To develop a pathology-derived radiomics signature for detecting clinically significant prostate cancer (csPCa) and to evaluate its performance using lesion diameter-based simplified segmentations.
In this retrospective single-center study, 175 participants (120 radical prostatectomy cases; 55 controls) underwent biparametric MRI during 2013-2022. Whole-mount histopathology was registered to MRI using a patient-specific, mold-based 3D pipeline to generate lesion-level ground truth. Six radiologists from different institutions marked lesion diameters per Prostate Imaging Reporting & Data System (PI-RADS) v2.1, blinded to pathology; automated circular segmentations were generated from these measurements and expanded (±1 slice). Features (PyRadiomics) were preprocessed, filtered, and benchmarked via nested cross-validation. Recursive feature elimination produced a 10-feature pathology-derived radiomics signature. Models (Signature, prostate-specific antigen density [PSAD], PI-RADS, and their combinations) were trained/evaluated using a soft-voting ensemble (logistic regression, random forest, and XGBoost) with patient-level grouping; thresholds were optimized using Youden's J. DeLong's and McNemar's tests were used for model comparisons.
PSAD+Signature achieved 0.75 area under the curve (AUC) and 68% (211/312) accuracy. PI-RADS+PSAD achieved 0.77 AUC and 74% (230/312) accuracy. Signature-only achieved 0.66 AUC and 62% (194/312) accuracy. A higher AUC for PSAD+Signature versus Signature (|ΔAUC|=0.093, p=0.012) and for the tripartite model versus Signature (|ΔAUC| = 0.11, p=0.007) was found. PSAD+Signature and PI-RADS+PSAD had similar accuracy (p=0.06).
A histopathology-trained radiomics signature demonstrated moderate standalone performance for lesion-level csPCa detection. When combined with PSAD, diagnostic performance improved and approached that of PI-RADS+PSAD, which achieved the highest absolute accuracy. The PSAD+Signature framework offers a simplified, spatially localized approach that may complement existing PI-RADS-based assessment while maintaining low implementation complexity.
Academic radiology. 2026 Apr 27 [Epub ahead of print]
Omer Tarik Esengur, Stephanie A Harmon, David G Gelikman, Enis C Yilmaz, Haoyue Zhang, Benjamin Simon, Julie Y An, Sena Azamat, Yan Mee Law, Daniel J A Margolis, Jamie Marko, Valeria Panebianco, Maria J Merino, Sandeep Gurram, Bradford J Wood, Rosina Lis, Peter L Choyke, Peter A Pinto, Baris Turkbey
Molecular Imaging Branch, National Cancer Institute, National Institutes of Health, Bethesda, MD (O.T.E., S.A.H., D.G.G., E.C.Y., H.Z., B.S., R.L., P.L.C., B.T.)., Department of Radiology, University of California San Diego, San Diego, CA (J.Y.A.)., Department of Radiology, Cam and Sakura City Hospital, Istanbul, Turkey (S.A.)., Department of Radiology, Singapore General Hospital, Singapore (Y.M.L.)., Department of Radiology, Weill Cornell Medical College, New York, NY (D.J.A.M.)., Department of Radiology, Uniformed Services University, Bethesda, MD (J.M.)., Department of Radiological Sciences, Oncology and Pathology, Sapienza University of Rome, Rome, Italy (V.P.)., Laboratory of Pathology, National Cancer Institute, National Institutes of Health, Bethesda, MD (M.J.M.)., Urologic Oncology Branch, National Cancer Institute, National Institutes of Health, Bethesda, MD (S.G., P.A.P.)., Center for Interventional Oncology, National Cancer Institute, National Institutes of Health, Bethesda, MD (B.J.W., P.A.P.); Department of Radiology, Clinical Center, National Institutes of Health, Bethesda, MD (B.J.W.)., Urologic Oncology Branch, National Cancer Institute, National Institutes of Health, Bethesda, MD (S.G., P.A.P.); Center for Interventional Oncology, National Cancer Institute, National Institutes of Health, Bethesda, MD (B.J.W., P.A.P.)., Molecular Imaging Branch, National Cancer Institute, National Institutes of Health, Bethesda, MD (O.T.E., S.A.H., D.G.G., E.C.Y., H.Z., B.S., R.L., P.L.C., B.T.). Electronic address: .