CHS-NET: A Cascaded Neural Network with Semi-Focal Loss for Mitosis Detection

Yanbo Ma, Jiarui Sun, Qiuhao Zhou, Kaili Cheng, Xuesong Chen, Yong Zhao
Proceedings of The 10th Asian Conference on Machine Learning, PMLR 95:161-175, 2018.

Abstract

Counting of mitotic figures in hematoxylin and eosin(H&E) stained histological slide is the main indicator of tumor proliferation speed which is an important biomarker indicative of breast cancer patients’ prognosis. It is difficult to detect mitotic cells due to the diversity of the cells and the problem of class imbalance. We propose a new network called CHS-NET which is a cascaded neural network with hard example mining and semi-focal loss to detect mitotic cells in breast cancer. First, we propose a screening network to identify the candidates of mitotic cells preliminary and a refined network to identify mitotic cells from these candidates more accurately. We propose a new feature fusion module in each network to explore complex nonlinear predictors and improve accuracy. Then, we propose a novel loss named semi-focal loss and we use off-line hard example mining to solve the problem of class imbalance and error labeling. Finally, we propose a new training skill of cutting patches in the whole slide image, considering the size and distribution of mitotic cells. Our method achieves 0.68 F1 score which outperforms the best result in Tumor Proliferation Assessment Challenge 2016 held by MICCAI.

Cite this Paper

BibTeX
@InProceedings{pmlr-v95-ma18a, title = {CHS-NET: A Cascaded Neural Network with Semi-Focal Loss for Mitosis Detection}, author = {Ma, Yanbo and Sun, Jiarui and Zhou, Qiuhao and Cheng, Kaili and Chen, Xuesong and Zhao, Yong}, booktitle = {Proceedings of The 10th Asian Conference on Machine Learning}, pages = {161--175}, year = {2018}, editor = {Zhu, Jun and Takeuchi, Ichiro}, volume = {95}, series = {Proceedings of Machine Learning Research}, month = {14--16 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v95/ma18a/ma18a.pdf}, url = {https://proceedings.mlr.press/v95/ma18a.html}, abstract = {Counting of mitotic figures in hematoxylin and eosin(H&E) stained histological slide is the main indicator of tumor proliferation speed which is an important biomarker indicative of breast cancer patients’ prognosis. It is difficult to detect mitotic cells due to the diversity of the cells and the problem of class imbalance. We propose a new network called CHS-NET which is a cascaded neural network with hard example mining and semi-focal loss to detect mitotic cells in breast cancer. First, we propose a screening network to identify the candidates of mitotic cells preliminary and a refined network to identify mitotic cells from these candidates more accurately. We propose a new feature fusion module in each network to explore complex nonlinear predictors and improve accuracy. Then, we propose a novel loss named semi-focal loss and we use off-line hard example mining to solve the problem of class imbalance and error labeling. Finally, we propose a new training skill of cutting patches in the whole slide image, considering the size and distribution of mitotic cells. Our method achieves 0.68 F1 score which outperforms the best result in Tumor Proliferation Assessment Challenge 2016 held by MICCAI.} }
Endnote
%0 Conference Paper %T CHS-NET: A Cascaded Neural Network with Semi-Focal Loss for Mitosis Detection %A Yanbo Ma %A Jiarui Sun %A Qiuhao Zhou %A Kaili Cheng %A Xuesong Chen %A Yong Zhao %B Proceedings of The 10th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2018 %E Jun Zhu %E Ichiro Takeuchi %F pmlr-v95-ma18a %I PMLR %P 161--175 %U https://proceedings.mlr.press/v95/ma18a.html %V 95 %X Counting of mitotic figures in hematoxylin and eosin(H&E) stained histological slide is the main indicator of tumor proliferation speed which is an important biomarker indicative of breast cancer patients’ prognosis. It is difficult to detect mitotic cells due to the diversity of the cells and the problem of class imbalance. We propose a new network called CHS-NET which is a cascaded neural network with hard example mining and semi-focal loss to detect mitotic cells in breast cancer. First, we propose a screening network to identify the candidates of mitotic cells preliminary and a refined network to identify mitotic cells from these candidates more accurately. We propose a new feature fusion module in each network to explore complex nonlinear predictors and improve accuracy. Then, we propose a novel loss named semi-focal loss and we use off-line hard example mining to solve the problem of class imbalance and error labeling. Finally, we propose a new training skill of cutting patches in the whole slide image, considering the size and distribution of mitotic cells. Our method achieves 0.68 F1 score which outperforms the best result in Tumor Proliferation Assessment Challenge 2016 held by MICCAI.
APA
Ma, Y., Sun, J., Zhou, Q., Cheng, K., Chen, X. & Zhao, Y.. (2018). CHS-NET: A Cascaded Neural Network with Semi-Focal Loss for Mitosis Detection. Proceedings of The 10th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 95:161-175 Available from https://proceedings.mlr.press/v95/ma18a.html.

Related Material