Differentiable Boundary Point Extraction for Weakly Supervised Star-shaped Object Segmentation

Robin Camarasa, Hoel Kervadec, Daniel Bos, Marleen de Bruijne
Proceedings of The 5th International Conference on Medical Imaging with Deep Learning, PMLR 172:188-198, 2022.

Abstract

Although Deep Learning is the new gold standard in medical image segmentation, the annotation burden limits its expansion to clinical practice. We also observe a mismatch between annotations required by deep learning methods designed with pixel-wise optimization in mind and clinically relevant annotations designed for biomarkers extraction (diameters, counts, etc.). Our study proposes a first step toward bridging this gap, optimizing vessel segmentation based on its diameter annotations. To do so we propose to extract bound- ary points from a star-shaped segmentation in a differentiable manner. This differentiable extraction allows reducing annotation burden as instead of the pixel-wise segmentation only the two annotated points required for diameter measurement are used for training the model. Our experiments show that training based on diameter is efficient; produces state-of-the-art weakly supervised segmentation; and performs reasonably compared to full supervision. Our code is publicly available: https://gitlab.com/radiology/aim/carotid-artery-image-analysis/diameter-learning

Cite this Paper


BibTeX
@InProceedings{pmlr-v172-camarasa22a, title = {Differentiable Boundary Point Extraction for Weakly Supervised Star-shaped Object Segmentation}, author = {Camarasa, Robin and Kervadec, Hoel and Bos, Daniel and de Bruijne, Marleen}, booktitle = {Proceedings of The 5th International Conference on Medical Imaging with Deep Learning}, pages = {188--198}, year = {2022}, editor = {Konukoglu, Ender and Menze, Bjoern and Venkataraman, Archana and Baumgartner, Christian and Dou, Qi and Albarqouni, Shadi}, volume = {172}, series = {Proceedings of Machine Learning Research}, month = {06--08 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v172/camarasa22a/camarasa22a.pdf}, url = {https://proceedings.mlr.press/v172/camarasa22a.html}, abstract = {Although Deep Learning is the new gold standard in medical image segmentation, the annotation burden limits its expansion to clinical practice. We also observe a mismatch between annotations required by deep learning methods designed with pixel-wise optimization in mind and clinically relevant annotations designed for biomarkers extraction (diameters, counts, etc.). Our study proposes a first step toward bridging this gap, optimizing vessel segmentation based on its diameter annotations. To do so we propose to extract bound- ary points from a star-shaped segmentation in a differentiable manner. This differentiable extraction allows reducing annotation burden as instead of the pixel-wise segmentation only the two annotated points required for diameter measurement are used for training the model. Our experiments show that training based on diameter is efficient; produces state-of-the-art weakly supervised segmentation; and performs reasonably compared to full supervision. Our code is publicly available: https://gitlab.com/radiology/aim/carotid-artery-image-analysis/diameter-learning } }
Endnote
%0 Conference Paper %T Differentiable Boundary Point Extraction for Weakly Supervised Star-shaped Object Segmentation %A Robin Camarasa %A Hoel Kervadec %A Daniel Bos %A Marleen de Bruijne %B Proceedings of The 5th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2022 %E Ender Konukoglu %E Bjoern Menze %E Archana Venkataraman %E Christian Baumgartner %E Qi Dou %E Shadi Albarqouni %F pmlr-v172-camarasa22a %I PMLR %P 188--198 %U https://proceedings.mlr.press/v172/camarasa22a.html %V 172 %X Although Deep Learning is the new gold standard in medical image segmentation, the annotation burden limits its expansion to clinical practice. We also observe a mismatch between annotations required by deep learning methods designed with pixel-wise optimization in mind and clinically relevant annotations designed for biomarkers extraction (diameters, counts, etc.). Our study proposes a first step toward bridging this gap, optimizing vessel segmentation based on its diameter annotations. To do so we propose to extract bound- ary points from a star-shaped segmentation in a differentiable manner. This differentiable extraction allows reducing annotation burden as instead of the pixel-wise segmentation only the two annotated points required for diameter measurement are used for training the model. Our experiments show that training based on diameter is efficient; produces state-of-the-art weakly supervised segmentation; and performs reasonably compared to full supervision. Our code is publicly available: https://gitlab.com/radiology/aim/carotid-artery-image-analysis/diameter-learning
APA
Camarasa, R., Kervadec, H., Bos, D. & de Bruijne, M.. (2022). Differentiable Boundary Point Extraction for Weakly Supervised Star-shaped Object Segmentation. Proceedings of The 5th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 172:188-198 Available from https://proceedings.mlr.press/v172/camarasa22a.html.

Related Material