nnUNet meets pathology: Bridging the gap for application to whole slide images and computational biomarkers

Joey Spronck, Thijs Gelton, Leander van Eekelen, Joep Bogaerts, Leslie Tessier, Mart van Rijthoven, Lieke van der Woude, Michel van den Heuvel, Willemijn Theelen, Jeroen van der Laak, Francesco Ciompi
Medical Imaging with Deep Learning, PMLR 227:1859-1874, 2024.

Abstract

Image segmentation is at the core of many tasks in medical imaging, including the engineering of computational biomarkers. While the self-configuring nnUNet framework for image segmentation tasks completely shifted the state-of-the-art in the radiology field, it has never been adapted to overcome its limitations for application on the pathology domain. Our study showcases the potential of nnUNet in computational pathology and bridges the gap that currently exists in utilizing nnUNet for pathology applications. Our proposed nnUNet for pathology framework has demonstrated its significance and potential to shift the state-of-the-art in the computational pathology field, as seen from the exceptional first-place segmentation ranking on the TIGER challenge’s experimental leaderboard 1. Our framework includes critical hyperparameter adjustments and pathology-specific color augmentations, as well as an essential WSI inference pipeline and a novel inference uncertainty approach that proves helpful for biomarker development. We release the code of our accurate and workflow-friendly segmentation tool to promote and foster growth within the computational pathology community.

Cite this Paper

BibTeX
@InProceedings{pmlr-v227-spronck24a, title = {nnUNet meets pathology: Bridging the gap for application to whole slide images and computational biomarkers}, author = {Spronck, Joey and Gelton, Thijs and van Eekelen, Leander and Bogaerts, Joep and Tessier, Leslie and van Rijthoven, Mart and van der Woude, Lieke and van den Heuvel, Michel and Theelen, Willemijn and van der Laak, Jeroen and Ciompi, Francesco}, booktitle = {Medical Imaging with Deep Learning}, pages = {1859--1874}, year = {2024}, editor = {Oguz, Ipek and Noble, Jack and Li, Xiaoxiao and Styner, Martin and Baumgartner, Christian and Rusu, Mirabela and Heinmann, Tobias and Kontos, Despina and Landman, Bennett and Dawant, Benoit}, volume = {227}, series = {Proceedings of Machine Learning Research}, month = {10--12 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v227/spronck24a/spronck24a.pdf}, url = {https://proceedings.mlr.press/v227/spronck24a.html}, abstract = {Image segmentation is at the core of many tasks in medical imaging, including the engineering of computational biomarkers. While the self-configuring nnUNet framework for image segmentation tasks completely shifted the state-of-the-art in the radiology field, it has never been adapted to overcome its limitations for application on the pathology domain. Our study showcases the potential of nnUNet in computational pathology and bridges the gap that currently exists in utilizing nnUNet for pathology applications. Our proposed nnUNet for pathology framework has demonstrated its significance and potential to shift the state-of-the-art in the computational pathology field, as seen from the exceptional first-place segmentation ranking on the TIGER challenge’s experimental leaderboard 1. Our framework includes critical hyperparameter adjustments and pathology-specific color augmentations, as well as an essential WSI inference pipeline and a novel inference uncertainty approach that proves helpful for biomarker development. We release the code of our accurate and workflow-friendly segmentation tool to promote and foster growth within the computational pathology community.} }
Endnote
%0 Conference Paper %T nnUNet meets pathology: Bridging the gap for application to whole slide images and computational biomarkers %A Joey Spronck %A Thijs Gelton %A Leander van Eekelen %A Joep Bogaerts %A Leslie Tessier %A Mart van Rijthoven %A Lieke van der Woude %A Michel van den Heuvel %A Willemijn Theelen %A Jeroen van der Laak %A Francesco Ciompi %B Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2024 %E Ipek Oguz %E Jack Noble %E Xiaoxiao Li %E Martin Styner %E Christian Baumgartner %E Mirabela Rusu %E Tobias Heinmann %E Despina Kontos %E Bennett Landman %E Benoit Dawant %F pmlr-v227-spronck24a %I PMLR %P 1859--1874 %U https://proceedings.mlr.press/v227/spronck24a.html %V 227 %X Image segmentation is at the core of many tasks in medical imaging, including the engineering of computational biomarkers. While the self-configuring nnUNet framework for image segmentation tasks completely shifted the state-of-the-art in the radiology field, it has never been adapted to overcome its limitations for application on the pathology domain. Our study showcases the potential of nnUNet in computational pathology and bridges the gap that currently exists in utilizing nnUNet for pathology applications. Our proposed nnUNet for pathology framework has demonstrated its significance and potential to shift the state-of-the-art in the computational pathology field, as seen from the exceptional first-place segmentation ranking on the TIGER challenge’s experimental leaderboard 1. Our framework includes critical hyperparameter adjustments and pathology-specific color augmentations, as well as an essential WSI inference pipeline and a novel inference uncertainty approach that proves helpful for biomarker development. We release the code of our accurate and workflow-friendly segmentation tool to promote and foster growth within the computational pathology community.
APA
Spronck, J., Gelton, T., van Eekelen, L., Bogaerts, J., Tessier, L., van Rijthoven, M., van der Woude, L., van den Heuvel, M., Theelen, W., van der Laak, J. & Ciompi, F.. (2024). nnUNet meets pathology: Bridging the gap for application to whole slide images and computational biomarkers. Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 227:1859-1874 Available from https://proceedings.mlr.press/v227/spronck24a.html.

Related Material