SparseConvMIL: Sparse Convolutional Context-Aware Multiple Instance Learning for Whole Slide Image Classification

Marvin Lerousseau, Maria Vakalopoulou, Eric Deutsch, Nikos Paragios
Proceedings of the MICCAI Workshop on Computational Pathology, PMLR 156:129-139, 2021.

Abstract

Multiple instance learning (MIL) is the preferred approach for whole slide image classification. However, most MIL approaches do not exploit the interdependencies of tiles extracted from a whole slide image, which could provide valuable cues for classification. This paper presents a novel MIL approach that exploits the spatial relationship of tiles for classifying whole slide images. To do so, a sparse map is built from tiles embeddings, and is then classified by a sparse-input CNN. It obtained state-of-the-art performance over popular MIL approaches on the classification of cancer subtype involving 10,000 whole slide images. Our results suggest that the proposed approach might (i) improve the representation learning of instances and (ii) exploit the context of instance embeddings to enhance the classification performance. The code of this work is made open-source.

Cite this Paper

BibTeX
@InProceedings{pmlr-v156-lerousseau21a, title = {SparseConvMIL: Sparse Convolutional Context-Aware Multiple Instance Learning for Whole Slide Image Classification}, author = {Lerousseau, Marvin and Vakalopoulou, Maria and Deutsch, Eric and Paragios, Nikos}, booktitle = {Proceedings of the MICCAI Workshop on Computational Pathology}, pages = {129--139}, 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/lerousseau21a/lerousseau21a.pdf}, url = {https://proceedings.mlr.press/v156/lerousseau21a.html}, abstract = {Multiple instance learning (MIL) is the preferred approach for whole slide image classification. However, most MIL approaches do not exploit the interdependencies of tiles extracted from a whole slide image, which could provide valuable cues for classification. This paper presents a novel MIL approach that exploits the spatial relationship of tiles for classifying whole slide images. To do so, a sparse map is built from tiles embeddings, and is then classified by a sparse-input CNN. It obtained state-of-the-art performance over popular MIL approaches on the classification of cancer subtype involving 10,000 whole slide images. Our results suggest that the proposed approach might (i) improve the representation learning of instances and (ii) exploit the context of instance embeddings to enhance the classification performance. The code of this work is made open-source.} }
Endnote
%0 Conference Paper %T SparseConvMIL: Sparse Convolutional Context-Aware Multiple Instance Learning for Whole Slide Image Classification %A Marvin Lerousseau %A Maria Vakalopoulou %A Eric Deutsch %A Nikos Paragios %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-lerousseau21a %I PMLR %P 129--139 %U https://proceedings.mlr.press/v156/lerousseau21a.html %V 156 %X Multiple instance learning (MIL) is the preferred approach for whole slide image classification. However, most MIL approaches do not exploit the interdependencies of tiles extracted from a whole slide image, which could provide valuable cues for classification. This paper presents a novel MIL approach that exploits the spatial relationship of tiles for classifying whole slide images. To do so, a sparse map is built from tiles embeddings, and is then classified by a sparse-input CNN. It obtained state-of-the-art performance over popular MIL approaches on the classification of cancer subtype involving 10,000 whole slide images. Our results suggest that the proposed approach might (i) improve the representation learning of instances and (ii) exploit the context of instance embeddings to enhance the classification performance. The code of this work is made open-source.
APA
Lerousseau, M., Vakalopoulou, M., Deutsch, E. & Paragios, N.. (2021). SparseConvMIL: Sparse Convolutional Context-Aware Multiple Instance Learning for Whole Slide Image Classification. Proceedings of the MICCAI Workshop on Computational Pathology, in Proceedings of Machine Learning Research 156:129-139 Available from https://proceedings.mlr.press/v156/lerousseau21a.html.

Related Material