IRO Journals
Journal of Innovative Image Processing

Dual-Model Transfer Learning with Graph Neural Networks and SHAP Explainability for Robust Colorectal Tumor Margin Detection Process

Open Access
Published: 17 July, 2026
Pages: 1076-1095
  • Divya Midhunchakkaravarthy , Divya Midhunchakkaravarthy
    Associate Professor, Department of Electronics and Communication Engineering, Lincoln University College, Petaling Jaya, Malaysia
    Associate Professor, Department of Electronics and Communication Engineering, Lincoln University College, Petaling Jaya, Malaysia
  • Muni Nagamani G. , Muni Nagamani G.
    Post Doctoral Fellowship Scholar, Department of Computer Science and Engineering, Lincoln University College, Petaling Jaya, Malaysia
    Post Doctoral Fellowship Scholar, Department of Computer Science and Engineering, Lincoln University College, Petaling Jaya, Malaysia
  • Lakshman Narayana V. Lakshman Narayana V.
    Professor, Department of Computer Science and Engineering, Vignan's Nirula Institute of Technology and Science for Women, Guntur, India
    Professor, Department of Computer Science and Engineering, Vignan's Nirula Institute of Technology and Science for Women, Guntur, India
view PDF
view PDF

How to Cite

Midhunchakkaravarthy, Divya, Muni Nagamani G., and Lakshman Narayana V. 2026. “Dual-Model Transfer Learning With Graph Neural Networks and SHAP Explainability for Robust Colorectal Tumor Margin Detection Process”. Journal of Innovative Image Processing 8 (3): 1076-95. https://doi.org/10.36548/jiip.2026.3.016.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Graph Neural Networks
SHAP Explainability
Colorectal Tumor Margin
Transfer Learning
Multi-Center Histopathology
Boundary Fidelity

Abstract

When performing surgery for colorectal cancer, it is essential to precisely delineate the margins of the tumor. This is because even minute errors in the margins can have a significant impact on the quality of the resection, the risk of recurrence, and the planning of therapy following the surgery. When slides are supplied from multiple locations, the computer-aided pathology models now in use do not always work correctly, and their explanations do not always focus on the invasive boundary, which is where clinical decisions are most critical. The purpose of this study is to demonstrate a two-model transfer learning system that combines spatial aggregation based on graph neural networks with SHAP-guided border explainability in order to improve the accuracy of colorectal tumor margin identification. Weighted tissue graphs are created from the slides used in histopathology. While the lines illustrate how the cells are related in space shape by utilizing Delaunay and k-nearest neighbor, the nodes illustrate the areas that are split into cellular or super-pixel regions. At the same time, five modules are utilized: CDGCV, which stands for Cross-Domain Graph Consistency Validation, is a technique that verifies the consistency of the topology between centers. BFSRT, which stands for Boundary-Focused SHAP Refinement Test, is a test that verifies the correctness of boundary-specific explanations. The strength of the structure is evaluated using a technique known as Multi-Scale Relational Perturbation Assessment (MSRPA); Dynamic SHAP-Graph Alignment (DSGA) is used to determine whether t the interpretation is timely, and Hierarchical Graph-SHAP Ensemble (HGSE) is used to determine whether the epithelium, stroma, and invasive-front cells are in accord with one another. Dice scores can reach up to 0.94, boundary fidelity is close to 0.90, cross-center consistency is over 0.82, and F1 degradation is less than 3% when edges are rewired 20%, according to experimental tests conducted on the Kather, CRC-TIA, and internal multi-center cohorts. The support for transferability is increased by testing conducted at an external center. Therefore, the system provides accurate margin localization, stable graph reasoning, and explanations that are comprehensible to medical professionals for the purpose of deploying colorectal pathology across many locations.

References

  1. Kather, Jakob Nikolas, Johannes Krisam, Pornpimol Charoentong, Tom Luedde, Esther Herpel, Cleo-Aron Weis, Timo Gaiser et al. "Predicting Survival from Colorectal Cancer Histology Slides Using Deep Learning: A Retrospective Multicenter Study." PLoS medicine 16, no. 1 (2019): e1002730.
  2. Kather, Jakob Nikolas, Niels Halama, and Alexander Marx. “100,000 Histological Images of Human Colorectal Cancer and Healthy Tissue.” Zenodo, 2018. https://doi.org/10.5281/zenodo.1214456
  3. Hatami, Nima. "DeepFEL: Deep Fastfood Ensemble Learning for Histopathology Image Analysis." arXiv preprint arXiv:2301.09525 (2023).
  4. Kim, Hyeongsub, Hongjoon Yoon, Nishant Thakur, Gyoyeon Hwang, Eun Jung Lee, Chulhong Kim, and Yosep Chong. "Deep Learning-Based Histopathological Segmentation for Whole Slide Images of Colorectal Cancer in a Compressed Domain." Scientific reports 11, no. 1 (2021): 22520.
  5. Peng, Ziyang, Kexin Peng, Chengdao Liu, and Xingzhi Zhang. "DP-U-Net++: Inter-Layer Feature Fusion for Colorectal Gland Image Segmentation." International Journal of Machine Learning and Cybernetics 15, no. 10 (2024): 4459-4473.
  6. Ma, Lei, Jiangkai Yan, Dangguo Shao, Jingtao Li, Jiawei Wang, and Yukun Yan. "Mcff-Net: Multi-Scale Contextual Feature Fusion Network for Polyp Segmentation." Journal of Shanghai Jiaotong University (Science) (2024): 1-13.
  7. Zhou, Yanning, Simon Graham, Navid Alemi Koohbanani, Muhammad Shaban, Pheng-Ann Heng, and Nasir Rajpoot. "Cgc-Net: Cell Graph Convolutional Network for Grading of Colorectal Cancer Histology Images." In Proceedings of the IEEE/CVF international conference on computer vision workshops, 2019, 0-0.
  8. Pati, Pushpak, Guillaume Jaume, Lauren Alisha Fernandes, Antonio Foncubierta-Rodríguez, Florinda Feroce, Anna Maria Anniciello, Giosue Scognamiglio et al. "Hact-Net: A Hierarchical Cell-To-Tissue Graph Neural Network for Histopathological Image Classification." In International Workshop on Uncertainty for Safe Utilization of Machine Learning in Medical Imaging, Cham: Springer International Publishing, 2020, 208-219.
  9. Paul, Sudipta, Bülent Yener, and Amanda W. Lund. "C2P-GCN: Cell-to-Patch Graph Convolutional Network for Colorectal Cancer Grading." In 2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), IEEE, 2024, 1-4.
  10. Brussee, Siemen, Giorgio Buzzanca, Anne MR Schrader, and Jesper Kers. "Graph Neural Networks in Histopathology: Emerging Trends and Future Directions." Medical Image Analysis 101 (2025): 103444.
  11. Shao, Zhuchen, Hao Bian, Yang Chen, Yifeng Wang, Jian Zhang, and Xiangyang Ji. "Transmil: Transformer Based Correlated Multiple Instance Learning for Whole Slide Image Classification." Advances in neural information processing systems 34 (2021): 2136-2147.
  12. Wang, Xiyue, Sen Yang, Jun Zhang, Minghui Wang, Jing Zhang, Wei Yang, Junzhou Huang, and Xiao Han. "Transformer-Based Unsupervised Contrastive Learning for Histopathological Image Classification." Medical image analysis 81 (2022): 102559.
  13. Chen, Richard J., Tong Ding, Ming Y. Lu, Drew FK Williamson, Guillaume Jaume, Andrew H. Song, Bowen Chen et al. "Towards a General-Purpose Foundation Model for Computational Pathology." Nature medicine 30, no. 3 (2024): 850-862.
  14. Vorontsov, Eugene, Alican Bozkurt, Adam Casson, George Shaikovski, Michal Zelechowski, Kristen Severson, Eric Zimmermann et al. "A Foundation Model for Clinical-Grade Computational Pathology and Rare Cancers Detection." Nature medicine 30, no. 10 (2024): 2924-2935.
  15. Lu, Ming Y., Bowen Chen, Drew FK Williamson, Richard J. Chen, Ivy Liang, Tong Ding, Guillaume Jaume et al. "A Visual-Language Foundation Model for Computational Pathology." Nature medicine 30, no. 3 (2024): 863-874.
  16. Ding, Tong, Sophia J. Wagner, Andrew H. Song, Richard J. Chen, Ming Y. Lu, Andrew Zhang, Anurag J. Vaidya et al. "A Multimodal Whole-Slide Foundation Model for Pathology." Nature medicine (2025): 1-13.
  17. Lundberg, Scott M., and Su-In Lee. "A Unified Approach to Interpreting Model Predictions." Advances in neural information processing systems 30 (2017).
  18. Kipf, Thomas N., and Max Welling. "Semi-Supervised Classification with Graph Convolutional Networks." arXiv preprint arXiv:1609.02907 (2016).
  19. Qin, Zhuanping, Wenhao Sun, Tinghang Guo, and Guangda Lu. "Colorectal Cancer Image Recognition Algorithm Based on Improved Transformer." Discover Applied Sciences 6, no. 8 (2024): 422