期刊
MICROSCOPY
卷 68, 期 3, 页码 216-233出版社
OXFORD UNIV PRESS
DOI: 10.1093/jmicro/dfz002
关键词
breast cancer; mitosis count; convolutional neural networks; transfer learning; nuclei segmentation
类别
资金
- Higher Education Commission of Pakistan [213-53737-2PS2-038]
- Basic Science Research Program through the National Research Foundation of Korea (NRF) - Ministry of Education [2017R1A2B2005065]
- National Research Foundation of Korea [2017R1A2B2005065] Funding Source: Korea Institute of Science & Technology Information (KISTI), National Science & Technology Information Service (NTIS)
A Transfer Learning based system is proposed for segmentation and detection of mitotic nuclei. To give the classifier a balanced dataset, first a pre-trained convolutional neural network (CNN) is modified for segmentation of the nuclei. Then another Hybrid-CNN (with Weights Transfer and custom layers) is used for classification of mitoses. Abstract Segmentation and detection of mitotic nuclei is a challenging task. To address this problem, a Transfer Learning based fast and accurate system is proposed. To give the classifier a balanced dataset, this work exploits the concept of Transfer Learning by first using a pre-trained convolutional neural network (CNN) for segmentation, and then another Hybrid-CNN (with Weights Transfer and custom layers) for classification of mitoses. First, mitotic nuclei are automatically annotated, based on the ground truth centroids. The segmentation module then segments mitotic nuclei and also produces some false positives. Finally, the detection module is trained on the patches from the segmentation module and performs the final detection. Fine-tuning based Transfer Learning reduced training time, provided good initial weights, and improved the detection rate with F-measure of 0.713 and 76% area under the precision-recall curve for the challenging task of mitosis detection.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据