AUTHOR=Zhao Xinyu , Meng Lihui , Su Hao , Lv Bin , Lv Chuanfeng , Xie Guotong , Chen Youxin 

TITLE=Deep-Learning-Based Hemoglobin Concentration Prediction and Anemia Screening Using Ultra-Wide Field Fundus Images

JOURNAL=Frontiers in Cell and Developmental Biology

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/cell-and-developmental-biology/articles/10.3389/fcell.2022.888268

DOI=10.3389/fcell.2022.888268

ISSN=2296-634X

ABSTRACT=Background Anaemia is the most common haematological disorder. The purpose of this study was to establish and validate a deep-learning model to predict Hgb concentrations and screen anaemia using ultra-wide-field (UWF) fundus images. 
Methods The study was conducted in 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 were 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 prediction task of 0.83 g/dl (95%CI: 0.81-0.85 g/dl) and the AUC of 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 anaemia in a non-invasive and accurate way with high efficiency.