Xinyu Zhao1,2, Lihui Meng1,2, Hao Su3, Bin Lv3, Chuanfeng Lv3, Guotong Xie3,4,5, Youxin Chen1,2. 1. Department of Ophthalmology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences, Beijing, China. 2. Key Lab of Ocular Fundus Diseases, Chinese Academy of Medical Sciences, Beijing, China. 3. Ping An Healthcare Technology Company Limited, Shenzhen, China. 4. Ping An Health Cloud Company Limited, Shenzhen, China. 5. Ping An International Smart City Technology Company Limited, Shenzhen, China.
Abstract
Background: Anemia is the most common hematological disorder. The purpose of this study was to establish and validate a deep-learning model to predict Hgb concentrations and screen anemia using ultra-wide-field (UWF) fundus images. Methods: The study was conducted at Peking Union Medical College Hospital. Optos color images taken between January 2017 and June 2021 were screened for building the dataset. ASModel_UWF using UWF images was developed. Mean absolute error (MAE) and area under the receiver operating characteristics curve (AUC) were used to evaluate its performance. Saliency maps were generated to make the visual explanation of the model. Results: ASModel_UWF acquired the MAE of the prediction task of 0.83 g/dl (95%CI: 0.81-0.85 g/dl) and the AUC of the screening task of 0.93 (95%CI: 0.92-0.95). Compared with other screening approaches, it achieved the best performance of AUC and sensitivity when the test dataset size was larger than 1000. The model tended to focus on the area around the optic disc, retinal vessels, and some regions located at the peripheral area of the retina, which were undetected by non-UWF imaging. Conclusion: The deep-learning model ASModel_UWF could both predict Hgb concentration and screen anemia in a non-invasive and accurate way with high efficiency.
Background: Anemia is the most common hematological disorder. The purpose of this study was to establish and validate a deep-learning model to predict Hgb concentrations and screen anemia using ultra-wide-field (UWF) fundus images. Methods: The study was conducted at Peking Union Medical College Hospital. Optos color images taken between January 2017 and June 2021 were screened for building the dataset. ASModel_UWF using UWF images was developed. Mean absolute error (MAE) and area under the receiver operating characteristics curve (AUC) were used to evaluate its performance. Saliency maps were generated to make the visual explanation of the model. Results: ASModel_UWF acquired the MAE of the prediction task of 0.83 g/dl (95%CI: 0.81-0.85 g/dl) and the AUC of the screening task of 0.93 (95%CI: 0.92-0.95). Compared with other screening approaches, it achieved the best performance of AUC and sensitivity when the test dataset size was larger than 1000. The model tended to focus on the area around the optic disc, retinal vessels, and some regions located at the peripheral area of the retina, which were undetected by non-UWF imaging. Conclusion: The deep-learning model ASModel_UWF could both predict Hgb concentration and screen anemia in a non-invasive and accurate way with high efficiency.
Authors: J A Batsis; G G Boateng; L M Seo; C L Petersen; K L Fortuna; E V Wechsler; R J Peterson; S B Cook; D Pidgeon; R S Dokko; R J Halter; D F Kotz Journal: World Acad Sci Eng Technol Date: 2019
Authors: Ali Simsek; Mehmet Tekin; Abdurrahman Bilen; Ayse Sevgi Karadag; Ibrahim Hakan Bucak; Mehmet Turgut Journal: Invest Ophthalmol Vis Sci Date: 2016-11-01 Impact factor: 4.799