DeepMitosis: Mitosis Detection via Deep Detection, Verication and Segmentation Networks

Publication date: Available online 31 January 2018
Source:Medical Image Analysis
Author(s): Chao Li, Xinggang Wang, Wenyu Liu, Longin Jan Latecki
Mitotic count is a critical predictor of tumor aggressiveness in the breast cancer diagnosis. Nowadays mitosis counting is mainly performed by patholo-gists manually, which is extremely arduous and time-consuming. In this paper, we propose an accurate method for detecting the mitotic cells from histopatho-logical slides using a novel multi-stage deep learning framework. Our method consists of a deep segmentation network for generating mitosis region when on-ly a weak label is given (i.e., only the centroid pixel of mitosis is annotated), an elaborately designed deep detection network for localizing mitosis by using contextual region information, and a deep veri cation network for improving detection accuracy by removing false positives. We validate the proposed deep learning method on two widely used Mitosis Detection in Breast Cancer His-tological Images (MITOSIS) datasets. Experimental results show that we can achieve the highest F-score on the MITOSIS dataset from ICPR 2012 grand challenge merely using the deep detection network. For the ICPR 2014 MI-TOSIS dataset that only provides the centroid location of mitosis, we employ the segmentation model to estimate the bounding box annotation for training the deep detection network. We also apply the veri cation model to eliminate some false positives produced from the detection model. By fusing scores of the detection and veri cation models, we achieve the state-of-the-art results. More-over, our method is very fast with GPU computing, which makes it feasible for clinical practice.



http://ift.tt/2EuLryo