Attention-based Multiple Instance Learning with Mixed Supervision on the Camelyon16 Dataset

Paul Tourniaire, Marius Ilie, Paul Hofman, Nicholas Ayache, Herve Delingette
Proceedings of the MICCAI Workshop on Computational Pathology, PMLR 156:216-226, 2021.

Abstract

Since the standardization of Whole Slide Images (WSIs) digitization, the use of deep learning methods for the analysis of histological images has shown much potential. However, the sheer size of WSIs is a real challenge, as they are often up to 100,000 pixels wide and high at the highest resolution, and therefore cannot be processed directly by any model. Moreover, as the manual delineation of structures within WSIs is tedious, histological datasets often only contain slide-level labels, or a limited amount of delineated slides. In this context, multiple-instance learning (MIL) approaches have been proposed, considering WSIs as bags of smaller images, designated as tiles or patches. Among these methods, the attention-based MIL aims at learning the importance of each tile for the slide final classification while at the same time performing a clustering of those tiles. In this paper, we introduce the concept of mixed supervision within this framework, by exploiting tile-level labels in addition to slide-level labels to improve the classification of slides. More precisely, we show on the Camelyon16 dataset that even a small proportion of slides with pixel-wise annotations can improve their classification but also the localization of tumorous regions. This improves the consistency of the results between the tile and slide levels and the interpretability of the algorithm.

Cite this Paper

BibTeX
@InProceedings{pmlr-v156-tourniaire21a, title = {Attention-based Multiple Instance Learning with Mixed Supervision on the Camelyon16 Dataset}, author = {Tourniaire, Paul and Ilie, Marius and Hofman, Paul and Ayache, Nicholas and Delingette, Herve}, booktitle = {Proceedings of the MICCAI Workshop on Computational Pathology}, pages = {216--226}, year = {2021}, editor = {Atzori, Manfredo and Burlutskiy, Nikolay and Ciompi, Francesco and Li, Zhang and Minhas, Fayyaz and Müller, Henning and Peng, Tingying and Rajpoot, Nasir and Torben-Nielsen, Ben and van der Laak, Jeroen and Veta, Mitko and Yuan, Yinyin and Zlobec, Inti}, volume = {156}, series = {Proceedings of Machine Learning Research}, month = {27 Sep}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v156/tourniaire21a/tourniaire21a.pdf}, url = {https://proceedings.mlr.press/v156/tourniaire21a.html}, abstract = {Since the standardization of Whole Slide Images (WSIs) digitization, the use of deep learning methods for the analysis of histological images has shown much potential. However, the sheer size of WSIs is a real challenge, as they are often up to 100,000 pixels wide and high at the highest resolution, and therefore cannot be processed directly by any model. Moreover, as the manual delineation of structures within WSIs is tedious, histological datasets often only contain slide-level labels, or a limited amount of delineated slides. In this context, multiple-instance learning (MIL) approaches have been proposed, considering WSIs as bags of smaller images, designated as tiles or patches. Among these methods, the attention-based MIL aims at learning the importance of each tile for the slide final classification while at the same time performing a clustering of those tiles. In this paper, we introduce the concept of mixed supervision within this framework, by exploiting tile-level labels in addition to slide-level labels to improve the classification of slides. More precisely, we show on the Camelyon16 dataset that even a small proportion of slides with pixel-wise annotations can improve their classification but also the localization of tumorous regions. This improves the consistency of the results between the tile and slide levels and the interpretability of the algorithm.} }
Endnote
%0 Conference Paper %T Attention-based Multiple Instance Learning with Mixed Supervision on the Camelyon16 Dataset %A Paul Tourniaire %A Marius Ilie %A Paul Hofman %A Nicholas Ayache %A Herve Delingette %B Proceedings of the MICCAI Workshop on Computational Pathology %C Proceedings of Machine Learning Research %D 2021 %E Manfredo Atzori %E Nikolay Burlutskiy %E Francesco Ciompi %E Zhang Li %E Fayyaz Minhas %E Henning Müller %E Tingying Peng %E Nasir Rajpoot %E Ben Torben-Nielsen %E Jeroen van der Laak %E Mitko Veta %E Yinyin Yuan %E Inti Zlobec %F pmlr-v156-tourniaire21a %I PMLR %P 216--226 %U https://proceedings.mlr.press/v156/tourniaire21a.html %V 156 %X Since the standardization of Whole Slide Images (WSIs) digitization, the use of deep learning methods for the analysis of histological images has shown much potential. However, the sheer size of WSIs is a real challenge, as they are often up to 100,000 pixels wide and high at the highest resolution, and therefore cannot be processed directly by any model. Moreover, as the manual delineation of structures within WSIs is tedious, histological datasets often only contain slide-level labels, or a limited amount of delineated slides. In this context, multiple-instance learning (MIL) approaches have been proposed, considering WSIs as bags of smaller images, designated as tiles or patches. Among these methods, the attention-based MIL aims at learning the importance of each tile for the slide final classification while at the same time performing a clustering of those tiles. In this paper, we introduce the concept of mixed supervision within this framework, by exploiting tile-level labels in addition to slide-level labels to improve the classification of slides. More precisely, we show on the Camelyon16 dataset that even a small proportion of slides with pixel-wise annotations can improve their classification but also the localization of tumorous regions. This improves the consistency of the results between the tile and slide levels and the interpretability of the algorithm.
APA
Tourniaire, P., Ilie, M., Hofman, P., Ayache, N. & Delingette, H.. (2021). Attention-based Multiple Instance Learning with Mixed Supervision on the Camelyon16 Dataset. Proceedings of the MICCAI Workshop on Computational Pathology, in Proceedings of Machine Learning Research 156:216-226 Available from https://proceedings.mlr.press/v156/tourniaire21a.html.

Related Material