A retrospective comparison of deep learning to manual annotations for optic disc and optic cup segmentation in fundus photographs

Fu，Huazhu2; Li，Fei1; Xu，Yanwu3; Liao，Jingan4; Xiong，Jian1; Shen，Jianbing2; Liu，Jiang5,6; Zhang，Xiulan1; Yang，Chunman7; Lin，Fengbin8; Luo，Huang9; Li，Hao8; Che，Huixin10; Li，Nuhui8; Fan，Yazhi11

2020

10.1167/tvst.9.2.33

Translational Vision Science & Technology   影响因子和分区

2164-2591

2164-2591

Purpose: Optic disc (OD) and optic cup (OC) segmentation are fundamental for fundus image analysis. Manual annotation is time consuming, expensive, and highly subjec-tive, whereas an automated system is invaluable to the medical community. The aim of this study is to develop a deep learning system to segment OD and OC in fundus photographs, and evaluate how the algorithm compares against manual annotations. Methods: A total of 1200 fundus photographs with 120 glaucoma cases were collected. The OD and OC annotations were labeled by seven licensed ophthalmologists, and glaucoma diagnoses were based on comprehensive evaluations of the subject medical records. A deep learning system for OD and OC segmentation was developed. The performances of segmentation and glaucoma discriminating based on the cup-to-disc ratio (CDR) of automated model were compared against the manual annotations. Results: The algorithm achieved an OD dice of 0.938 (95% confidence interval [CI] = 0.934–0.941), OC dice of 0.801 (95% CI = 0.793–0.809), and CDR mean absolute error (MAE) of 0.077 (95% CI = 0.073 mean absolute error (MAE)0.082). For glaucoma discriminating based on CDR calculations, the algorithm obtained an area under receiver operator characteristic curve (AUC) of 0.948 (95% CI = 0.920 mean absolute error (MAE)0.973), with a sensitivity of 0.850 (95% CI = 0.794–0.923) and specificity of 0.853 (95% CI = 0.798–0.918). Conclusions: We demonstrated the potential of the deep learning system to assist ophthalmologists in analyzing OD and OC segmentation and discriminating glaucoma from nonglaucoma subjects based on CDR calculations. Translational Relevance: We investigate the segmentation of OD and OC by deep learning system compared against the manual annotations.

Artificial intelligence Optic cup Optic disc Segmentation

SCI

英语

其他

2-s2.0-85089124973

Scopus

1.State Key Laboratory of Ophthalmology,Zhongshan Ophthalmic Center,Sun Yat-sen University,Guangzhou,China
2.Inception Institute of Artificial Intelligence,Abu Dhabi,United Arab Emirates
3.Intelligent Healthcare Unit,Beijing,Baidu,China
4.School of Computer Science and Engineering,South China University of Technology,Guangzhou,China
5.Department of Computer Science and Engineering,Southern University of Science and Technology,Guangzhou,China
6.Cixi Institute of Biomedical Engineering,Chinese Academy of Sciences,Ningbo,China
7.The 2nd Affiliated Hospital of Guizhou Medical University,Kaili,China
8.Zhongshan Ophthalmic Center,Guangzhou,China
9.Guangzhou Hospital of TCM,Guangzhou,China
10.Aier Eye Hospital,Jinzhou,China
11.The 2nd Affiliated Hospital of Xi’an Jiaotong University,China
12.

Fu，Huazhu,Li，Fei,Xu，Yanwu,et al. A retrospective comparison of deep learning to manual annotations for optic disc and optic cup segmentation in fundus photographs[J]. Translational Vision Science & Technology,2020,9(2):1-11.

Fu，Huazhu.,Li，Fei.,Xu，Yanwu.,Liao，Jingan.,Xiong，Jian.,...&Fan，Yazhi.(2020).A retrospective comparison of deep learning to manual annotations for optic disc and optic cup segmentation in fundus photographs.Translational Vision Science & Technology,9(2),1-11.

Fu，Huazhu,et al."A retrospective comparison of deep learning to manual annotations for optic disc and optic cup segmentation in fundus photographs".Translational Vision Science & Technology 9.2(2020):1-11.