AUTHOR=Hu Xiao-yan , Li Yu-jie , Shu Xin , Song Ai-lin , Liang Hao , Sun Yi-zhu , Wu Xian-feng , Li Yong-shuai , Tan Li-fang , Yang Zhi-yong , Yang Chun-yong , Xu Lin-quan , Chen Yu-wen , Yi Bin TITLE=A new, feasible, and convenient method based on semantic segmentation and deep learning for hemoglobin monitoring JOURNAL=Frontiers in Medicine VOLUME=Volume 10 - 2023 YEAR=2023 URL=https://www.frontiersin.org/journals/medicine/articles/10.3389/fmed.2023.1151996 DOI=10.3389/fmed.2023.1151996 ISSN=2296-858X ABSTRACT=Objective: Non-invasive methods for hemoglobin (Hb) monitoring can provide additional and relatively precise information between invasive measurements of Hb to help doctors' decisionmaking. We aimed to develop a new method for Hb monitoring based on mask R-CNN and MobileNetV3 with the eye images as input.Methods: Surgical patients from our center were enrolled. After image acquisition and preprocessing, the eye images, the manually selected palpebral conjunctiva, and features extracted respectively from the two mentioned kinds of images were as inputs. A combination of feature engineering and regression, solely MobileNetV3, and a combination of mask R-CNN and MobileNetV3 were applied for model development. The model performance was evaluated by R 2 , explained variance score (EVS), and mean absolute error (MAE).Results: A total of 1065 original images were analyzed. Model performance based on the combination of mask R-CNN and MobileNetV3 using the eye images achieved an R 2 , EVS and MAE of 0.503 (95% CI, 0.499-0.507), 0.518 (95% CI, 0.515-0.522) and 1.6 g/dL (95% CI,1.6-1.6 g/dL), which was similar to that based on MobileNetV3 using the manually selected palpebral conjunctiva images (R 2 : 0.509, EVS:0.516, MAE:1.6 g/dL).Conclusions: we developed a new and automatic method for Hb monitoring to help medical staffs' decision-making with high efficiency, especially in case of disaster rescue and casualty transport, etc.