A key-point based real-time tracking of lung tumor in x-ray image sequence by using difference of Gaussians filtering and optical flow.

In radiation therapy, for accurate radiation dose delivery to a target tumor and reduction of the extra exposure of normal tissues, real-time tumor tracking is typically an important technique in lung cancer treatment since lung tumors move with patients' respiration. To observe a tumor motion in real time, x-ray fluoroscopic devices can be employed, and various tracking techniques have been proposed to track tumors. However, development of a fast and accurate tracking method for clinical use is still a challenging task since the obscured image of the tumor can cause decreased tracking accuracy and can result in additional processing time for remedying the accuracy. In this study, a new key-point-based tumor tracking method, which is sufficiently fast and accurate, is presented. Given an x-ray image sequence, the proposed method employs a difference-of-Gaussians filtering technique to detect key points in the tumor region of the first frame which are robust against noise and outliers in the subsequent frames. In the subsequent frames, these key points are tracked using a fast optical flow technique, and tumor motion is estimated via their movement. To evaluate the performance, the proposed method has been tested on several clinical kV and MV x-ray image sequences. The experimental results showed that the average of the root mean square errors of tracking were [Formula: see text] and [Formula: see text] for kV and MV x-ray image sequences, respectively. This tracking performance was more accurate than previous tracking methods. In addition, the average processing times for each frame were [Formula: see text] and [Formula: see text] for kV and MV image sequences, respectively, and the proposed method was faster than previous methods as well as shorter than frame acquisition interval. Therefore, the proposed method has the potential for both highly accurate and fast tumor tracking in clinical applications.

SU-D-BRA-02: An Extended Time-Variant Seasonal Autoregressive Model-Based Prediction for Irregular Breathing Motion Tracking.

PURPOSE: Real-time tumor position/shape measurement and dynamic beam tracking techniques allow accurate and continuous irradiation to moving tumor, but there can be a delay of several hundred milliseconds between observation and irradiation. A time-variant seasonal autoregressive (TVSAR) model has been proposed for compensating the delay by predicting respiratory tumor motion with sub-millimeter accuracy for a second latency. This is the-state-of-the-art model for almost regular breathing prediction so far. In this study, we propose an extended prediction method based on TVSAR to be usable for various breathing patterns, by predicting the residual component obtained from conventional TVSAR. METHODS: An essential core of the method is to take into account the residual component that is not predictable by only TVSAR. The residual component involves baseline shift, amplitude variation, and so on. In this study, the time series of the residual obtained for every new sample are predicted by using autoregressive (AR) model. The order and parameters of the AR model is adaptively determined for each residual component by using an information criterion. Eleven data sets of 3-D lung tumor motion, observed at Georgetown University Hospital by using Cyberknife Synchrony system, were used for evaluation of the prediction performance. RESULTS: Experimental results indicated that the proposed method is superior to those of conventional and the state-of-the-art methods for 0 to 1 s ahead prediction. The average prediction error of the proposed method was 0.920 plus/minus 0.348 mm for 0.5 s forward prediction. CONCLUSION: We have developed the new prediction method based on TVSAR model with adaptive residual prediction. The new method can predict various respiratory motions including not only regular but also a variety of irregular breathing patterns and thus can compensate the bad effect of the delay in dynamic irradiation system for moving tumor tracking. A part of this work has been financially supported by Varian Medical Systems Inc., Palo Alto, CA and Japan Society for the Promotion of Science (JSPS), Japan.