Enforcing 3D Coherence in Semi-Supervised Segmentation for Pancreatic Tumor Histopathology from Light Sheet Fluorescence Microscopy

Yousif Hashisho, Diana Pinkert-Leetsch, Jeannine Missbach-Guentner
Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, PMLR 315:3018-3035, 2026.

Abstract

Light sheet fluorescence microscopy (LSFM) provides unprecedented two-dimensional (2D) tomographic views and three-dimensional (3D) reconstructions of tissue volumes, but generates such large data sets that complete annotation is not feasible. This results in volumes with sparse axial annotations, where ground truth is available for only a small fraction of slices. Standard semi-supervised learning (SSL) methods often fail in this regime, unable to bridge the large gaps between labeled slices to produce coherent 3D segmentations. To address this, we propose a novel SSL framework designed to enforce 3D anatomical plausibility from sparse 2D supervision. The core of our contribution is an axial continuity loss, a regularization term that enforces prediction consistency between adjacent unlabeled slices. This loss is integrated into a voxel-aware Mean-Teacher framework that effectively leverages abundant unlabeled data. We validate our approach on a 3D LSFM dataset of human pancreatic ductal adenocarcinoma (PDAC), which we collected and sparsely annotated for this study. Our experiments show that standard SSL baselines degrade in performance as annotations become sparser, producing noisy predictions between labeled slices. In contrast, our full framework, which integrates an attention-gated 3D U-Net with our proposed continuity loss, maintains robust 3D coherence even in low-data regimes, enabling reliable histopathological analysis from minimal annotations.

Cite this Paper

BibTeX
@InProceedings{pmlr-v315-hashisho26a, title = {Enforcing 3D Coherence in Semi-Supervised Segmentation for Pancreatic Tumor Histopathology from Light Sheet Fluorescence Microscopy}, author = {Hashisho, Yousif and Pinkert-Leetsch, Diana and Missbach-Guentner, Jeannine}, booktitle = {Proceedings of The 9th International Conference on Medical Imaging with Deep Learning}, pages = {3018--3035}, 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/hashisho26a/hashisho26a.pdf}, url = {https://proceedings.mlr.press/v315/hashisho26a.html}, abstract = {Light sheet fluorescence microscopy (LSFM) provides unprecedented two-dimensional (2D) tomographic views and three-dimensional (3D) reconstructions of tissue volumes, but generates such large data sets that complete annotation is not feasible. This results in volumes with sparse axial annotations, where ground truth is available for only a small fraction of slices. Standard semi-supervised learning (SSL) methods often fail in this regime, unable to bridge the large gaps between labeled slices to produce coherent 3D segmentations. To address this, we propose a novel SSL framework designed to enforce 3D anatomical plausibility from sparse 2D supervision. The core of our contribution is an axial continuity loss, a regularization term that enforces prediction consistency between adjacent unlabeled slices. This loss is integrated into a voxel-aware Mean-Teacher framework that effectively leverages abundant unlabeled data. We validate our approach on a 3D LSFM dataset of human pancreatic ductal adenocarcinoma (PDAC), which we collected and sparsely annotated for this study. Our experiments show that standard SSL baselines degrade in performance as annotations become sparser, producing noisy predictions between labeled slices. In contrast, our full framework, which integrates an attention-gated 3D U-Net with our proposed continuity loss, maintains robust 3D coherence even in low-data regimes, enabling reliable histopathological analysis from minimal annotations.} }
Endnote
%0 Conference Paper %T Enforcing 3D Coherence in Semi-Supervised Segmentation for Pancreatic Tumor Histopathology from Light Sheet Fluorescence Microscopy %A Yousif Hashisho %A Diana Pinkert-Leetsch %A Jeannine Missbach-Guentner %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-hashisho26a %I PMLR %P 3018--3035 %U https://proceedings.mlr.press/v315/hashisho26a.html %V 315 %X Light sheet fluorescence microscopy (LSFM) provides unprecedented two-dimensional (2D) tomographic views and three-dimensional (3D) reconstructions of tissue volumes, but generates such large data sets that complete annotation is not feasible. This results in volumes with sparse axial annotations, where ground truth is available for only a small fraction of slices. Standard semi-supervised learning (SSL) methods often fail in this regime, unable to bridge the large gaps between labeled slices to produce coherent 3D segmentations. To address this, we propose a novel SSL framework designed to enforce 3D anatomical plausibility from sparse 2D supervision. The core of our contribution is an axial continuity loss, a regularization term that enforces prediction consistency between adjacent unlabeled slices. This loss is integrated into a voxel-aware Mean-Teacher framework that effectively leverages abundant unlabeled data. We validate our approach on a 3D LSFM dataset of human pancreatic ductal adenocarcinoma (PDAC), which we collected and sparsely annotated for this study. Our experiments show that standard SSL baselines degrade in performance as annotations become sparser, producing noisy predictions between labeled slices. In contrast, our full framework, which integrates an attention-gated 3D U-Net with our proposed continuity loss, maintains robust 3D coherence even in low-data regimes, enabling reliable histopathological analysis from minimal annotations.
APA
Hashisho, Y., Pinkert-Leetsch, D. & Missbach-Guentner, J.. (2026). Enforcing 3D Coherence in Semi-Supervised Segmentation for Pancreatic Tumor Histopathology from Light Sheet Fluorescence Microscopy. Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 315:3018-3035 Available from https://proceedings.mlr.press/v315/hashisho26a.html.

Related Material