VOCA: Cell Nuclei Detection In Histopathology Images By Vector Oriented Confidence Accumulation

Chensu Xie, Chad M. Vanderbilt, Anne Grabenstetter, Thomas J. Fuchs
Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning, PMLR 102:527-539, 2019.

Abstract

Cell nuclei detection is the basis for many tasks in Computational Pathology ranging from cancer diagnosis to survival analysis. It is a challenging task due to the significant inter/intra-class variation of cellular morphology. The problem is aggravated by the need for additional accurate localization of the nuclei for downstream applications. Most of the existing methods regress the probability of each pixel being a nuclei centroid, while relying on post-processing to implicitly infer the rough location of nuclei centers. To solve this problem we propose a novel multi-task learning framework called vector oriented confidence accumulation (VOCA) based on deep convolutional encoder-decoder. The model learns a confidence score, localization vector and weight of contribution for each pixel. The three tasks are trained concurrently and the confidence of pixels are accumulated according to the localization vectors in detection stage to generate a sparse map that describes accurate and precise cell locations. A detailed comparison to the state-of-the-art based on a publicly available colorectal cancer dataset showed superior detection performance and significantly higher localization accuracy.

Cite this Paper

BibTeX
@InProceedings{pmlr-v102-xie19a, title = {VOCA: Cell Nuclei Detection In Histopathology Images By Vector Oriented Confidence Accumulation}, author = {Xie, Chensu and Vanderbilt, Chad M. and Grabenstetter, Anne and Fuchs, Thomas J.}, booktitle = {Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning}, pages = {527--539}, 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/xie19a/xie19a.pdf}, url = {https://proceedings.mlr.press/v102/xie19a.html}, abstract = { Cell nuclei detection is the basis for many tasks in Computational Pathology ranging from cancer diagnosis to survival analysis. It is a challenging task due to the significant inter/intra-class variation of cellular morphology. The problem is aggravated by the need for additional accurate localization of the nuclei for downstream applications. Most of the existing methods regress the probability of each pixel being a nuclei centroid, while relying on post-processing to implicitly infer the rough location of nuclei centers. To solve this problem we propose a novel multi-task learning framework called vector oriented confidence accumulation (VOCA) based on deep convolutional encoder-decoder. The model learns a confidence score, localization vector and weight of contribution for each pixel. The three tasks are trained concurrently and the confidence of pixels are accumulated according to the localization vectors in detection stage to generate a sparse map that describes accurate and precise cell locations. A detailed comparison to the state-of-the-art based on a publicly available colorectal cancer dataset showed superior detection performance and significantly higher localization accuracy.} }
Endnote
%0 Conference Paper %T VOCA: Cell Nuclei Detection In Histopathology Images By Vector Oriented Confidence Accumulation %A Chensu Xie %A Chad M. Vanderbilt %A Anne Grabenstetter %A Thomas J. Fuchs %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-xie19a %I PMLR %P 527--539 %U https://proceedings.mlr.press/v102/xie19a.html %V 102 %X Cell nuclei detection is the basis for many tasks in Computational Pathology ranging from cancer diagnosis to survival analysis. It is a challenging task due to the significant inter/intra-class variation of cellular morphology. The problem is aggravated by the need for additional accurate localization of the nuclei for downstream applications. Most of the existing methods regress the probability of each pixel being a nuclei centroid, while relying on post-processing to implicitly infer the rough location of nuclei centers. To solve this problem we propose a novel multi-task learning framework called vector oriented confidence accumulation (VOCA) based on deep convolutional encoder-decoder. The model learns a confidence score, localization vector and weight of contribution for each pixel. The three tasks are trained concurrently and the confidence of pixels are accumulated according to the localization vectors in detection stage to generate a sparse map that describes accurate and precise cell locations. A detailed comparison to the state-of-the-art based on a publicly available colorectal cancer dataset showed superior detection performance and significantly higher localization accuracy.
APA
Xie, C., Vanderbilt, C.M., Grabenstetter, A. & Fuchs, T.J.. (2019). VOCA: Cell Nuclei Detection In Histopathology Images By Vector Oriented Confidence Accumulation. Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 102:527-539 Available from https://proceedings.mlr.press/v102/xie19a.html.

Related Material