End-to-end Multiple Instance Learning for Whole-Slide Cytopathology of Urothelial Carcinoma

Joshua Butke, Tatjana Frick, Florian Roghmann, Samir F El-Mashtoly, Klaus Gerwert, Axel Mosig
Proceedings of the MICCAI Workshop on Computational Pathology, PMLR 156:57-68, 2021.

Abstract

As a non-invasive approach, cytopathology of urine sediment is a highly promising approach to diagnosing urothelial carcinoma. However, computational assessment of the cytopathological status of a sample raises the challenge of identifying few cancerous cells among thousands of cells in a microscopic whole-slide image. To address this challenge, we propose an end-to-end trainable multiple instance learning approach that combines the attention mechanism and hard negative mining to classify hematoxylin and eosin stained patient-level whole-slide images of urine sediment cells. The singular cells are extracted by a simple foreground detection algorithm. With feature embeddings computed for each image patch in a bag by a convolutional neural network, the attention mechanism serves as the pooling operator, enabling a bag-level prediction while still giving an interpretable score for each image patch. This enables the identification of key instances and potential regions of interest that trigger a patient-level decision. Our results show that the proposed system can differentiate between normal and cancerous urothelial cells, thus enabling the non-invasive diagnosis of urothelial carcinoma in patients using urine sediment analysis.

Cite this Paper

BibTeX
@InProceedings{pmlr-v156-butke21a, title = {End-to-end Multiple Instance Learning for Whole-Slide Cytopathology of Urothelial Carcinoma}, author = {Butke, Joshua and Frick, Tatjana and Roghmann, Florian and El-Mashtoly, Samir F and Gerwert, Klaus and Mosig, Axel}, booktitle = {Proceedings of the MICCAI Workshop on Computational Pathology}, pages = {57--68}, 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/butke21a/butke21a.pdf}, url = {https://proceedings.mlr.press/v156/butke21a.html}, abstract = {As a non-invasive approach, cytopathology of urine sediment is a highly promising approach to diagnosing urothelial carcinoma. However, computational assessment of the cytopathological status of a sample raises the challenge of identifying few cancerous cells among thousands of cells in a microscopic whole-slide image. To address this challenge, we propose an end-to-end trainable multiple instance learning approach that combines the attention mechanism and hard negative mining to classify hematoxylin and eosin stained patient-level whole-slide images of urine sediment cells. The singular cells are extracted by a simple foreground detection algorithm. With feature embeddings computed for each image patch in a bag by a convolutional neural network, the attention mechanism serves as the pooling operator, enabling a bag-level prediction while still giving an interpretable score for each image patch. This enables the identification of key instances and potential regions of interest that trigger a patient-level decision. Our results show that the proposed system can differentiate between normal and cancerous urothelial cells, thus enabling the non-invasive diagnosis of urothelial carcinoma in patients using urine sediment analysis.} }
Endnote
%0 Conference Paper %T End-to-end Multiple Instance Learning for Whole-Slide Cytopathology of Urothelial Carcinoma %A Joshua Butke %A Tatjana Frick %A Florian Roghmann %A Samir F El-Mashtoly %A Klaus Gerwert %A Axel Mosig %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-butke21a %I PMLR %P 57--68 %U https://proceedings.mlr.press/v156/butke21a.html %V 156 %X As a non-invasive approach, cytopathology of urine sediment is a highly promising approach to diagnosing urothelial carcinoma. However, computational assessment of the cytopathological status of a sample raises the challenge of identifying few cancerous cells among thousands of cells in a microscopic whole-slide image. To address this challenge, we propose an end-to-end trainable multiple instance learning approach that combines the attention mechanism and hard negative mining to classify hematoxylin and eosin stained patient-level whole-slide images of urine sediment cells. The singular cells are extracted by a simple foreground detection algorithm. With feature embeddings computed for each image patch in a bag by a convolutional neural network, the attention mechanism serves as the pooling operator, enabling a bag-level prediction while still giving an interpretable score for each image patch. This enables the identification of key instances and potential regions of interest that trigger a patient-level decision. Our results show that the proposed system can differentiate between normal and cancerous urothelial cells, thus enabling the non-invasive diagnosis of urothelial carcinoma in patients using urine sediment analysis.
APA
Butke, J., Frick, T., Roghmann, F., El-Mashtoly, S.F., Gerwert, K. & Mosig, A.. (2021). End-to-end Multiple Instance Learning for Whole-Slide Cytopathology of Urothelial Carcinoma. Proceedings of the MICCAI Workshop on Computational Pathology, in Proceedings of Machine Learning Research 156:57-68 Available from https://proceedings.mlr.press/v156/butke21a.html.

Related Material