Abstract
Abstract
Background
Glaucoma is one of the major causes of blindness; it is estimated that over 110 million people will be affected by glaucoma worldwide by 2040. Research on glaucoma detection using deep learning technology has been increasing, but the diagnosis of glaucoma in a large population with high incidence of myopia remains a challenge. This study aimed to provide a decision support system for the automatic detection of glaucoma using fundus images, which can be applied for general screening, especially in areas of high incidence of myopia.
Methods
A total of 1,155 fundus images were acquired from 667 individuals with a mean axial length of 25.60 ± 2.0 mm at the National Taiwan University Hospital, Hsinchu Br. These images were graded based on the findings of complete ophthalmology examinations, visual field test, and optical coherence tomography into three groups: normal (N, n = 596), pre-perimetric glaucoma (PPG, n = 66), and glaucoma (G, n = 493), and divided into a training-validation (N: 476, PPG: 55, G: 373) and test (N: 120, PPG: 11, G: 120) sets. A multimodal model with the Xception model as image feature extraction and machine learning algorithms [random forest (RF), support vector machine (SVM), dense neural network (DNN), and others] was applied.
Results
The Xception model classified the N, PPG, and G groups with 93.9% of the micro-average area under the receiver operating characteristic curve (AUROC) with tenfold cross-validation. Although normal and glaucoma sensitivity can reach 93.51% and 86.13% respectively, the PPG sensitivity was only 30.27%. The AUROC increased to 96.4% in the N + PPG and G groups. The multimodal model with the N + PPG and G groups showed that the AUROCs of RF, SVM, and DNN were 99.56%, 99.59%, and 99.10%, respectively; The N and PPG + G groups had less than 1% difference. The test set showed an overall 3%–5% less AUROC than the validation results.
Conclusion
The multimodal model had good AUROC while detecting glaucoma in a population with high incidence of myopia. The model shows the potential for general automatic screening and telemedicine, especially in Asia.
Trial registration: The study was approved by the Institutional Review Board of the National Taiwan University Hospital, Hsinchu Branch (no. NTUHHCB 108-025-E).
Funder
Ministry of Science and Technology, Taiwan
Publisher
Springer Science and Business Media LLC
Subject
Radiology, Nuclear Medicine and imaging
Reference47 articles.
1. Chua J, Baskaran M, Ong PG, Zheng Y, Wong TY, Aung T, et al. Prevalence, risk factors, and visual features of undiagnosed glaucoma: the Singapore Epidemiology of Eye Diseases Study. JAMA ophthalmology. 2015;133(8):938–46.
2. Prum BE, Rosenberg LF, Gedde SJ, Mansberger SL, Stein JD, Moroi SE, et al. Primary open-angle glaucoma preferred practice pattern® guidelines. Ophthalmology. 2016;123(1):P41–111.
3. Wintergerst MW, Jansen LG, Holz FG, Finger RP. A novel device for smartphone-based fundus imaging and documentation in clinical practice: comparative image analysis study. JMIR Mhealth Uhealth. 2020;8(7):e17480.
4. Jampel HD, Friedman D, Quigley H, Vitale S, Miller R, Knezevich F, et al. Agreement among glaucoma specialists in assessing progressive disc changes from photographs in open-angle glaucoma patients. Am J Ophthalmol. 2009;147(1):39–44. e1.
5. Gaasterland DE, Blackwell B, Dally LG, Caprioli J, Katz LJ, Ederer F, et al. The Advanced Glaucoma Intervention Study (AGIS): 10. Variability among academic glaucoma subspecialists in assessing optic disc notching. Trans Am Ophthalmol Soc. 2001;99:177.
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献