Weakly Supervised Deep Nuclei Segmentation using Points Annotation in Histopathology Images

Hui Qu, Pengxiang Wu, Qiaoying Huang, Jingru Yi, Gregory M. Riedlinger, Subhajyoti De, Dimitris N. Metaxas
Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning, PMLR 102:390-400, 2019.

Abstract

Nuclei segmentation is a fundamental task in histopathological image analysis. Typically, such segmentation tasks require significant effort to manually generate pixel-wise annotations for fully supervised training. To alleviate the manual effort, in this paper we propose a novel approach using points only annotation. Two types of coarse labels with complementary information are derived from the points annotation, and are then utilized to train a deep neural network. The fully-connected conditional random field loss is utilized to further refine the model without introducing extra computational complexity during inference. Experimental results on two nuclei segmentation datasets reveal that the proposed method is able to achieve competitive performance compared to the fully supervised counterpart and the state-of-the-art methods while requiring significantly less annotation effort. Our code is publicly available.

Cite this Paper

BibTeX
@InProceedings{pmlr-v102-qu19a, title = {Weakly Supervised Deep Nuclei Segmentation using Points Annotation in Histopathology Images}, author = {Qu, Hui and Wu, Pengxiang and Huang, Qiaoying and Yi, Jingru and Riedlinger, Gregory M. and De, Subhajyoti and Metaxas, Dimitris N.}, booktitle = {Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning}, pages = {390--400}, year = {2019}, editor = {Cardoso, M. Jorge and Feragen, Aasa and Glocker, Ben and Konukoglu, Ender and Oguz, Ipek and Unal, Gozde and Vercauteren, Tom}, volume = {102}, series = {Proceedings of Machine Learning Research}, month = {08--10 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v102/qu19a/qu19a.pdf}, url = {https://proceedings.mlr.press/v102/qu19a.html}, abstract = {Nuclei segmentation is a fundamental task in histopathological image analysis. Typically, such segmentation tasks require significant effort to manually generate pixel-wise annotations for fully supervised training. To alleviate the manual effort, in this paper we propose a novel approach using points only annotation. Two types of coarse labels with complementary information are derived from the points annotation, and are then utilized to train a deep neural network. The fully-connected conditional random field loss is utilized to further refine the model without introducing extra computational complexity during inference. Experimental results on two nuclei segmentation datasets reveal that the proposed method is able to achieve competitive performance compared to the fully supervised counterpart and the state-of-the-art methods while requiring significantly less annotation effort. Our code is publicly available.} }
Endnote
%0 Conference Paper %T Weakly Supervised Deep Nuclei Segmentation using Points Annotation in Histopathology Images %A Hui Qu %A Pengxiang Wu %A Qiaoying Huang %A Jingru Yi %A Gregory M. Riedlinger %A Subhajyoti De %A Dimitris N. Metaxas %B Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2019 %E M. Jorge Cardoso %E Aasa Feragen %E Ben Glocker %E Ender Konukoglu %E Ipek Oguz %E Gozde Unal %E Tom Vercauteren %F pmlr-v102-qu19a %I PMLR %P 390--400 %U https://proceedings.mlr.press/v102/qu19a.html %V 102 %X Nuclei segmentation is a fundamental task in histopathological image analysis. Typically, such segmentation tasks require significant effort to manually generate pixel-wise annotations for fully supervised training. To alleviate the manual effort, in this paper we propose a novel approach using points only annotation. Two types of coarse labels with complementary information are derived from the points annotation, and are then utilized to train a deep neural network. The fully-connected conditional random field loss is utilized to further refine the model without introducing extra computational complexity during inference. Experimental results on two nuclei segmentation datasets reveal that the proposed method is able to achieve competitive performance compared to the fully supervised counterpart and the state-of-the-art methods while requiring significantly less annotation effort. Our code is publicly available.
APA
Qu, H., Wu, P., Huang, Q., Yi, J., Riedlinger, G.M., De, S. & Metaxas, D.N.. (2019). Weakly Supervised Deep Nuclei Segmentation using Points Annotation in Histopathology Images. Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 102:390-400 Available from https://proceedings.mlr.press/v102/qu19a.html.

Related Material