Segmentation of Laser Marks of Diabetic Retinopathy in the Fundus Photographs Using Lightweight U-Net

• Published in: Journal of Diabetes Research Vol. 2021; pp. 8766517 - 10
• Main Authors: Jiang, Yukang, Pan, Jianying, Yuan, Ming, Shen, Yanhe, Zhu, Jin, Wang, Yishen, Li, Yewei, Zhang, Ke, Yu, Qingyun, Xie, Huirui, Li, Huiting, Wang, Xueqin, Luo, Yan
• Format: Journal Article
• Language: English
• Published: England Hindawi 2021; John Wiley & Sons, Inc; Hindawi Limited
• Subjects: Algorithms; Care and treatment; Cicatrix - pathology; Data mining; Datasets; Deep Learning; Diabetes; Diabetic retinopathy; Diabetic Retinopathy - pathology; Diabetic Retinopathy - surgery; Fundus Oculi; Hemorrhage; Humans; Image Processing, Computer-Assisted; Lasers; Light Coagulation; Machine learning; Medical personnel; Photography; Severity of Illness Index; China; Taiwan; United Kingdom > UK
• ISSN: 2314-6745; 2314-6753
• DOI: 10.1155/2021/8766517

Diabetic retinopathy (DR) is a prevalent vision-threatening disease worldwide. Laser marks are the scars left after panretinal photocoagulation, a treatment to prevent patients with severe DR from losing vision. In this study, we develop a deep learning algorithm based on the lightweight U-Net to segment laser marks from the color fundus photos, which could help indicate a stage or providing valuable auxiliary information for the care of DR patients. We prepared our training and testing data, manually annotated by trained and experienced graders from Image Reading Center, Zhongshan Ophthalmic Center, publicly available to fill the vacancy of public image datasets dedicated to the segmentation of laser marks. The lightweight U-Net, along with two postprocessing procedures, achieved an AUC of 0.9824, an optimal sensitivity of 94.16%, and an optimal specificity of 92.82% on the segmentation of laser marks in fundus photographs. With accurate segmentation and high numeric metrics, the lightweight U-Net method showed its reliable performance in automatically segmenting laser marks in fundus photographs, which could help the AI assist the diagnosis of DR in the severe stage.