neural networks (CNN, ResNet, U-Net) to classify and segment cancerous tissue. Deep networks benefit from residual connections and segmentation architectures to improve accuracy and training stability.

A comprehensive literature review highlights recent AI advances in CRC diagnostics, including interpretable models, texture analysis, and hybrid feature approaches, while noting challenges like data heterogeneity and clinical integration.

The study’s machine learning pipeline involves careful data preparation, feature selection, and model tuning using GPU-accelerated frameworks (TensorFlow, PyTorch), aiming to deliver scalable, automated tools that enhance diagnostic precision and support personalized treatment.

Conclusion

Colon cancer remains a critical public health concern, characterized by its high prevalence, delayed detection, and the significant mortality associated with late-stage diagnosis. This research was undertaken with the objective of addressing some of the most pressing challenges in the diagnostic process, namely, the invasiveness, subjectivity, and latency of traditional diagnostic methods. By introducing a machine learning framework that leverages deep learning techniques and integrates multi-modal imaging data, the study contributes a powerful tool capable of automating, accelerating, and refining colon cancer diagnosis and grading. The methodology incorporated state-of-the-art deep learning architectures, including Convolutional Neural Networks (CNN), Residual Networks (ResNet), and U-Net, to achieve classification and segmentation tasks with high precision. These were supported by traditional machine learning classifiers such as Support Vector Machines and Random Forests for benchmarking and ensemble purposes. The multi-modal dataset, drawn from credible public repositories and clinical sources, provided a robust foundation for model training and validation, encompassing colonoscopy images, histopathological slides, and MRI scans. The comprehensive pre-processing steps, including noise reduction, normalization, and extensive data augmentation, ensured the models were trained on clean and diverse data, minimizing bias and enhancing generalizability. The results demonstrate that the proposed system achieved high levels of performance across standard evaluation metrics. The deep learning models accurately classified normal and cancerous tissues, effectively distinguished between different grades of colon cancer, and precisely segmented tumor regions. Visualization tools such as Grad-CAM and SHAP added transparency to the models’ decisions, thereby fostering clinical trust and adoption. Additionally, the system was computationally optimized, enabling near real-time inference, a key requirement for deployment in clinical settings.

References

[1] Neto, P. C., Montezuma, D., Oliveira, S. P., Oliveira, D., Fraga, J., Monteiro, A., ... & Cardoso, J. S. (2024). An interpretable machine learning system for colorectal cancer diagnosis from pathology slides. NPJ precision oncology, 8(1), 56. [2] Rai, H. M. (2024). Cancer detection and segmentation using machine learning and deep learning techniques: A review. Multimedia Tools and Applications, 83(9), 27001-27035. [3] Bülbül, H. M., Burakgazi, G., & Kesimal, U. (2024). Preoperative assessment of grade, T stage, and lymph node involvement: machine learning-based CT texture analysis in colon cancer. Japanese Journal of Radiology, 42(3), 300-307. [4] Bülbül, H. M., Burakgazi, G., & Kesimal, U. (2024). Preoperative assessment of grade, T stage, and lymph node involvement: machine learning-based CT texture analysis in colon cancer. Japanese Journal of Radiology, 42(3), 300-307. [5] Talebi, R., Celis-Morales, C. A., Akbari, A., Talebi, A., Borumandnia, N., & Pourhoseingholi, M. A. (2024). Machine learning-based classifiers to predict metastasis in colorectal cancer patients. Frontiers in Artificial Intelligence, 7. [6] Sharkas, M., & Attallah, O. (2024). Color-CADx: a deep learning approach for colorectal cancer classification through triple convolutional neural networks and discrete cosine transform. Scientific Reports, 14(1), 6914. [7] Karthikeyan, A., Jothilakshmi, S., & Suthir, S. (2024). Colorectal cancer detection based on convolutional neural networks (CNN) and ranking algorithm. Measurement: Sensors, 31, 100976. [8] Chhillar, I., & Singh, A. (2024). A feature engineering-based machine learning technique to detect and classify lung and colon cancer from histopathological images. Medical & Biological Engineering & Computing, 62(3), 913-924. [9] Suominen, M., Subasi, M. E., & Subasi, A. (2024). Automated detection of colon cancer from histopathological images using deep neural networks. In Applications of Artificial Intelligence Healthcare and Biomedicine (pp. 243-287). Academic Press. [10] Wei, R., Yu, G., Wang, X., Jiang, Z., & Guan, X. (2024). Construction and validation of machine learning models for predicting distant metastases in newly diagnosed colorectal cancer patients: A large?scale and real?world cohort study. Cancer Medicine, 13(5), e6971. [11] Alboaneen, D., Alqarni, R., Alqahtani, S., Alrashidi, M., Alhuda, R., Alyahyan, E., & Alshammari, T. (2023). Predicting colorectal cancer using machine and deep learning algorithms: Challenges and opportunities. Big Data and Cognitive Computing, 7(2), 74. [12] Azar, A. T., Tounsi, M., Fati, S. M., Javed, Y., Amin, S. U., Khan, Z. I., ... & Ganesan, J. (2023). Automated system for colon cancer detection and segmentation based on deep learning techniques. International Journal of Sociotechnology and Knowledge Development (IJSKD), 15(1), 1-28. [13] Bokhorst, J. M., Nagtegaal, I. D., Fraggetta, F., Vatrano, S., Mesker, W., Vieth, M., ... & Ciompi, F. (2023). Deep learning for multi-class semantic segmentation enables colorectal cancer detection and classification in digital pathology images. Scientific Reports, 13(1), 8398. [14] Bostanci, E., Kocak, E., Unal, M., Guzel, M. S., Acici, K., & Asuroglu, T. (2023). Machine learning analysis of RNA-seq data for diagnostic and prognostic prediction of colon cancer. Sensors, 23(6), 3080. [15] Peng, S., Lu, D., Zhang, B., You, R., Chen, J., Xu, H., & Lu, Y. (2023). Machine learning– assisted internal standard calibration label-free SERS strategy for colon cancer detection. Analytical and Bioanalytical Chemistry, 415(9), 1699-1707. [16] Al-Rajab, M., Lu, J., Xu, Q., Kentour, M., Sawsa, A., Shuweikeh, E., ... & Arasaradnam, R. (2023). A hybrid machine learning feature selection model—HMLFSM to enhance gene classification applied to multiple colon cancers dataset. Plos one, 18(11), e0286791. [17] Mokoatle, M., Marivate, V., Mapiye, D., Bornman, R., & Hayes, V. M. (2023). A review and comparative study of cancer detection using machine learning: SBERT and SimCSE application. BMC bioinformatics, 24(1), 112. [18] Mengash, H. A., Alamgeer, M., Maashi, M., Othman, M., Hamza, M. A., Ibrahim, S. S., ... & Yaseen, I. (2023). Leveraging marine predators algorithm with deep learning for lung and colon cancer diagnosis. Cancers, 15(5), 1591. [19] Wahid, R. R., Nisa, C., Amaliyah, R. P., & Puspaningrum, E. Y. (2023, February). Lung and colon cancer detection with convolutional neural networks on histopathological images. In AIP Conference Proceedings (Vol. 2654, No. 1). AIP Publishing. [20] Muniz, F. B., Baffa, M. D. F. O., Garcia, S. B., Bachmann, L., & Felipe, J. C. (2023). Histopathological diagnosis of colon cancer using micro-FTIR hyperspectral imaging and deep learning. Computer Methods and Programs in Biomedicine, 231, 107388. [21] Jiang, D., et al. (2022). Integrated Photoacoustic Pen for Breast Cancer Sentinel Lymph Node Detection. IEEE International Ultrasonics Symposium (IUS), 1-3. https://doi.org/10.1109/IUS54386.2022.9958597 [22] Li, X., Chai, Y., Zhang, K., Chen, W., & Huang, P. (2021). Early gastric cancer detection based on the combination of convolutional neural network and attention mechanism. 2021 China Automation Congress (CAC), 5731-5735. https://doi.org/10.1109/CAC53003.2021.9728413 [23] Nawreen, N., Hany, U., & Islam, T. (2021). Lung Cancer Detection and Classification using CT Scan Image Processing. 2021 International Conference on Automation, Control and Mechatronics for Industry 4.0 (ACMI), 1-6. https://doi.org/10.1109/ACMI53878.2021.9528297 [24] Soni, A., & Singh, A. P. (2020). Automatic Pulmonary Cancer Detection using Prewitt & Morphological Dilation. 2nd International Conference on Data, Engineering and Applications (IDEA), 1-6. https://doi.org/10.1109/IDEA49133.2020.9170680 [25] Qin, J., Puckett, L., & Qian, X. (2020). Image Based Fractal Analysis for Detection of Cancer Cells. IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 1482-1486. https://doi.org/10.1109/BIBM49941.2020.9313176 [26] Lingappa, E., & Parvathy, L. R. (2022). Active Contour Neural Network Identifying MRI Image Edge Computing Methods Deep Learning Bone Cancer Detection. 2022 2nd International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE), 830-834. https://doi.org/10.1109/ICACITE53722.2022.9823617 [27] Yu, Y., Yang, Q., & Shaohan, L. (2020). An Improved Faster R-CNN for Colorectal Cancer Cell Detection. IEEE 3rd International Conference on Electronics and Communication Engineering (ICECE), 186-190. https://doi.org/10.1109/ICECE51594.2020.9353044 [28] Zheng, Z., Zhang, H., Li, X., Liu, S., & Teng, Y. (2021). ResNet-Based Model for Cancer Detection. IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE), 325-328. https://doi.org/10.1109/ICCECE51280.2021.9342346 [29] Shi, C., Pan, Q., & Rehman, M. (2022). Cervical Cancer Cell Image Detection Method Based on Improved YOLOv4. 2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP), 1996-2000. https://doi.org/10.1109/ICSP54964.2022.9778577 [30] Santilli, A. M. L., et al. (2021). Self-Supervised Learning For Detection Of Breast Cancer In Surgical Margins With Limited Data. IEEE 18th International Symposium on Biomedical Imaging (ISBI), 980-984. https://doi.org/10.1109/ISBI48211.2021.9433829 [31] Firdaus, Q., Sigit, R., Harsono, T., & Anwar, A. (2020). Lung Cancer Detection Based On CT-Scan Images With Detection Features Using Gray Level Co-Occurrence Matrix (GLCM) and Support Vector Machine (SVM) Methods. 2020 International Electronics Symposium (IES), 643-648. https://doi.org/10.1109/IES50839.2020.9231663 [32] Hemalatha, S., Chidambararaj, N., & Motupalli, R. (2022). Performance Evaluation of Oral Cancer Detection and Classification using Deep Learning Approach. 2022 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI), 1-6. https://doi.org/10.1109/ACCAI53970.2022.9752505 [33] Zhang, S., et al. (2023). CCS-Net: Cascade Detection Network With the Convolution Kernel Switch Block and Statistics Optimal Anchors Block in Hypopharyngeal Cancer MRI. IEEE Journal of Biomedical and Health Informatics, 27*(1), 433-444. https://doi.org/10.1109/JBHI.2022.3217174 [34] Poojahsri, S., Prince, G. K., Prerana, S., & Krishnakumar, S. (2023). Various Methods in Texture Analysis and Classification Techniques used in Cervical Cancer Detection. 2023 5th International Conference on Smart Systems and Inventive Technology (ICSSIT), 1649-1652. https://doi.org/10.1109/ICSSIT55814.2023.10060990 [35] Sajan, S. C., Singh, A., Sharma, P. K., & Kumar, S. (2023). Silicon Photonics Biosensors for Cancer Cells Detection—A Review. IEEE Sensors Journal, 23*(4), 3366-3377. https://doi.org/10.1109/JSEN.2023.3235920 [36] Naraparaju, S. L., Eerlapalli, N. S. N., Modem, N., Paidipati, R., Karthikeyan, C., & Sathish Kumar, K. (2023). Analyzing the Accuracy of AI Techniques for Breast Cancer Detection. 2023 5th International Conference on Smart Systems and Inventive Technology (ICSSIT), 1660-1664. https://doi.org/10.1109/ICSSIT55814.2023.10061075 [37] Singh, S., Singh, N. K., & Singh, S. (2023). Breast-Cancer Biomarker (C-erbB-2) Detection in Saliva/Serum Based on InGaAs/Si Heterojunction Dopingless TFET Biosensor. IEEE Transactions on NanoBioscience, 22*(1), 28-37. [38] Patel, V., Chaurasia, V., Mahadeva, R., & Patole, S. P. (2023). GARL-Net: Graph Based Adaptive Regularized Learning Deep Network for Breast Cancer Classification. IEEE Access, 11, 9095-9112. https://doi.org/10.1109/ACCESS.2023.3239671 [39] Maier, M., Stapelfeldt, F. -N., & Issakov, V. (2023). Effect of Phase Noise in FMCW and PMCW Radar Systems for Breast Cancer Detection. 2023 IEEE Radio and Wireless Symposium (RWS), 37-39. Las Vegas, NV, USA. https://doi.org/10.1109/RWS55624.2023.10046294 [40] Priyadarshani, K. N., & Singh, S. (2023). Ultra Sensitive Breast Cancer Cell Lines Detection Using Dual Nanocavities Engraved Junctionless FET. IEEE Transactions on NanoBioscience*. https://doi.org/10.1109/TNB.2023.3246106

Copyright

Copyright © 2025 Ritu Goyal, Dr. Anil Dudi. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.