期刊
BIOCYBERNETICS AND BIOMEDICAL ENGINEERING
卷 39, 期 1, 页码 214-223出版社
ELSEVIER
DOI: 10.1016/j.bbe.2018.10.007
关键词
Histopathology; Mitosis; Krill herd optimization; Convolutional Neural Network; Transfer learning; Random forest
资金
- RCC Thiruvananthapuram, India
The exact measure of mitotic count is one of the crucial parameters in breast cancer grading and prognosis. Detection of mitosis in standard H & E stained histopathology images is challenging due to diffused intensities along object boundaries and shape variation in different stages of mitosis. This paper explores the feasibility of transfer learning for mitosis detection. A pre-trained Convolutional Neural Network is transformed by coupling random forest classifier with the initial fully connected layers to extract discriminant features from nuclei patches and to precisely prognosticate the class label of cell nuclei. The modified Convolutional Neural Network accurately classify the detected cell nuclei with limited training data. The designed framework accomplishes higher classification accuracy by carefully fine tuning the pre-trained model and pre-processing the extracted features. Moreover, proposed method is evaluated on MITOS dataset provided for the MITOS-ATYPIA contest 2014 and clinical data set from Regional Cancer Centre, Thiruvananthapuram, India. Significance of Convolutional Neural Network based method is justified by comparing with recently reported works including a Multi Classifier System based on Deep Belief Network. Experiments show that the pre-trained Convolutional Neural Network model outperforms conventionally used detection systems and provides at least 15% improvement in F-score on other state-of-the-art techniques. (C) 2018 Published by Elsevier B.V. on behalf of Nalecz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences.
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