Abstract Book

S99

ESTRO 37

2 VU University Medical Center, Department of Radiation Oncology Medical Physics, Amsterdam, The Netherlands Purpose or Objective Verification of intra-fractional tumor position during gated delivery is of utmost importance. We integrated gated breath-hold delivery under MRI guidance with only 3 mm margins using video-feedback to patients, and report on the accuracy of the real-time gated delivery system and reproducibility of tumor position. Material and Methods MR-guided gated breath-hold SBRT delivery in combination with visual feedback was implemented with the MRIdian system (Viewray Inc, Mountain View, USA). During treatment delivery, real-time tumor tracking is realized through repeated fast planar MR imaging in a single sagittal plane at 4 frames-per-second with 3.5mm x 3.5mm in-plane resolution via deformable image registration. An in-room MR-compatible monitor allows projection of this sagittal image with visualization of both the tracked GTV contour and gating boundary, which is the PTV (GTV+3mm). For each delivery, a threshold ROI% is set which determines the maximum allowed percentage of the GTV-area that can be outside the gating window before triggering a beam-hold. Accuracy of the real-time gated delivery and reproducibility of tumor position during repeated breath- holds was analyzed for 15 patients with five lung-, adrenal- and pancreas tumors each for a total of 87 fractions, resulting in a cumulative 33.4 hours of MR-cine. For image analysis, bi-cubic interpolation was applied to all acquired frames resulting in images with 0.8mmx0.8mm resolution. For each fraction we analyzed: [1] reproducibility of the GTV-centroid (GTV-COM) position within the PTV; [2] the geometric coverage of the GTV-area within the PTV; [3] treatment duty cycle efficiency; [4] effects of threshold ROI%-settings on treatment duty cycle efficiency and GTV-area coverage. Results Figure 1 shows a single 2D planar tracking image for a lung patient with observed GTV-COM positions, relative to the PTV-COM during beam-on. Grouped results showed 5 th –95 th percentile distributions of GTV-COM positions, relative to PTV-COM, in AP [ventral-dorsal] direction of [- 3.3mm,+2.8mm], [-2.5mm,+3.7mm] and [- 4.4mm,+2.9mm] for lung-, adrenal- and pancreas tumors, respectively. The corresponding distributions in CC [caudal-cranial] direction were [-2.6mm,+4.6mm], [- 4.1mm,+4.4mm] and [-4.4mm,+4.5mm], respectively. However, the mean GTV-areas that were encompassed by the PTV during beam-on across all fractions were 94.6%, 94.3% and 95.3% for lung-, adrenal- and pancreas tumors. The mean treatment duty cycle efficiency ranged from 67% to 87% for tumor sites. Selecting a higher threshold ROI% resulted in increased duty cycle efficiency, at the cost of a slight decrease in GTV area coverage.

Conclusion Gated delivery during repeated breath-holds under real- time MR-guidance with video-feedback to patients resulted in approximately 95% geometric coverage of the GTV by the PTV. High duty-cycle efficiencies were realized using this approach. OC-0186 Real-time long-term multi-object tracking on cineMR using a tracking-learning-detection framework J. Dhont 1 , D. Cusumano 2 , L. Boldrini 3 , G. Chiloiro 3 , L. Azario 2 , F. Cellini 3 , M. De Spirito 2 , L. Omelina 4 , J. Vandemeulebroucke 4 , D. Verellen 5 , V. Valentini 3 1 Universitair Ziekenhuis Brussel, Radiotherapy Medical Physics, Brussels, Belgium 2 Fondazione Policlinico Universitario A.Gemelli, UOC Fisica Sanitaria, Rome, Italy 3 Fondazione Policlinico Universitario A.Gemelli, Radioterapia Oncologica- Gemelli-ART, Rome, Italy 4 Vrije Universiteit Brussel, VUB-Department of Electronics and Informatics ETRO, Brussels, Belgium 5 GZA Ziekenhuizen - Iridium Kankernetwerk, Radiotherapy Medical Physics, Antwerp, Belgium Purpose or Objective Cine-MR imaging during radiotherapy allows accurate target monitoring. However, current tumor tracking algorithms suffer from drift and fail if the target dis- and re-appears. Furthermore, multi-object (MO) tracking is currently not clinically available. MO tracking would allow gating based on target-in-field but also OAR-not-in- field. This study adapts, applies and evaluates a tracking- learning-detection (TLD) framework which allows real- time and long-term MO tracking in cine-MR. It allows dis- and re-appearance of objects that move perpendicular to the 2D MR slice. The TLD framework was proposed elsewhere [1], but to the knowledge of the authors the application has been limited to non-medical images such as high frame-rate action videos. Material and Methods The TLD framework consists of three building blocks; a tracker, detection algorithm and a learning framework allowing the detection algorithm to learn in real-time, not requiring off-line pretreatment learning. The tracking algorithm applied in this study is based on median flow. The object detector uses a scanning-window grid and cascaded classifier. Each patch is re-sampled to a normalized resolution (25x25 pixels). The cascaded classifier consists of patch variance analysis, followed by an ensemble classifier performing independent pixel comparisons and finally a nearest neighbor classifier. The detection algorithm is trained based on the first cine-MR frame on which the objects to be tracked are indicated by the user. On each of the following frames, both the tracker and the object detector individually locate the objects. Exploiting the fact that the objects follow a smooth trajectory with limited frame-to-frame motion, and that the objects can only be in one location, detector errors (false positives and - negatives) can be estimated. The labels of wrong detections are corrected and fed back to the detector to train, improving its accuracy. The final object location is determined based on the most confident result from either tracker or detector. If neither give a location, the object is not visible. The TLD framework was evaluated based on the center- of-mass of 10 objects in sagittal 2D cine-MR (0.35 T, 4 Hz, 3 x 3 mm) from 5 patients treated on Viewray MRIdian, see Fig 1. The objects ranged from unique and stable in appearance (obj. 1,3,6,8) to highly deforming (obj. 4,7,9,10), or were very similar to other objects in the image (obj. 2,5,9). Ground-truth was established through contouring by an expert. Intra-observer variability was evaluated by contouring twice on different days.