3DCNN-Based Palpation Localization with Temporal Attention Module

Palpation is necessary in Traditional Chinese Medicine (TCM). In TCM, doctors need to touch patient’s wrist and exert pressure on it to obtain physiological signal. Locating the pulse position is an important step in palpation. Nowadays, researchers have proposed numerous methods to locate the pulse position accurately. In this paper, we propose an accurate and effective framework to locate the pulse position. Our framework is based on 3-dimensional convolutional neural network (3DCNN), and we propose a novel temporal attention module to further improve the performance. Our framework achieves superior results, the accuracy of locating the pulse position on a video with a resolution of 2048 × 1088 within 100 pixels is 97%. More and more cross-domain applications of computer science and medical science provides more ways for doctors to treat patients, such as telemedicine, computed tomography image analysis, and physiological signal analysis. Our research presents the great potential to be applied to palpation automation and intelligent medical treatment.