DeepMitosis: Mitosis detection via deep detection, verification and segmentation networks
DeepMitosis: Mitosis detection via deep detection, verification and segmentation networks
复制标题
DeepMitosis：通过深度检测、验证和分割网络进行有丝分裂检测
DOI：
10.1016/j.media.2017.12.002
复制
发表时间：
2018-04-01
影响因子：
10.9
通讯作者：
Latecki, Longin Jan
中科院分区：
文献类型：
--
作者：
Li, Chao;Wang, Xinggang;Latecki, Longin Jan
有丝分裂计数是乳腺癌诊断中肿瘤侵袭性的重要预测因子。目前有丝分裂计数主要由病理学家手工进行，极其艰巨且耗时。在本文中，我们提出了一种使用新的多阶段深度学习框架从组织病理学切片中检测有丝分裂细胞的准确方法。我们的方法由一个深度分割网络组成，用于在仅给出弱标签时生成有丝分裂区域（即，仅注释有丝分裂的质心像素）、用于通过使用上下文区域信息来定位有丝分裂的精心设计的深度检测网络、以及用于通过去除假阳性来提高检测准确性的深度验证网络。我们在两个广泛使用的乳腺癌组织学图像有丝分裂检测（MITOSIS）数据集上验证了所提出的深度学习方法。实验结果表明，仅使用深度检测网络，我们就可以在ICPR 2012大挑战的MITOSIS数据集上获得最高的F分数。对于仅提供有丝分裂质心位置的ICPR 2014 MITOSIS数据集，我们采用分割模型来估计用于训练深度检测网络的边界框注释。我们还应用验证模型，以消除一些误报产生的检测模型。通过融合数十个检测和验证模型，我们获得了最先进的结果。此外，我们的方法是非常快的GPU计算，这使得它可行的临床实践。(C)2018 Elsevier B.V.版权所有。
Mitotic count is a critical predictor of tumor aggressiveness in the breast cancer diagnosis. Nowadays mitosis counting is mainly performed by pathologists manually, which is extremely arduous and time-consuming. In this paper, we propose an accurate method for detecting the mitotic cells from histopathological slides using a novel multi-stage deep learning framework. Our method consists of a deep segmentation network for generating mitosis region when only 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 verification 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 Histological 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 MITOSIS 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 verification model to eliminate some false positives produced from the detection model. By fusing scores of the detection and verification models, we achieve the state-of-the-art results. Moreover, our method is very fast with GPU computing, which makes it feasible for clinical practice. (C) 2018 Elsevier B.V. All rights reserved.