Unsupervised Domain Adaptation for the Histopathological Cell Segmentation through Self-Ensembling

Chaoqun Li, Yitian Zhou, Tangqi Shi, Yenan Wu, Meng Yang, Zhongyu Li
Proceedings of the MICCAI Workshop on Computational Pathology, PMLR 156:151-158, 2021.

Abstract

Histopathological images are generally considered as the golden standard for clinical diagnosis and cancer grading. Accurate segmentation of cells/nuclei from histopathological images is a critical step to obtain reliable morphological information for quantitative analysis. However, cell/nuclei segmentation relies heavily on well-annotated datasets, which are extremely labor-intensive, time-consuming, and expensive in practical applications. Meanwhile, one might want to fine-tune pretrained models on certain target datasets. But it is always difficult to collect enough target training images for proper fine-tuning. Therefore, there is a need for methods that can transfer learned information from one domain to another without additional target annotations. In this paper, we propose a novel framework for cell segmentation on the unlabeled images through the unsupervised domain adaptation with self-ensembling. It is achieved by applying generative adversarial networks (GANs) for the unsupervised domain adaptation of cell segmentation crossing different tissues. Images in the source and target domain can be differentiated through the learned discriminator. Meanwhile, we present a self-ensembling model to consider the source and the target domain together as a semi-supervised segmentation task to reduce the differences of outputs. Additionally, we introduce conditional random field (CRF) as post-processing to preserve the local consistency on the outputs. We validate our framework with unsupervised domain adaptation on three public cell segmentation datasets captured from different types of tissues, which achieved superior performance in comparison with state-of-the-art.

Cite this Paper

BibTeX
@InProceedings{pmlr-v156-li21a, title = {Unsupervised Domain Adaptation for the Histopathological Cell Segmentation through Self-Ensembling}, author = {Li, Chaoqun and Zhou, Yitian and Shi, Tangqi and Wu, Yenan and Yang, Meng and Li, Zhongyu}, booktitle = {Proceedings of the MICCAI Workshop on Computational Pathology}, pages = {151--158}, 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/li21a/li21a.pdf}, url = {https://proceedings.mlr.press/v156/li21a.html}, abstract = {Histopathological images are generally considered as the golden standard for clinical diagnosis and cancer grading. Accurate segmentation of cells/nuclei from histopathological images is a critical step to obtain reliable morphological information for quantitative analysis. However, cell/nuclei segmentation relies heavily on well-annotated datasets, which are extremely labor-intensive, time-consuming, and expensive in practical applications. Meanwhile, one might want to fine-tune pretrained models on certain target datasets. But it is always difficult to collect enough target training images for proper fine-tuning. Therefore, there is a need for methods that can transfer learned information from one domain to another without additional target annotations. In this paper, we propose a novel framework for cell segmentation on the unlabeled images through the unsupervised domain adaptation with self-ensembling. It is achieved by applying generative adversarial networks (GANs) for the unsupervised domain adaptation of cell segmentation crossing different tissues. Images in the source and target domain can be differentiated through the learned discriminator. Meanwhile, we present a self-ensembling model to consider the source and the target domain together as a semi-supervised segmentation task to reduce the differences of outputs. Additionally, we introduce conditional random field (CRF) as post-processing to preserve the local consistency on the outputs. We validate our framework with unsupervised domain adaptation on three public cell segmentation datasets captured from different types of tissues, which achieved superior performance in comparison with state-of-the-art.} }
Endnote
%0 Conference Paper %T Unsupervised Domain Adaptation for the Histopathological Cell Segmentation through Self-Ensembling %A Chaoqun Li %A Yitian Zhou %A Tangqi Shi %A Yenan Wu %A Meng Yang %A Zhongyu Li %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-li21a %I PMLR %P 151--158 %U https://proceedings.mlr.press/v156/li21a.html %V 156 %X Histopathological images are generally considered as the golden standard for clinical diagnosis and cancer grading. Accurate segmentation of cells/nuclei from histopathological images is a critical step to obtain reliable morphological information for quantitative analysis. However, cell/nuclei segmentation relies heavily on well-annotated datasets, which are extremely labor-intensive, time-consuming, and expensive in practical applications. Meanwhile, one might want to fine-tune pretrained models on certain target datasets. But it is always difficult to collect enough target training images for proper fine-tuning. Therefore, there is a need for methods that can transfer learned information from one domain to another without additional target annotations. In this paper, we propose a novel framework for cell segmentation on the unlabeled images through the unsupervised domain adaptation with self-ensembling. It is achieved by applying generative adversarial networks (GANs) for the unsupervised domain adaptation of cell segmentation crossing different tissues. Images in the source and target domain can be differentiated through the learned discriminator. Meanwhile, we present a self-ensembling model to consider the source and the target domain together as a semi-supervised segmentation task to reduce the differences of outputs. Additionally, we introduce conditional random field (CRF) as post-processing to preserve the local consistency on the outputs. We validate our framework with unsupervised domain adaptation on three public cell segmentation datasets captured from different types of tissues, which achieved superior performance in comparison with state-of-the-art.
APA
Li, C., Zhou, Y., Shi, T., Wu, Y., Yang, M. & Li, Z.. (2021). Unsupervised Domain Adaptation for the Histopathological Cell Segmentation through Self-Ensembling. Proceedings of the MICCAI Workshop on Computational Pathology, in Proceedings of Machine Learning Research 156:151-158 Available from https://proceedings.mlr.press/v156/li21a.html.

Related Material