PURE-MRI: An International Study Assessing Physician Accuracy in Delineating the Prostate and Urethra on Prostate MRI

PurposePrecise delineation of genitourinary structures during prostate cancer (PCa) care is critical to optimize treatment delivery while minimizing toxicity and injury. The Prostate and UREthra on MRI (PURE-MRI) study was an international, prospective study to assess physicians accuracy segmenting prostate and urethra on MRI. MethodsPhysicians who diagnose or treat PCa were invited to contour prostate and urethra on patient cases using standard T2-weighted MRI (all planes). We compared these contours to reference consensus segmentations produced by a multidisciplinary panel of experts. We also evaluated performance of a validated prostate auto- segmentation AI tool. Accuracy was assessed with spatial and volumetric analyses. Mixed effects model was used to evaluate potential factors influencing contour performance. Results62 specialists from 11 countries created 114 prostate and 110 urethra contours. Prostate median (min, max) Dice score was 0.92 (0.62, 0.95) for physicians. There was no clear effect of clinical experience or focus. Maximum deviation inside (under-segmentation), maximum deviation beyond expert contour, and mean deviation (per case) from the reference prostate were 3.4 mm (1.0, 12.4), 5.3 mm (2.4, 17.3), and 1.6 mm (0.9, 3.9), respectively. In comparison, prostate auto-segmentation tool results were 0.95 (0.94, 0.96), 3.0 mm, 3.9 mm (3.1, 4.9), and 1.2 mm (1.1, 1.6), respectively. Physician performance was considerably worse for urethra, with Dice score of 0.33 (0.03, 0.69). No urethra AI tool was tested. ConclusionPhysicians contour the prostate on MRI with overall Dice score >0.9, though contours typically had errors >5 mm and sometimes >10 mm. These patterns were observed regardless of clinical experience, specialty, or clinical focus. AI tool performs well enough for clinical use, given comparable accuracy to practicing physicians. In contrast, urethra segmentation on MRI is challenging. More training, better imaging, and/or AI tools may be necessary to achieve consistent, accurate results for the urethra.