Deep learning for contour quality assurance for RTOG 0933: In-silico evaluation.

PURPOSE: To validate a CT-based deep learning (DL) hippocampal segmentation model trained on a single-institutional dataset and explore its utility for multi-institutional contour quality assurance (QA). METHODS: A DL model was trained to contour hippocampi from a dataset generated by an institutional observer (IO) contouring on brain MRIs from a single-institution cohort. The model was then evaluated on the RTOG 0933 dataset by comparing the treating physician (TP) contours to blinded IO and DL contours using Dice and Haussdorf distance (HD) agreement metrics as well as evaluating differences in dose to hippocampi when TP vs. IO vs. DL contours are used for planning. The specificity and sensitivity of the DL model to capture planning discrepancies was quantified using criteria of HD > 7 mm and Dmax hippocampi > 17 Gy. RESULTS: The DL model showed greater agreement with IO contours compared to TP contours (DL:IO L/R Dice 74 %/73 %, HD 4.86/4.74; DL:TP L/R Dice 62 %/65 %, HD 7.23/6.94, all p < 0.001). Thirty percent of contours and 53 % of dose plans failed QA. The DL model achieved an AUC L/R 0.80/0.79 on the contour QA task via Haussdorff comparison and AUC of 0.91 via Dmax comparison. The false negative rate was 17.2 %/20.5 % (contours) and 5.8 % (dose). False negative cases tended to demonstrate a higher DL:IO Dice agreement (L/R p = 0.42/0.03) and better qualitative visual agreement compared with true positive cases. CONCLUSION: Our study demonstrates the feasibility of using a single-institutional DL model to perform contour QA on a multi-institutional trial for the task of hippocampal segmentation.

High frequency percussive ventilation for respiratory immobilization in radiotherapy.

High frequency percussive ventilation (HFPV) employs high frequency low tidal volumes (100-400 bursts/min) to provide respiration in awake patients while simultaneously reducing respiratory motion. The purpose of this study is to evaluate HFPV as a technique for respiratory motion immobilization in radiotherapy. In this study fifteen healthy volunteers (age 30-75 y) underwent HFPV using three different oral interfaces. We evaluated each HFPV oral interface device for compliance, ease of use, comfort, geometric interference, minimal chest wall motion, duty cycle and prolonged percussive time. Their chest wall motion was monitored using an external respiratory motion laser system. The percussive ventilations were delivered via an air driven pneumatic system. All volunteers were monitored for PO2 and tc-CO2 with a pulse oximeter and CO2 Monitoring System. A total of N = 62 percussive sessions were analyzed from the external respiratory motion laser system. Chest-wall motion was well tolerated and drastically reduced using HFPV in each volunteer evaluated. As a result, we believe HFPV may provide thoracic immobilization during radiotherapy, particularly for SBRT and pencil beam scanning proton therapy.