Computational Anatomy And AI For Quantifying Tumor–Immune Spatial Geometry From Medical Images And Predicting Treatment Sensitivity

Ashok Kumar Dogra; Disha Anoop Nagpure; Swapna Babu Budala; Dr. Smriti Tiwari; Dr. Sana Fathima; Dr Kumar Sambhav; Avijit Kumar Chaudhuri

doi:10.29284/s98jm241

Authors

Ashok Kumar Dogra Assistant professor, Department of Biochemistry, Specialization in oncology, Government Medical College, Srinagar, Jammu and Kashmir
Disha Anoop Nagpure HOD(AIML department Alard college of Engineering, Pune), Department of AIML, Specialization in Machine Learning, Alard college of Engineering, Pune, Pin code: 411057, India, Orcid Id: 0009-0008-95035367
Swapna Babu Budala Assistant Professor, Department Of CSE-AIML, Aditya University, Surampalem, Kakinada District, Andhra Pradesh, Pin Code: 533437, India, Orcid Id:0009-0007-8651-8415
Dr. Smriti Tiwari Lecturer, Department of Pharmacy Practice, Teerthanker Mahaveer College of Pharmacy, TMU University, Moradabad Orcid Id: 0009-0008-1818-0560
Dr. Sana Fathima Department of Histopathology, Specialization in MD PATHOLOGY, Bengaluru, Pin code : 560001, India, Orcid Id: 0000-0001-7614-9483
Dr Kumar Sambhav Assistant Professor, Department of Anatomy, MD( Anatomy), All India Institute of Medical Sciences, Bilaspur, Himachal Pradesh Orcid Id: 0000-0003-0012-3994
Avijit Kumar Chaudhuri Professor & HOD, Department of Computer Science & Engineering, Brainware University, Barasat, Kolkata – 125, West Bengal, India, Pin code: 700125, Orcid Id: 0000-0002-5310-3180

DOI:

https://doi.org/10.29284/s98jm241

Keywords:

Computational anatomy; Tumor–immune spatial geometry; Medical image analytics; Graph neural networks; Treatment sensitivity prediction.

Abstract

The spatial organization of tumor and immune cells within the tumor microenvironment has emerged as a critical determinant of therapeutic response and clinical outcome. Advances in digital pathology, multiplex imaging, and radiological modalities now enable high-resolution acquisition of spatially resolved tumor–immune architecture. This review synthesizes recent progress in computational anatomy and artificial intelligence (AI) frameworks for quantifying tumor–immune spatial geometry from medical images and translating these representations into predictive models of treatment sensitivity. The image preprocessing and normalization strategies, segmentation and instance detection methods, and geometric modeling approaches including spatial point processes, graph-based representations, and topological descriptors. Modern AI architectures convolutional neural networks, graph neural networks, transformers, and multimodal foundation models for spatial feature learning and outcome prediction were further analyzed. Comparative evaluation highlights methodological trends, trade-offs in scalability and interpretability, and reproducibility challenges across studies. Persistent limitations include domain shift, annotation variability, computational burden of gigapixel whole-slide images, and the absence of standardized benchmarking protocols. Emerging directions such as self-supervised learning, federated training, and multiscale representation alignment are discussed as pathways toward robust and generalizable spatial analytics. Collectively, computational anatomy integrated with AI-driven spatial modeling provides a scalable framework for objective, quantitative assessment of tumor–immune interactions and precision prediction of treatment sensitivity from medical images.

References

1. Gong, D., Arbesfeld-Qiu, J.M., Perrault, E., Bae, J.W. and Hwang, W.L., 2024. Spatial oncology: Translating contextual biology to the clinic. Cancer Cell, 42(10), pp.1653-1675.

2. Janeiro, A.L., Wong, E.M., Jiménez-Sánchez, D., de Solorzano, C.O., Lozano, M.D., Teijeira, A., Schalper, K.A., Melero, I. and De Andrea, C.E., 2024. Spatially resolved tissue imaging to analyze the tumor immune microenvironment: beyond cell-type densities. Journal for Immunotherapy of Cancer, 12(5), p.e008589.

3. Heindl, A., Nawaz, S. and Yuan, Y., 2015. Mapping spatial heterogeneity in the tumor microenvironment: a new era for digital pathology. Laboratory investigation, 95(4), pp.377-384.

4. Hu, C., Wang, F., Xu, H., Dong, X., Xiong, X., Zhang, Y., Zhao, T., He, Y., Deng, L. and Lu, X., 2025. Deep learning-based spatial analysis on tumor and immune cells of pathology images predicts MIBC prognosis. Plos one, 20(8), p.e0328816.

5. Park, Y.M. and Lin, D.C., 2023. Moving closer towards a comprehensive view of tumor biology and microarchitecture using spatial transcriptomics. nature communications, 14(1), p.7017.

6. Lu, M.Y., Williamson, D.F., Chen, T.Y., Chen, R.J., Barbieri, M. and Mahmood, F., 2021. Data-efficient and weakly supervised computational pathology on whole-slide images. Nature biomedical engineering, 5(6), pp.555-570.

7. Hanson, G.F., Goundry, K.A., Wessel, R.E., Brown, M.G., Bullock, T.N. and Dolatshahi, S., 2025. A flexible systems analysis pipeline for elucidating spatial relationships in the tumor microenvironment linked with cellular phenotypes and patient-level features. Frontiers in Immunology, 16, p.1642527.

8. Xu, C., Sun, Y., Zhang, Y., Liu, T., Wang, X., Hu, D., Huang, S., Li, J., Zhang, F. and Li, G., 2025. Stain Normalization of Histopathological Images Based on Deep Learning: A Review. Diagnostics, 15(8), p.1032.

9. Breen, J., Zucker, K., Allen, K., Ravikumar, N. and Orsi, N.M., 2024. Generative adversarial networks for stain normalisation in histopathology. In Applications of Generative AI (pp. 227-247). Cham: Springer International Publishing.

10. Hu, B., Sajid, M., Lv, R., Liu, L. and Sun, C., 2022. A review of spatial profiling technologies for characterizing the tumor microenvironment in immuno-oncology. Frontiers in Immunology, 13, p.996721.

11. Elhanani, O., Ben-Uri, R. and Keren, L., 2023. Spatial profiling technologies illuminate the tumor microenvironment. Cancer cell, 41(3), pp.404-420.

12. Ronneberger, O., Fischer, P. and Brox, T., 2015, October. U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention (pp. 234-241). Cham: Springer international publishing.

13. Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F. and Adam, H., 2018. Encoder-decoder with atrous separable convolution for semantic image segmentation. In Proceedings of the European conference on computer vision (ECCV) (pp. 801-818).

14. Isensee, F., Jaeger, P.F., Kohl, S.A., Petersen, J. and Maier-Hein, K.H., 2021. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nature methods, 18(2), pp.203-211.

15. Greenwald, N.F., Miller, G., Moen, E., Kong, A., Kagel, A., Dougherty, T., Fullaway, C.C., McIntosh, B.J., Leow, K.X., Schwartz, M.S. and Pavelchek, C., 2022. Whole-cell segmentation of tissue images with human-level performance using large-scale data annotation and deep learning. Nature biotechnology, 40(4), pp.555-565.

16. He, K., Gkioxari, G., Dollár, P. and Girshick, R., 2017. Mask r-cnn. In Proceedings of the IEEE international conference on computer vision (pp. 2961-2969).

17. Graham, S., Vu, Q.D., Raza, S.E.A., Azam, A., Tsang, Y.W., Kwak, J.T. and Rajpoot, N., 2019. Hover-net: Simultaneous segmentation and classification of nuclei in multi-tissue histology images. Medical image analysis, 58, p.101563.

18. Schmidt, U., Weigert, M., Broaddus, C. and Myers, G., 2018, September. Cell detection with star-convex polygons. In International conference on medical image computing and computer-assisted intervention (pp. 265-273). Cham: Springer International Publishing.

19. Stringer, C., Wang, T., Michaelos, M. and Pachitariu, M., 2021. Cellpose: a generalist algorithm for cellular segmentation. Nature methods, 18(1), pp.100-106.

20. Benimam, M.M., Meas-Yedid, V., Mukherjee, S., Frafjord, A., Corthay, A., Lagache, T. and Olivo-Marin, J.C., 2025. Statistical analysis of spatial patterns in tumor microenvironment images. Nature Communications, 16(1), p.3090.

21. Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K. and Yuille, A.L., 2017. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE transactions on pattern analysis and machine intelligence, 40(4), pp.834-848.

22. Kipf, T.N., 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907.

23. Velickovic, P., Cucurull, G., Casanova, A., Romero, A., Lio, P. and Bengio, Y., 2017. Graph attention networks. stat, 1050(20), pp.10-48550.

24. Hamilton, W., Ying, Z. and Leskovec, J., 2017. Inductive representation learning on large graphs. Advances in neural information processing systems, 30.

25. Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S. and Guo, B., 2021. Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE/CVF international conference on computer vision (pp. 10012-10022).

26. Chen, R.J., Lu, M.Y., Shaban, M., Chen, C., Chen, T.Y., Williamson, D.F. and Mahmood, F., 2021, September. Whole slide images are 2d point clouds: Context-aware survival prediction using patch-based graph convolutional networks. In International Conference on Medical Image Computing and Computer-Assisted Intervention (pp. 339-349). Cham: Springer International Publishing.

27. Ding, T., Wagner, S.J., Song, A.H., Chen, R.J., Lu, M.Y., Zhang, A., Vaidya, A.J., Jaume, G., Shaban, M., Kim, A. and Williamson, D.F., 2025. A multimodal whole-slide foundation model for pathology. Nature medicine, pp.1-13.

28. Li, H., Shui, Z., Zhang, Y., Zhu, C. and Yang, L., 2025. PathVQ: Reforming Computational Pathology Foundation Model for Whole Slide Image Analysis via Vector Quantization. arXiv preprint arXiv:2503.06482.

29. Xu, K., Hu, W., Leskovec, J. and Jegelka, S., 2018. How powerful are graph neural networks?. arXiv preprint arXiv:1810.00826.

30. Shao, Z., Bian, H., Chen, Y., Wang, Y., Zhang, J. and Ji, X., 2021. Transmil: Transformer based correlated multiple instance learning for whole slide image classification. Advances in neural information processing systems, 34, pp.2136-2147.

31. Shao, W., Shi, Y., Zhang, D., Zhou, J. and Wan, P., 2024. Tumor micro-environment interactions guided graph learning for survival analysis of human cancers from whole-slide pathological images. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 11694-11703).

32. Li, R., Yao, J., Zhu, X., Li, Y. and Huang, J., 2018, September. Graph CNN for survival analysis on whole slide pathological images. In International conference on medical image computing and computer-assisted intervention (pp. 174-182). Cham: Springer International Publishing.

33. Yao, J., Zhu, X., Jonnagaddala, J., Hawkins, N. and Huang, J., 2020. Whole slide images based cancer survival prediction using attention guided deep multiple instance learning networks. Medical image analysis, 65, p.101789.

34. Madusanka, N., Padmanabha, P., Guruge, K. and Lee, B.I., 2025. Structure-Preserving Histopathological Stain Normalization via Attention-Guided Residual Learning. Bioengineering, 12(9), p.950.

35. Fashi, P.A., Hemati, S., Babaie, M., Gonzalez, R. and Tizhoosh, H.R., 2022. A self-supervised contrastive learning approach for whole slide image representation in digital pathology. Journal of Pathology Informatics, 13, p.100133.

36. Ilse, M., Tomczak, J. and Welling, M., 2018, July. Attention-based deep multiple instance learning. In International conference on machine learning (pp. 2127-2136). PMLR.