Imaging sebaceous gland using optical coherence tomography with deep learning assisted automatic identification. Issue 6 (24th March 2021)

• Record Type: Journal Article
• Authors: Luo, Yuemei; Wang, Xianghong; Yu, Xiaojun; Jin, Ruibing; Liu, Linbo
• Is Part Of: Journal of biophotonics. Volume 14:Issue 6(2021)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2021-03-24
• Subjects: computer‐aided diagnosis -- deep learning -- optical coherence tomography -- optical imaging -- sebaceous glands; Photonics -- Periodicals; Optical materials -- Periodicals; Optics -- Periodicals; Medical instruments and apparatus -- Periodicals; 621.3605
• DOI: 10.1002/jbio.202100015
• Languages: English
• ISSNs: 1864-063X

Abstract

Abstract: Imaging sebaceous glands and evaluating morphometric parameters are important for diagnosis and treatment of serum problems. In this article, we investigate the feasibility of high‐resolution optical coherence tomography (OCT) in combination with deep learning assisted automatic identification for these purposes. Specifically, with a spatial resolution of 2.3 μm × 6.2 μm (axial × lateral, in air), OCT is capable of clearly differentiating sebaceous gland from other skin structures and resolving the sebocyte layer. In order to achieve efficient and timely imaging analysis, a deep learning approach built upon ResNet18 is developed to automatically classify OCT images (with/without sebaceous gland), with a classification accuracy of 97.9%. Based on the result of automatic identification, we further demonstrate the possibility to measure gland size, sebocyte layer thickness and gland density. Abstract : We investigate the feasibility of high‐resolution optical coherence tomography (OCT) in combination with deep learning assisted identification for the purposes of imaging sebaceous glands and evaluating morphometric parameters. Specifically, high‐resolution OCT can clearly differentiate sebaceous gland from other skin structures and resolve the sebocyte layer. The proposed deep learning approach built upon ResNet18 is able to automatically classify OCT images (with/without sebaceous gland) with a classification accuracy of 97.9%.