Location of acupuncture points based on graph convolution and 3D deep learning in virtual humans

Abstract

Automatic acupoint searching is an indispensable part of intelligent acupuncture robot. Clinical practice have proofed that Dazhu, Fengmen and Xinshu, which could be located by Dazhui, are curative when these points are acupuncture. The existing methods are mainly based on regular or image. The regular‐based methods are based on the experience of physicians, and the accuracy will decrease for different patients; While the image‐based methods will lose some features in image. In order to solve the existing problems, we propose a novel graph convolution mixed with point cloud deep learning method. In this method, the skinned multi‐person linear model is regarded as a graph structure input, and the coarsened graph is obtained by graph convolution. After feeding the coarsened graph into the PointNet network, the coordinates of Dazhui are output. Different from the existing methods, the proposed method can directly label the results on the adaptive model, thus improving the accuracy on different models. An optimization method based on graph structure is introduced for better fit the predicted acupoints to the surface. In addition, a dataset marked with Dazhui is constructed for training. Experiments show that the accuracy of positioning could meet the requirements of needle application under certain circumstances.