Respiratory Motion Estimation of Tumor Using Point Clouds of Skin Surface

Traditional methods of respiration tracking used in radiosurgical robotics use external optical markers to estimate the tumor position, which requires extracting the respiratory motion characteristics of the chest and establishing correlation models manually. The estimation is easily affected by the placement and number of markers. To solve the above problem, an estimation method of tumor location during respiratory motion is proposed using point clouds of the chest and abdominal skin surface. Based on the correlations with the tumor's location, the essential area of the surface is selected as a dataset and processed. Then, a hierarchical network is built to extract the feature of the skin and map those features to the location of tumors. To improve the estimation accuracy, a correlation smooth strategy is used to avoid the miss correlations between the skin surface and tumor locations. Investigations are conducted to find the optimal combinations of primary factors. Five typical respiratory data are collected in the experiments. The results show that combining the essential area of the skin surface and the classification network leads to better performance. Further results also show that the error of the proposed method is smaller than that of the traditional optical marker estimation method. Using the proposed method, manually extracting features and establishing correlation models are unnecessary, and the estimation accuracy is increased.