A regularization term for slide correlation reduction in whole slide image analysis with deep learning

Hongrun Zhang, Yanda Meng, Xuesheng Qian, Xiaoyun Yang, Sarah E. Coupland, Yalin Zheng
Proceedings of the Fourth Conference on Medical Imaging with Deep Learning, PMLR 143:842-854, 2021.

Abstract

To develop deep learning-based models for automatic analysis of histopathology whole slide images (WSIs), the atomic entities to be directly processed are often the smaller patches cropped from WSIs as it is not always possible to feed a whole WSI to a model given its enormous size. However, a trained model tends to relate the slide-specific characteristics to diagnosis results because a large number of patches cropped from the same WSI will share common slide features and thus have strong correlations between them, resulting in deteriorated generalization capability of the trained model. Current approaches to alleviate this issue include data pre-processing (stain normalization or color augmentation) and adversarial learning, both of which introduce extra complications in computations. Alternatively, we propose to reduce the impact of this issue by introducing a new regularization term to the standard loss function to reduce the correlation of the patches from the same WSI. It is intuitive and easy-to-implement and introduces comparably smaller computation overhead compared to existing approaches. Experimental results prove that the proposed regularization term is able to enhance the generalization capability of learning models and consequently to achieve better performance. The code is available in: \url{https://github.com/hrzhang1123/SlideCorrelationReduction}.

Cite this Paper

BibTeX
@InProceedings{pmlr-v143-zhang21a, title = {A regularization term for slide correlation reduction in whole slide image analysis with deep learning}, author = {Zhang, Hongrun and Meng, Yanda and Qian, Xuesheng and Yang, Xiaoyun and Coupland, Sarah E. and Zheng, Yalin}, booktitle = {Proceedings of the Fourth Conference on Medical Imaging with Deep Learning}, pages = {842--854}, year = {2021}, editor = {Heinrich, Mattias and Dou, Qi and de Bruijne, Marleen and Lellmann, Jan and Schläfer, Alexander and Ernst, Floris}, volume = {143}, series = {Proceedings of Machine Learning Research}, month = {07--09 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v143/zhang21a/zhang21a.pdf}, url = {https://proceedings.mlr.press/v143/zhang21a.html}, abstract = {To develop deep learning-based models for automatic analysis of histopathology whole slide images (WSIs), the atomic entities to be directly processed are often the smaller patches cropped from WSIs as it is not always possible to feed a whole WSI to a model given its enormous size. However, a trained model tends to relate the slide-specific characteristics to diagnosis results because a large number of patches cropped from the same WSI will share common slide features and thus have strong correlations between them, resulting in deteriorated generalization capability of the trained model. Current approaches to alleviate this issue include data pre-processing (stain normalization or color augmentation) and adversarial learning, both of which introduce extra complications in computations. Alternatively, we propose to reduce the impact of this issue by introducing a new regularization term to the standard loss function to reduce the correlation of the patches from the same WSI. It is intuitive and easy-to-implement and introduces comparably smaller computation overhead compared to existing approaches. Experimental results prove that the proposed regularization term is able to enhance the generalization capability of learning models and consequently to achieve better performance. The code is available in: \url{https://github.com/hrzhang1123/SlideCorrelationReduction}.} }
Endnote
%0 Conference Paper %T A regularization term for slide correlation reduction in whole slide image analysis with deep learning %A Hongrun Zhang %A Yanda Meng %A Xuesheng Qian %A Xiaoyun Yang %A Sarah E. Coupland %A Yalin Zheng %B Proceedings of the Fourth Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2021 %E Mattias Heinrich %E Qi Dou %E Marleen de Bruijne %E Jan Lellmann %E Alexander Schläfer %E Floris Ernst %F pmlr-v143-zhang21a %I PMLR %P 842--854 %U https://proceedings.mlr.press/v143/zhang21a.html %V 143 %X To develop deep learning-based models for automatic analysis of histopathology whole slide images (WSIs), the atomic entities to be directly processed are often the smaller patches cropped from WSIs as it is not always possible to feed a whole WSI to a model given its enormous size. However, a trained model tends to relate the slide-specific characteristics to diagnosis results because a large number of patches cropped from the same WSI will share common slide features and thus have strong correlations between them, resulting in deteriorated generalization capability of the trained model. Current approaches to alleviate this issue include data pre-processing (stain normalization or color augmentation) and adversarial learning, both of which introduce extra complications in computations. Alternatively, we propose to reduce the impact of this issue by introducing a new regularization term to the standard loss function to reduce the correlation of the patches from the same WSI. It is intuitive and easy-to-implement and introduces comparably smaller computation overhead compared to existing approaches. Experimental results prove that the proposed regularization term is able to enhance the generalization capability of learning models and consequently to achieve better performance. The code is available in: \url{https://github.com/hrzhang1123/SlideCorrelationReduction}.
APA
Zhang, H., Meng, Y., Qian, X., Yang, X., Coupland, S.E. & Zheng, Y.. (2021). A regularization term for slide correlation reduction in whole slide image analysis with deep learning. Proceedings of the Fourth Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 143:842-854 Available from https://proceedings.mlr.press/v143/zhang21a.html.

Related Material