Novel dosimetric validation of a commercial CT scanner based deep learning automated contour solution for prostate radiotherapy.

PURPOSE: OAR delineation accuracy influences: (i) a patient's optimised dose distribution (PD), (ii) the reported doses (RD) presented at approval, which represent plan quality. This study utilised a novel dosimetric validation methodology, comprehensively evaluating a new CT-scanner-based AI contouring solution in terms of PD and RD within an automated planning workflow. METHODS: 20 prostate patients were selected to evaluate AI contouring for rectum, bladder, and proximal femurs. Five planning 'pipelines' were considered; three using AI contours with differing levels of manual editing (nominally none (AIStd), minor editing in specific regions (AIMinEd), and fully corrected (AIFullEd)). Remaining pipelines were manual delineations from two observers (MDOb1, MDOb2). Automated radiotherapy plans were generated for each pipeline. Geometric and dosimetric agreement of contour sets AIStd, AIMinEd, AIFullEd and MDOb2 were evaluated against the reference set MDOb1. Non-inferiority of AI pipelines was assessed, hypothesising that compared to MDOb1, absolute deviations in metrics for AI contouring were no greater than that from MDOb2. RESULTS: Compared to MDOb1, organ delineation time was reduced by 24.9 min (96 %), 21.4 min (79 %) and 12.2 min (45 %) for AIStd, AIMinEd and AIFullEd respectively. All pipelines exhibited generally good dosimetric agreement with MDOb1. For RD, median deviations were within ± 1.8 cm3, ± 1.7 % and ± 0.6 Gy for absolute volume, relative volume and mean dose metrics respectively. For PD, respective values were within ± 0.4 cm3, ± 0.5 % and ± 0.2 Gy. Statistically (p < 0.05), AIMinEd and AIFullEd were dosimetrically non-inferior to MDOb2. CONCLUSIONS: This novel dosimetric validation demonstrated that following targeted minor editing (AIMinEd), AI contours were dosimetrically non-inferior to manual delineations, reducing delineation time by 79 %.

Evaluating the application of Pareto navigation guided automated radiotherapy treatment planning to prostate cancer.

BACKGROUND AND PURPOSE: Current automated planning methods do not allow for the intuitive exploration of clinical trade-offs during calibration. Recently a novel automated planning solution, which is calibrated using Pareto navigation principles, has been developed to address this issue. The purpose of this work was to clinically validate the solution for prostate cancer patients with and without elective nodal irradiation. MATERIALS AND METHODS: For 40 randomly selected patients (20 prostate and seminal vesicles (PSV) and 20 prostate and pelvic nodes (PPN)) automatically generated volumetric modulated arc therapy plans (VMATAuto) were compared against plans created by expert dosimetrists under clinical conditions (VMATClinical) and no time pressures (VMATIdeal). Plans were compared through quantitative comparison of dosimetric parameters and blind review by an oncologist. RESULTS: Upon blind review 39/40 and 33/40 VMATAuto plans were considered preferable or equal to VMATClinical and VMATIdeal respectively, with all deemed clinically acceptable. Dosimetrically, VMATAuto, VMATClinical and VMATIdeal were similar, with observed differences generally of low clinical significance. Compared to VMATClinical, VMATAuto reduced hands-on planning time by 94% and 79% for PSV and PPN respectively. Total planning time was significantly reduced from 22.2 mins to 14.0 mins for PSV, with no significant reduction observed for PPN. CONCLUSIONS: A novel automated planning solution has been evaluated, whose Pareto navigation based calibration enabled clinical decision-making on trade-off balancing to be intuitively incorporated into automated protocols. It was successfully applied to two sites of differing complexity and robustly generated high quality plans in an efficient manner.