Unsupervised Stain Decomposition via Inversion Regulation for Multiplex Immunohistochemistry Images

Shahira Abousamra, Danielle Fassler, Jiachen Yao, Rajarsi R. Gupta, Tahsin Kurc, Luisa Escobar-Hoyos, Dimitris Samaras, Kenneth Shroyer, Joel Saltz, Chao Chen
Medical Imaging with Deep Learning, PMLR 227:74-94, 2024.

Abstract

Multiplex Immunohistochemistry (mIHC) is a cost-effective and accessible method for in situ labeling of multiple protein biomarkers in a tissue sample. By assigning a different stain to each biomarker, it allows the visualization of different types of cells within the tumor vicinity for downstream analysis. However, to detect different types of stains in a given mIHC image is a challenging problem, especially when the number of stains is high. Previous deep-learning-based methods mostly assume full supervision; yet the annotation can be costly. In this paper, we propose a novel unsupervised stain decomposition method to detect different stains simultaneously. Our method does not require any supervision, except for color samples of different stains. A main technical challenge is that the problem is underdetermined and can have multiple solutions. To conquer this issue, we propose a novel inversion regulation technique, which eliminates most undesirable solutions. On a 7-plexed IHC image dataset, the proposed method achieves high quality stain decomposition results without human annotation.

Cite this Paper

BibTeX
@InProceedings{pmlr-v227-abousamra24a, title = {Unsupervised Stain Decomposition via Inversion Regulation for Multiplex Immunohistochemistry Images}, author = {Abousamra, Shahira and Fassler, Danielle and Yao, Jiachen and Gupta, Rajarsi R. and Kurc, Tahsin and Escobar-Hoyos, Luisa and Samaras, Dimitris and Shroyer, Kenneth and Saltz, Joel and Chen, Chao}, booktitle = {Medical Imaging with Deep Learning}, pages = {74--94}, 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/abousamra24a/abousamra24a.pdf}, url = {https://proceedings.mlr.press/v227/abousamra24a.html}, abstract = {Multiplex Immunohistochemistry (mIHC) is a cost-effective and accessible method for in situ labeling of multiple protein biomarkers in a tissue sample. By assigning a different stain to each biomarker, it allows the visualization of different types of cells within the tumor vicinity for downstream analysis. However, to detect different types of stains in a given mIHC image is a challenging problem, especially when the number of stains is high. Previous deep-learning-based methods mostly assume full supervision; yet the annotation can be costly. In this paper, we propose a novel unsupervised stain decomposition method to detect different stains simultaneously. Our method does not require any supervision, except for color samples of different stains. A main technical challenge is that the problem is underdetermined and can have multiple solutions. To conquer this issue, we propose a novel inversion regulation technique, which eliminates most undesirable solutions. On a 7-plexed IHC image dataset, the proposed method achieves high quality stain decomposition results without human annotation.} }
Endnote
%0 Conference Paper %T Unsupervised Stain Decomposition via Inversion Regulation for Multiplex Immunohistochemistry Images %A Shahira Abousamra %A Danielle Fassler %A Jiachen Yao %A Rajarsi R. Gupta %A Tahsin Kurc %A Luisa Escobar-Hoyos %A Dimitris Samaras %A Kenneth Shroyer %A Joel Saltz %A Chao Chen %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-abousamra24a %I PMLR %P 74--94 %U https://proceedings.mlr.press/v227/abousamra24a.html %V 227 %X Multiplex Immunohistochemistry (mIHC) is a cost-effective and accessible method for in situ labeling of multiple protein biomarkers in a tissue sample. By assigning a different stain to each biomarker, it allows the visualization of different types of cells within the tumor vicinity for downstream analysis. However, to detect different types of stains in a given mIHC image is a challenging problem, especially when the number of stains is high. Previous deep-learning-based methods mostly assume full supervision; yet the annotation can be costly. In this paper, we propose a novel unsupervised stain decomposition method to detect different stains simultaneously. Our method does not require any supervision, except for color samples of different stains. A main technical challenge is that the problem is underdetermined and can have multiple solutions. To conquer this issue, we propose a novel inversion regulation technique, which eliminates most undesirable solutions. On a 7-plexed IHC image dataset, the proposed method achieves high quality stain decomposition results without human annotation.
APA
Abousamra, S., Fassler, D., Yao, J., Gupta, R.R., Kurc, T., Escobar-Hoyos, L., Samaras, D., Shroyer, K., Saltz, J. & Chen, C.. (2024). Unsupervised Stain Decomposition via Inversion Regulation for Multiplex Immunohistochemistry Images. Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 227:74-94 Available from https://proceedings.mlr.press/v227/abousamra24a.html.

Related Material