Identifying diabetes from conjunctival images using a novel hierarchical multi-task network

• Published in: Scientific reports Vol. 12; no. 1; p. 264
• Main Authors: Li, Xinyue, Xia, Chenjie, Li, Xin, Wei, Shuangqing, Zhou, Sujun, Yu, Xuhui, Gao, Jiayue, Cao, Yanpeng, Zhang, Hong
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 07.01.2022; Nature Publishing Group; Nature Portfolio
• Subjects: 639/166/987; 639/705/117; 692/163/2743/137/773; 692/1807/1482; 692/699/3161/3164; Algorithms; Case-Control Studies; Conjunctiva - blood supply; Deep learning; Diabetes; Diabetes mellitus (non-insulin dependent); Diabetes Mellitus, Type 2 - complications; Diabetes Mellitus, Type 2 - pathology; Diabetic Angiopathies - etiology; Diabetic Angiopathies - pathology; Diagnosis, Computer-Assisted; Diagnostic Techniques, Ophthalmological; Humanities and Social Sciences; Humans; Image Interpretation, Computer-Assisted; Microvessels - pathology; multidisciplinary; Predictive Value of Tests; Prospective Studies; Reproducibility of Results; Science; Science (multidisciplinary)
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-021-04006-z

Diabetes can cause microvessel impairment. However, these conjunctival pathological changes are not easily recognized, limiting their potential as independent diagnostic indicators. Therefore, we designed a deep learning model to explore the relationship between conjunctival features and diabetes, and to advance automated identification of diabetes through conjunctival images. Images were collected from patients with type 2 diabetes and healthy volunteers. A hierarchical multi-tasking network model (HMT-Net) was developed using conjunctival images, and the model was systematically evaluated and compared with other algorithms. The sensitivity, specificity, and accuracy of the HMT-Net model to identify diabetes were 78.70%, 69.08%, and 75.15%, respectively. The performance of the HMT-Net model was significantly better than that of ophthalmologists. The model allowed sensitive and rapid discrimination by assessment of conjunctival images and can be potentially useful for identifying diabetes.