AI-based histopathology phenotyping reveals germline loci shaping breast cancer morphology

Shubham Chaudhary, Almut Voigts, Sergey Vilov, Matthias Heinig, Francesco Paolo Casale
Proceedings of the 20th Machine Learning in Computational Biology meeting, PMLR 311:199-212, 2025.

Abstract

AI foundation models have transformed cancer histopathology by enabling rich, data-driven feature extraction from H&E-stained whole-slide images. However, their application to studying how germline variation shapes tumor morphology remains limited. Here, we perform the first genome-wide association study of breast cancer morphology, independently analyzing AI-derived features from histology images and diagnostic pathology reports. Analyzing H&E slides from 753 patients with matched germline data, we identified six genome-wide significant loci associated with either imaging or textual features, two of which replicated across modalities. We then linked these two loci to histological features described in pathology reports, visual histological features through generative modelling, gene expression modules and patient survival. We found that rs819976 in ATAD3B is associated with disorganized, necrotic tumor morphology, poor-prognosis expression programs, and clinical features including invasive lobular carcinoma and ER positivity. These findings demonstrate the power of AI-based histology to uncover and characterize germline variants that shape tumor morphology, and assess their clinical significance.

Cite this Paper

BibTeX
@InProceedings{pmlr-v311-chaudhary25a, title = {AI-based histopathology phenotyping reveals germline loci shaping breast cancer morphology}, author = {Chaudhary, Shubham and Voigts, Almut and Vilov, Sergey and Heinig, Matthias and Casale, Francesco Paolo}, booktitle = {Proceedings of the 20th Machine Learning in Computational Biology meeting}, pages = {199--212}, year = {2025}, editor = {Knowles, David A and Koo, Peter K}, volume = {311}, series = {Proceedings of Machine Learning Research}, month = {10--11 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v311/main/assets/chaudhary25a/chaudhary25a.pdf}, url = {https://proceedings.mlr.press/v311/chaudhary25a.html}, abstract = {AI foundation models have transformed cancer histopathology by enabling rich, data-driven feature extraction from H&E-stained whole-slide images. However, their application to studying how germline variation shapes tumor morphology remains limited. Here, we perform the first genome-wide association study of breast cancer morphology, independently analyzing AI-derived features from histology images and diagnostic pathology reports. Analyzing H&E slides from 753 patients with matched germline data, we identified six genome-wide significant loci associated with either imaging or textual features, two of which replicated across modalities. We then linked these two loci to histological features described in pathology reports, visual histological features through generative modelling, gene expression modules and patient survival. We found that rs819976 in ATAD3B is associated with disorganized, necrotic tumor morphology, poor-prognosis expression programs, and clinical features including invasive lobular carcinoma and ER positivity. These findings demonstrate the power of AI-based histology to uncover and characterize germline variants that shape tumor morphology, and assess their clinical significance.} }
Endnote
%0 Conference Paper %T AI-based histopathology phenotyping reveals germline loci shaping breast cancer morphology %A Shubham Chaudhary %A Almut Voigts %A Sergey Vilov %A Matthias Heinig %A Francesco Paolo Casale %B Proceedings of the 20th Machine Learning in Computational Biology meeting %C Proceedings of Machine Learning Research %D 2025 %E David A Knowles %E Peter K Koo %F pmlr-v311-chaudhary25a %I PMLR %P 199--212 %U https://proceedings.mlr.press/v311/chaudhary25a.html %V 311 %X AI foundation models have transformed cancer histopathology by enabling rich, data-driven feature extraction from H&E-stained whole-slide images. However, their application to studying how germline variation shapes tumor morphology remains limited. Here, we perform the first genome-wide association study of breast cancer morphology, independently analyzing AI-derived features from histology images and diagnostic pathology reports. Analyzing H&E slides from 753 patients with matched germline data, we identified six genome-wide significant loci associated with either imaging or textual features, two of which replicated across modalities. We then linked these two loci to histological features described in pathology reports, visual histological features through generative modelling, gene expression modules and patient survival. We found that rs819976 in ATAD3B is associated with disorganized, necrotic tumor morphology, poor-prognosis expression programs, and clinical features including invasive lobular carcinoma and ER positivity. These findings demonstrate the power of AI-based histology to uncover and characterize germline variants that shape tumor morphology, and assess their clinical significance.
APA
Chaudhary, S., Voigts, A., Vilov, S., Heinig, M. & Casale, F.P.. (2025). AI-based histopathology phenotyping reveals germline loci shaping breast cancer morphology. Proceedings of the 20th Machine Learning in Computational Biology meeting, in Proceedings of Machine Learning Research 311:199-212 Available from https://proceedings.mlr.press/v311/chaudhary25a.html.

Related Material