Improving Multi-class Classification for Endomicroscopic Images by Semi-supervised Learning

• Type of Material: Article
• Authors: Hang Wu, Georgia Institute of Technology; Li Tong, Georgia Institute of Technology; Dongmei Wang, Emory University
• Language: English
• Date: 2017-01-01
• Publisher: IEEE
• Publication Version: Author Accepted Manuscript (After Peer Review)
• Copyright Statement: © Copyright 2017 IEEE - All rights reserved.
• Final Published Version (URL): http://dx.doi.org/10.1109/BHI.2017.7897191
• Title of Journal or Parent Work: 2017 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI)
• Volume: 2017
• Start Page: 5
• End Page: 8
• Grant/Funding Information: None declared
• Keywords: Medical Informatics; Life Sciences & Biomedicine; Science & Technology
• Research Categories: Biology, Microbiology; Biology, Bioinformatics; Engineering, Biomedical

Abstract

Optical Endomicroscopy (OE) is a newly-emerged biomedical imaging modality that can help physicians make real-time clinical decisions about patients' grade of dysplasia. However, the performance of applying medical imaging classification for computer-aided diagnosis is primarily limited by the lack of labeled images. To improve the classification performance, we propose a semi-supervised learning algorithm that can incorporate large sets of unlabeled images. Our real-world endo-microscopic imaging datasets consist of 425 labeled images and 2,826 unlabeled ones. With semi-supervised learning algorithms, we improved multi-class classification performance over supervised learning algorithms by around 10% in all evaluation metrics, namely precision, recall, F1 score and Cohen-Kappa statistics.