Search

To predict patients who would benefit from adaptive radiotherapy (ART) and re-planning intervention based on machine learning from anatomical and dosimetric variations in a retrospective dataset.90 patients (pts) treated for head-neck cancer (HN) formed a multicenter data-set. 41 HN pts (45.6%) were considered for learning; 49 pts (54.4%) were used to test the tool. A homemade machine-learning classifier was developed to analyze volume and dose variations of parotid glands (PG). Using deformable image registration (DIR) and GPU, patients' conditions were analyzed automatically. Support Vector Machines (SVM) was used for time-series evaluation. "Inadequate" class identified patients that might benefit from replanning. Double-blind evaluation by two radiation oncologists (ROs) was carried out to validate day/week selected for re-planning by the classifier.The cohort was affected by PG mean reduction of 23.7±8.8%. During the first 3weeks, 86.7% cases show PG deformation aligned with predefined tolerance, thus not requiring re-planning. From 4th week, an increased number of pts would potentially benefit from re-planning: a mean of 58% of cases, with an inter-center variability of 8.3%, showed "inadequate" conditions. 11% of cases showed "bias" due to DIR and script failure; 6% showed "warning" output due to potential positioning issues. Comparing re-planning suggested by tool with recommended by ROs, the 4th week seems the most favorable time in 70% cases.SVM and decision-making tool was applied to overcome ART challenges. Pts would benefit from ART and ideal time for re-planning intervention was identified in this retrospective analysis.

Purpose The ideal situation for radiotherapy would be a treatment under more or less static conditions in an ideal dosimetric situation with permanent control of the position of tumor, organs-at-risk (OAR) and patient surface. Methods This presentation will outline the current state of the art and explore, if/how/where in-room MR-guidance may go beyond current strategies and what requirements must be fulfilled on the way as layed out in a previous publication [1]. Results If there is a necessity for on line MR-guidance, there is a general necessity for broad use of advanced image guidance strategies, particularly as successful screening programs such as those for lung cancer and potentially even pancreatic cancer are established, as this potentially leads to more localized disease being treated. Several such strategies are now available but are underutilized, typically for lack of funding or perceived complexity. Online MR-image guidance has the ability to simultaneously image and target the cancer and is more intuitive when integrated into a single system and the high image quality of MRI-guidance may further facilitate the education of personnel and facilitate adaptive RT approaches. In addition, online MR-guidance systems may in the future better respond changing cancer physiology over the treatment, facilitate differential targeting of tumor, lymphatic tissue etc. and offer other added values not yet broadly established (e.g. targeting of atrial fibrillation) or completely identified. Conclusions There is no doubt that the use of advanced imaging on a broad scale is needed. It is a significant clinical problem that a large number of RT devices are still in clinical use without the capability for 3D-imaging and beam gating. As a next step, online MR-image guidance may offer a significant number of benefits over established approaches that may open new roads in radiotherapy.

Purpose To model and predict parotid gland (PG) deformation in HN red regions represent regions subjected to the highest displacement; distance value mm (right).

Purpose Automatic segmentations to contour region of interest (ROIs) in radiotherapy is becoming an impending necessity to reduce physicians’ workload and inter-user variability. The aims were: (I) Comparison of automatic segmentations between atlas-based-segmentation (ABS) and model-based-segmentation (MBS); (II) Evaluation of ABS performances with different inputs; (III) Implementation of a classifier to assess segmentations quality. Methods and materials 42 patients (37 training, 5 validation), previously contoured within left partial breast irradiation protocol, were used for atlas construction. We focused on lungs, spinal cord, heart, contralateral breast and thyroid. Automatic segmentations were evaluated by DiceSimilarityCoefficient (DSC) and Hausdorff distance (AHD) computed in RayStation® by IronPython® scripts. ABS were launched, varying the number of structures and training patients. The first method contoured all the structures in one session searching the best matching with one training patient. The second one contoured each structure finding a one-by-one matching. To test the algorithms, 13 new patients were used. Moreover, TrueNegative cases were generated from original ROIs with translations/expansions of 0.2 cm, 0.3 cm, 0.5 cm and 0.8 cm. The classifier was implemented in Matlab®. Results ABS gained results for heart, spinal cord and breast similar with clinical gold standard. ABS performed auto-segmentation better than MBS for lungs (DSC: 0.97–0.97; AHD: 0.09–0.06 for left and right). The thyroid segmentation was not satisfactory (DSC Conclusion ABS using the customized atlas perform better than the MBS. ABS segmentations had performances comparable with clinical gold standard except for small ROI. ABS reduce physician contouring workload up to 75%, with a time gain of 20–30 min for patient.