Learning from sparsely annotated data for semantic segmentation in histopathology images

John-Melle Bokhorst, Hans Pinckaers, Peter van Zwam, Iris Nagtegaal, Jeroen van der Laak, Francesco Ciompi
Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning, PMLR 102:84-91, 2019.

Abstract

We investigate the problem of building convolutional networks for semantic segmentation in histopathology images when weak supervision in the form of sparse manual annotations is provided in the training set. We propose to address this problem by modifying the loss function in order to balance the contribution of each pixel of the input data. We introduce and compare two approaches of loss balancing when sparse annotations are provided, namely (1) instance based balancing and (2) mini-batch based balancing. We also consider a scenario of full supervision in the form of dense annotations, and compare the performance of using either sparse or dense annotations with the proposed balancing schemes. Finally, we show that using a bulk of sparse annotations and a small fraction of dense annotations allows to achieve performance comparable to full supervision.

Cite this Paper

BibTeX
@InProceedings{pmlr-v102-bokhorst19a, title = {Learning from sparsely annotated data for semantic segmentation in histopathology images}, author = {Bokhorst, {John-Melle} and Pinckaers, Hans and {van Zwam}, Peter and Nagtegaal, Iris and {van der Laak}, Jeroen and Ciompi, Francesco}, booktitle = {Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning}, pages = {84--91}, year = {2019}, editor = {Cardoso, M. Jorge and Feragen, Aasa and Glocker, Ben and Konukoglu, Ender and Oguz, Ipek and Unal, Gozde and Vercauteren, Tom}, volume = {102}, series = {Proceedings of Machine Learning Research}, month = {08--10 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v102/bokhorst19a/bokhorst19a.pdf}, url = {https://proceedings.mlr.press/v102/bokhorst19a.html}, abstract = {We investigate the problem of building convolutional networks for semantic segmentation in histopathology images when weak supervision in the form of sparse manual annotations is provided in the training set. We propose to address this problem by modifying the loss function in order to balance the contribution of each pixel of the input data. We introduce and compare two approaches of loss balancing when sparse annotations are provided, namely (1) instance based balancing and (2) mini-batch based balancing. We also consider a scenario of full supervision in the form of dense annotations, and compare the performance of using either sparse or dense annotations with the proposed balancing schemes. Finally, we show that using a bulk of sparse annotations and a small fraction of dense annotations allows to achieve performance comparable to full supervision.} }
Endnote
%0 Conference Paper %T Learning from sparsely annotated data for semantic segmentation in histopathology images %A John-Melle Bokhorst %A Hans Pinckaers %A Peter van Zwam %A Iris Nagtegaal %A Jeroen van der Laak %A Francesco Ciompi %B Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2019 %E M. Jorge Cardoso %E Aasa Feragen %E Ben Glocker %E Ender Konukoglu %E Ipek Oguz %E Gozde Unal %E Tom Vercauteren %F pmlr-v102-bokhorst19a %I PMLR %P 84--91 %U https://proceedings.mlr.press/v102/bokhorst19a.html %V 102 %X We investigate the problem of building convolutional networks for semantic segmentation in histopathology images when weak supervision in the form of sparse manual annotations is provided in the training set. We propose to address this problem by modifying the loss function in order to balance the contribution of each pixel of the input data. We introduce and compare two approaches of loss balancing when sparse annotations are provided, namely (1) instance based balancing and (2) mini-batch based balancing. We also consider a scenario of full supervision in the form of dense annotations, and compare the performance of using either sparse or dense annotations with the proposed balancing schemes. Finally, we show that using a bulk of sparse annotations and a small fraction of dense annotations allows to achieve performance comparable to full supervision.
APA
Bokhorst, J., Pinckaers, H., van Zwam, P., Nagtegaal, I., van der Laak, J. & Ciompi, F.. (2019). Learning from sparsely annotated data for semantic segmentation in histopathology images. Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 102:84-91 Available from https://proceedings.mlr.press/v102/bokhorst19a.html.

Related Material