Segmentation-Consistent Probabilistic Lesion Counting

Julien Schroeter, Chelsea Myers-Colet, Douglas L Arnold, Tal Arbel
Proceedings of The 5th International Conference on Medical Imaging with Deep Learning, PMLR 172:1034-1056, 2022.

Abstract

Lesion counts are important indicators of disease severity, patient prognosis, and treatment efficacy, yet counting as a task in medical imaging is often overlooked in favor of segmentation. This work introduces a novel continuously differentiable function that maps lesion segmentation predictions to lesion count probability distributions in a consistent manner. The proposed end-to-end approach—which consists of voxel clustering, lesion-level voxel probability aggregation, and Poisson-binomial counting—is non-parametric and thus offers a robust and consistent way to augment lesion segmentation models with post hoc counting capabilities. Experiments on Gadolinium-enhancing lesion counting demonstrate that our method outputs accurate and well-calibrated count distributions that capture meaningful uncertainty information. They also reveal that our model is suitable for multi-task learning of lesion segmentation, is efficient in low data regimes, and is robust to adversarial attacks.

Cite this Paper

BibTeX
@InProceedings{pmlr-v172-schroeter22a, title = {Segmentation-Consistent Probabilistic Lesion Counting}, author = {Schroeter, Julien and Myers-Colet, Chelsea and Arnold, Douglas L and Arbel, Tal}, booktitle = {Proceedings of The 5th International Conference on Medical Imaging with Deep Learning}, pages = {1034--1056}, 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/schroeter22a/schroeter22a.pdf}, url = {https://proceedings.mlr.press/v172/schroeter22a.html}, abstract = {Lesion counts are important indicators of disease severity, patient prognosis, and treatment efficacy, yet counting as a task in medical imaging is often overlooked in favor of segmentation. This work introduces a novel continuously differentiable function that maps lesion segmentation predictions to lesion count probability distributions in a consistent manner. The proposed end-to-end approach—which consists of voxel clustering, lesion-level voxel probability aggregation, and Poisson-binomial counting—is non-parametric and thus offers a robust and consistent way to augment lesion segmentation models with post hoc counting capabilities. Experiments on Gadolinium-enhancing lesion counting demonstrate that our method outputs accurate and well-calibrated count distributions that capture meaningful uncertainty information. They also reveal that our model is suitable for multi-task learning of lesion segmentation, is efficient in low data regimes, and is robust to adversarial attacks.} }
Endnote
%0 Conference Paper %T Segmentation-Consistent Probabilistic Lesion Counting %A Julien Schroeter %A Chelsea Myers-Colet %A Douglas L Arnold %A Tal Arbel %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-schroeter22a %I PMLR %P 1034--1056 %U https://proceedings.mlr.press/v172/schroeter22a.html %V 172 %X Lesion counts are important indicators of disease severity, patient prognosis, and treatment efficacy, yet counting as a task in medical imaging is often overlooked in favor of segmentation. This work introduces a novel continuously differentiable function that maps lesion segmentation predictions to lesion count probability distributions in a consistent manner. The proposed end-to-end approach—which consists of voxel clustering, lesion-level voxel probability aggregation, and Poisson-binomial counting—is non-parametric and thus offers a robust and consistent way to augment lesion segmentation models with post hoc counting capabilities. Experiments on Gadolinium-enhancing lesion counting demonstrate that our method outputs accurate and well-calibrated count distributions that capture meaningful uncertainty information. They also reveal that our model is suitable for multi-task learning of lesion segmentation, is efficient in low data regimes, and is robust to adversarial attacks.
APA
Schroeter, J., Myers-Colet, C., Arnold, D.L. & Arbel, T.. (2022). Segmentation-Consistent Probabilistic Lesion Counting. Proceedings of The 5th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 172:1034-1056 Available from https://proceedings.mlr.press/v172/schroeter22a.html.

Related Material