Heteroscedastic Heatmap Regression for Reliable Pectoral Muscle Segmentation in Mammography

Paul Zech, Christian Hümmer, Benjamin El-Zein, Christopher Syben, Ludwig Ritschl, Steffen Kappler, Sebastian Stober
Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, PMLR 315:4085-4101, 2026.

Abstract

Breast cancer remains a leading cause of mortality worldwide, making accurate mammography screening essential for early detection. An important preprocessing step in mammography is the accurate segmentation of the pectoral muscle, as it affects downstream tasks such as breast density estimation or automated exposure control. Existing automated segmentation methods, both traditional and deep learning-based, often lack reliable confidence measures, which becomes especially problematic in the presence of occlusions or visually confounding structures such as skin folds or other muscle fibers. To address this limitation, we propose a probabilistic framework that combines heatmap-based boundary regression with heteroscedastic uncertainty estimation to capture input-dependent variability. Our approach not only predicts the pectoral muscle boundary but also quantifies the associated uncertainty. While mainly producing unimodal predictions, the probabilistic heatmaps reveal multimodal patterns for confounding structures, further enhancing transparency in challenging cases. We demonstrate that our method provides robust and transparent means to achieve accurate segmentation while producing meaningful uncertainty estimates.

Cite this Paper

BibTeX
@InProceedings{pmlr-v315-zech26a, title = {Heteroscedastic Heatmap Regression for Reliable Pectoral Muscle Segmentation in Mammography}, author = {Zech, Paul and H\"{u}mmer, Christian and El-Zein, Benjamin and Syben, Christopher and Ritschl, Ludwig and Kappler, Steffen and Stober, Sebastian}, booktitle = {Proceedings of The 9th International Conference on Medical Imaging with Deep Learning}, pages = {4085--4101}, year = {2026}, editor = {Huo, Yuankai and Gao, Mingchen and Kuo, Chang-Fu and Jin, Yueming and Deng, Ruining}, volume = {315}, series = {Proceedings of Machine Learning Research}, month = {08--10 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v315/main/assets/zech26a/zech26a.pdf}, url = {https://proceedings.mlr.press/v315/zech26a.html}, abstract = {Breast cancer remains a leading cause of mortality worldwide, making accurate mammography screening essential for early detection. An important preprocessing step in mammography is the accurate segmentation of the pectoral muscle, as it affects downstream tasks such as breast density estimation or automated exposure control. Existing automated segmentation methods, both traditional and deep learning-based, often lack reliable confidence measures, which becomes especially problematic in the presence of occlusions or visually confounding structures such as skin folds or other muscle fibers. To address this limitation, we propose a probabilistic framework that combines heatmap-based boundary regression with heteroscedastic uncertainty estimation to capture input-dependent variability. Our approach not only predicts the pectoral muscle boundary but also quantifies the associated uncertainty. While mainly producing unimodal predictions, the probabilistic heatmaps reveal multimodal patterns for confounding structures, further enhancing transparency in challenging cases. We demonstrate that our method provides robust and transparent means to achieve accurate segmentation while producing meaningful uncertainty estimates.} }
Endnote
%0 Conference Paper %T Heteroscedastic Heatmap Regression for Reliable Pectoral Muscle Segmentation in Mammography %A Paul Zech %A Christian Hümmer %A Benjamin El-Zein %A Christopher Syben %A Ludwig Ritschl %A Steffen Kappler %A Sebastian Stober %B Proceedings of The 9th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2026 %E Yuankai Huo %E Mingchen Gao %E Chang-Fu Kuo %E Yueming Jin %E Ruining Deng %F pmlr-v315-zech26a %I PMLR %P 4085--4101 %U https://proceedings.mlr.press/v315/zech26a.html %V 315 %X Breast cancer remains a leading cause of mortality worldwide, making accurate mammography screening essential for early detection. An important preprocessing step in mammography is the accurate segmentation of the pectoral muscle, as it affects downstream tasks such as breast density estimation or automated exposure control. Existing automated segmentation methods, both traditional and deep learning-based, often lack reliable confidence measures, which becomes especially problematic in the presence of occlusions or visually confounding structures such as skin folds or other muscle fibers. To address this limitation, we propose a probabilistic framework that combines heatmap-based boundary regression with heteroscedastic uncertainty estimation to capture input-dependent variability. Our approach not only predicts the pectoral muscle boundary but also quantifies the associated uncertainty. While mainly producing unimodal predictions, the probabilistic heatmaps reveal multimodal patterns for confounding structures, further enhancing transparency in challenging cases. We demonstrate that our method provides robust and transparent means to achieve accurate segmentation while producing meaningful uncertainty estimates.
APA
Zech, P., Hümmer, C., El-Zein, B., Syben, C., Ritschl, L., Kappler, S. & Stober, S.. (2026). Heteroscedastic Heatmap Regression for Reliable Pectoral Muscle Segmentation in Mammography. Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 315:4085-4101 Available from https://proceedings.mlr.press/v315/zech26a.html.

Related Material