Estimate changes in body fluids from facial images using AI processing

Abstract

This study presents a method to estimate the degree of edema from facial images taken before and after dialysis of renal failure patients. As tasks to estimate the degree of edema, we perform pre- and post-dialysis classification and body weight prediction. We introduce a multi- patient pre-training framework for acquiring knowledge of edema, and transfer the pre-training model into a model for each patient. For effective pre-training, we propose a novel contrastive representation learning, weight-aware su- pervised momentum contrast (WeightSupMoCo). Weight- SupMoCo aims to make feature representations of facial images closer according to the similarity of patient weight when pre- and post-dialysis label is the same. Experiment results show that our pre-training approach improves the accuracy of pre- and post-dialysis classification by 15% and the mean absolute error of weight prediction by 0.24 kg compared to the training from scratch. The proposed method realizes accurate estimation of the degree of edema from facial images, and our edema estimation system could be beneficial to dialysis patients.