TY - JOUR AU - Zhang, Kevin Sun AU - Schelb, Patrick AU - Netzer, Nils AU - Tavakoli, Anoshirwan Andrej AU - Keymling, Myriam AU - Wehrse, Eckhard AU - Hog, Robert AU - Rotkopf, Lukas Thomas AU - Wennmann, Markus AU - Glemser, Philip Alexander AU - Thierjung, Heidi AU - von Knebel Doeberitz, Nikolaus AU - Kleesiek, Jens AU - Görtz, Magdalena AU - Schütz, Viktoria AU - Hielscher, Thomas AU - Stenzinger, Albrecht AU - Hohenfellner, Markus AU - Schlemmer, Heinz-Peter AU - Maier-Hein, Klaus AU - Bonekamp, David TI - Pseudoprospective Paraclinical Interaction of Radiology Residents With a Deep Learning System for Prostate Cancer Detection: Experience, Performance, and Identification of the Need for Intermittent Recalibration. JO - Investigative radiology VL - 57 IS - 9 SN - 0020-9996 CY - [s.l.] PB - Ovid M1 - DKFZ-2022-00831 SP - 601-612 PY - 2022 N1 - #EA:E010#LA:E010# / 2022 Sep 1;57(9):601-612 AB - The aim of this study was to estimate the prospective utility of a previously retrospectively validated convolutional neural network (CNN) for prostate cancer (PC) detection on prostate magnetic resonance imaging (MRI).The biparametric (T2-weighted and diffusion-weighted) portion of clinical multiparametric prostate MRI from consecutive men included between November 2019 and September 2020 was fully automatically and individually analyzed by a CNN briefly after image acquisition (pseudoprospective design). Radiology residents performed 2 research Prostate Imaging Reporting and Data System (PI-RADS) assessments of the multiparametric dataset independent from clinical reporting (paraclinical design) before and after review of the CNN results and completed a survey. Presence of clinically significant PC was determined by the presence of an International Society of Urological Pathology grade 2 or higher PC on combined targeted and extended systematic transperineal MRI/transrectal ultrasound fusion biopsy. Sensitivities and specificities on a patient and prostate sextant basis were compared using the McNemar test and compared with the receiver operating characteristic (ROC) curve of CNN. Survey results were summarized as absolute counts and percentages.A total of 201 men were included. The CNN achieved an ROC area under the curve of 0.77 on a patient basis. Using PI-RADS ≥3-emulating probability threshold (c3), CNN had a patient-based sensitivity of 81.8 LB - PUB:(DE-HGF)16 C6 - pmid:35467572 DO - DOI:10.1097/RLI.0000000000000878 UR - https://inrepo02.dkfz.de/record/179659 ER -