Cross-task extreme learning machine for breast cancer image classification with deep convolutional features. (March 2020)

• Record Type: Journal Article
• Authors: Wang, Pin; Song, Qi; Li, Yongming; Lv, Shanshan; Wang, Jiaxin; Li, Linyu; Zhang, HeHua
• Is Part Of: Biomedical signal processing and control. Volume 57(2020)
• Publication Date: 2020-03
• Subjects: Breast cancer histopathology images -- Uninvolved images -- Convolutional neural networks -- Double deep transfer learning -- Interactive cross-task extreme learning machine; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2019.101789
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: A new hybrid structure including a double-deep transfer learning and interactive cross-task extreme learning machine is proposed. CNN models with transfer learning and double-step transfer learning are designed for feature extraction of breast cancer cell images. Interactive cross-task ELM is designed to improve the classification accuracy based on the designed loss functions. Abstract: Automatic classification of breast histopathology images plays a key role in computer-aided breast cancer diagnosis. However, feature-based classification methods rely on the accurate cell segmentation and feature extraction. Due to overlapping cells, dust, impurities and uneven irradiation the accurate segmentation and efficient feature extraction are still challenging. In order to overcome the above difficulties and limited breast histopathology images, in this paper, a hybrid structure which includes a double deep transfer learning (D 2 TL) and interactive cross-task extreme learning machine (ICELM) is proposed based on feature extraction and representation ability of CNN and classification robustness of ELM. First, high level features are extracted using deep transfer learning and double-step deep transfer learning. Then, the high level feature sets are jointly used as regularization terms to further improve classification performance in interactive cross task extreme learning machine. The proposed method was tested on 134 breast cancer histopathology images. Results show that our method has achieved remarkable performance in classification accuracy (96.67%, 96.96%, 98.18%). From the experiment result, the proposed method is promising for providing an efficient tool for breast cancer classification in clinical settings.