An optimal approach to MRI fusion targeted prostate biopsy (PBx) remains unclear (number of cores, inter-core distance, Gleason grading (GG) principle). The aim of this study was to develop a precise pixel-wise segmentation diagnostic AI algorithm for tumor detection and GG as well as an algorithm for virtual prostate biopsy that are used together to systematically investigate and find an optimal approach to targeted PBx. Pixel-wise AI algorithms for tumor detection and GG were developed using a high-quality, manually annotated dataset (slides n=442) after fast-track annotation transfer into segmentation style. To this end, a virtual biopsy algorithm was developed that can perform random biopsies from tumor regions in whole-mount whole-slide images with pre-defined parameters. A cohort of 115 radical prostatectomy (RP) patient cases with clinically significant, MRI-visible tumors (n=121) was used for systematic studies of the optimal biopsy approach. Three expert genitourinary (GU) pathologists participated in the validation. The tumor detection algorithm (aware version sensitivity/specificity 0.99/0.90, balanced version 0.97/0.97) and GG algorithm (quadratic kappa range vs pathologists 0.77-0.78) perform on par with expert GU pathologists. In total, 65,340 virtual biopsies were performed to study different biopsy approaches with the following results: 1) four biopsy cores is the optimal number for a targeted PBx, 2) cumulative GG strategy is superior to using maximal Gleason score for single cores, 3) controlling for minimal inter-core distance does not improve the predictive accuracy for the RP Gleason score, 4) Using tertiary Gleason pattern principle (for AI tool) in cumulative GG strategy might allow better predictions of final RP Gleason score. The AI algorithm (based on cumulative GG strategy) predicted the RP Gleason score of the tumor better than 2 of the 3 expert GU pathologists. In this study, using an original approach of virtual prostate biopsy on the real cohort of patient cases, we find the optimal approach to the biopsy procedure and the subsequent Gleason grading of a targeted PBx. We publicly release two large datasets with associated expert pathologists' GG and our virtual biopsy algorithm.
Modern pathology : an official journal of the United States and Canadian Academy of Pathology, Inc. 2024 Jul 17 [Epub ahead of print]
Christian Harder, Alexey Pryalukhin, Alexander Quaas, Marie-Lisa Eich, Maria Tretiakova, Sebastian Klein, Alexander Seper, Axel Heidenreich, George Jabboure Netto, Wolfgang Hulla, Reinhard Büttner, Kasia Bozek, Yuri Tolkach
Institute of Pathology, University Hospital Cologne, Cologne, Germany., Institute of Pathology, Wiener Neustadt State Hospital, Wiener Neustadt, Austria., Institute of Pathology, University Hospital Cologne, Cologne, Germany; Institute of Pathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humbolt-Universität zu Berlin and Berlin Institute of Health, Germany., Department of Laboratory Medicine and Pathology, University of Washington Medical Center, Seattle, WA, USA., Institute of Pathology, Wiener Neustadt State Hospital, Wiener Neustadt, Austria; Danube Private University, Austria., Department of Urology, Pro-Oncology, Robot-Assisted and Specialized Urologic Surgery, University Hospital Cologne, Cologne, Germany; Department of Urology, Medical University Vienna, Austria., Department of Pathology and Laboratory Medicine, Perelman School of Medicine at the University of Pennsylvania., Center for Molecular Medicine, University of Cologne, Cologne, Germany., Institute of Pathology, University Hospital Cologne, Cologne, Germany. Electronic address: .