A real-time feature-based markerless tumor tracking method using X-ray image sequence for radiotherapy

In this paper, we present a real-time markerless tumor tracking method for radiotherapy treatment. The proposed method is a feature-based tracking method using X-ray image sequence. In the proposed method, feature points of a tracking target are firstly detected by using the scale-invariant feature transform (SIFT) technique. Then, the feature points are tracked by an optical flow. The proposed method was tested by using clinical X-ray image sequences in comparison with two conventional tracking methods. The tracking error of the proposed method was 0.74±1.18 mm and the computational speed is about 20 frames/s. This result suggests that the proposed method is potential for real-time tumor tracking.