Comparative Study of Deep Learning-Based Frameworks for Colorectal Cancer Detection Using Histopathological Images
Keywords:
Colorectal Cancer Detection, Deep Learning, Transfer Learning, Histopathology Classification, CNN-LSTM HybridAbstract
This paper compares three deep learning-based frameworks—LbCCD, ColoSeqNet, and ColoTL-Framework—for automatic colorectal cancer detection using histopathological images. Each framework builds upon CNN-based architectures with different enhancements: LbCCD uses Enhanced ResNet50, ColoSeqNet integrates LSTM for sequence modeling, and ColoTL-Framework employs transfer learning with fine-tuned VGG19. We evaluate these models on the Colorectal Histopathology dataset across multiple metrics. Our results show that ColoTL-Framework achieves the highest accuracy of 98.79%, followed by ColoSeqNet with 96.89%, and LbCCD with 93.40%. This study highlights the proposed methods' architectural novelties, performance improvements, and clinical relevance...
Downloads
References
[1] Jha, D., et al., “ResUNet++: An Advanced Architecture for Colon Polyp Segmentation,” Scientific Reports, vol. 11, no. 1, pp. 1–9, 2021.
[2] Sajjad, M., et al., “Hybrid Deep Learning Model for Accurate Cancer Detection,” IEEE Access, vol. 10, pp. 73240–73250, 2022.
[3] Kartik, V., et al., “An Ensemble CNN-SVM Approach for Histopathology Image Classification,” Computers in Biology and Medicine, vol. 141, 105063, 2022.
[4] Ishak, A., et al., “Deep Learning Techniques in Colorectal Cancer Histopathology: A Comprehensive Review,” Healthcare Analytics, vol. 3, 100089, 2023.
[5] Echle, A., et al., “Deep Learning for Detecting Microsatellite Instability in Colorectal Cancer,” The Lancet Oncology, vol. 21, no. 1, pp. 72–82, 2020.
[6] ha, D., et al., “Kvasir-SEG: A Segmented Polyp Dataset,” Proceedings of the IEEE EMBC, pp. 4320–4324, 2020.
[7] Ibrahim, D. M., et al., “Multi-Class Deep Learning for Chest and Colorectal Disease Detection,” Expert Systems with Applications, vol. 185, 115599, 2021.
[8] Fan, P., et al., “PraNet: Parallel Reverse Attention Network for Polyp Segmentation,” Medical Image Analysis, vol. 67, 101857, 2021.
[9] Chehade, A., et al., “Colon and Lung Histopathology Image Classification Using XGBoost,” Computer Methods and Programs in Biomedicine, vol. 208, 106209, 2022.
[10] Dlamini, Z., et al., “Precision Oncology and AI: Current State and Future Prospects,” Cancers, vol. 14, no. 4, 889, 2022.
[11] Wen, J., et al., “Colonoscopy Polyp Segmentation with Fully Convolutional Networks,” IEEE Transactions on Medical Imaging, vol. 41, no. 3, pp. 625–635, 2022.
[12] Luo, X., and Bocklitz, T., “Benchmarking Transfer Learning for Colorectal Cancer Histology Classification,” Pattern Recognition Letters, vol. 158, pp. 104–110, 2022.
[13] Khan, S., et al., “Ensemble Transfer Learning for Colorectal Lymph Node Metastasis Detection,” Diagnostics, vol. 12, no. 3, 621, 2022.
[14] Abbas, Q., et al., “DeTraC: Deep Convolutional Neural Network for Medical Image Classification,” Applied Soft Computing, vol. 93, 106383, 2020.
[15] He, K., et al., “A Survey on Transformer Models in Medical Imaging,” Artificial Intelligence in Medicine, vol. 132, 102366, 2022
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
Terms:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
