A new, feasible, and convenient method based on semantic segmentation and deep learning for hemoglobin monitoring

OBJECTIVE: Non-invasive methods for hemoglobin (Hb) monitoring can provide additional and relatively precise information between invasive measurements of Hb to help doctors' decision-making. We aimed to develop a new method for Hb monitoring based on mask R-CNN and MobileNetV3 with eye images as input. METHODS: Surgical patients from our center were enrolled. After image acquisition and pre-processing, the eye images, the manually selected palpebral conjunctiva, and features extracted, respectively, from the two kinds of images were used 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's performance was evaluated using metrics such as R(2), explained variance score (EVS), and mean absolute error (MAE). RESULTS: A total of 1,065 original images were analyzed. The model's 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). CONCLUSION: We developed a new and automatic method for Hb monitoring to help medical staffs' decision-making with high efficiency, especially in cases of disaster rescue, casualty transport, and so on.