Detection of Prostate Cancer Using Biparametric Prostate MRI, Radiomics, and Kallikreins: A Retrospective Multicenter Study of Men With a Clinical Suspicion of Prostate Cancer

Abstract

Background: Accurate detection of clinically significant prostate cancer (csPCa), Gleason Grade Group ≥ 2, remains a challenge. Prostate MRI radiomics and blood kallikreins have been proposed as tools to improve the performance of biparametric MRI (bpMRI). Purpose: To develop and validate radiomics and kallikrein models for the detection of csPCa. Study Type: Retrospective. Population: A total of 543 men with a clinical suspicion of csPCa, 411 (76%, 411/543) had kallikreins available and 360 (88%, 360/411) did not take 5-alpha-reductase inhibitors. Two data splits into training, validation (split 1: single center, n = 72; split 2: random 50% of pooled datasets from all four centers), and testing (split 1: 4 centers, n = 288; split 2: remaining 50%) were evaluated. Field strength/Sequence: A 3 T/1.5 T, TSE T2-weighted imaging, 3x SE DWI. Assessment: In total, 20,363 radiomic features calculated from manually delineated whole gland (WG) and bpMRI suspicion lesion masks were evaluated in addition to clinical parameters, prostate-specific antigen, four kallikreins, MRI-based qualitative (PI-RADSv2.1/IMPROD bpMRI Likert) scores.

Evaluation of the Predictive Role of Blood-Based Biomarkers in the Context of Suspicious Prostate MRI in Patients Undergoing Prostate Biopsy

“…However, in contrast to our cohort, their study included more patients with equivocal (PI-RADS 3) MRI lesions; PSA (median 7.8-7.9 ng/mL), age (median 65-67 years), and other clinical variables were similar to those of our cohort [24]. In the future, new tools such as artificial intelligence with radiomics may limit the MRI inter-reader variability and further enhance risk stratification in patients with suspicious MRI [19,20,[25][26][27].…”

Editorial for “Diagnostic Performance of Prostate MRI Radiomics, Four Kallikrein Panel and Radiologist in the Detection of Prostate Cancer: A Retrospective External Validation Multi‐center Study of Men With a Clinical Suspicion of Prostate Cancer”

“…In this study, the authors compared an magnetic resonance imaging (MRI)-based csPca prediction approach to other prediction models that included various combinations of age, PSA, PSA-density, prostate volume, other kallikreins, and radiomics. 2 The kallikrein panel used in this study included total PSA, free-PSA, intact-PSA, and human kallikrein-2 (hk2). 2 PSA, a kallikrein, is secreted as pro-PSA and then cleaved to PSA in the lumen of the prostate gland by hK2.…”

“…2 The kallikrein panel used in this study included total PSA, free-PSA, intact-PSA, and human kallikrein-2 (hk2). 2 PSA, a kallikrein, is secreted as pro-PSA and then cleaved to PSA in the lumen of the prostate gland by hK2. Normally, a small amount of both precursors and cleaved forms leak into the circulation.…”

“…In this study, the authors evaluated different approaches to csPca prediction. 2 csPca was defined as Gleason Grade Group score ≥2. Prostate MR imaging was performed using a standardized imaging protocol and interpreted by an experienced radiologist using a previously developed MRI reporting system for prostate cancer-IMPROD bpMRI Likert (IMPROD-Improved Prostate Cancer Diagnosis-Combination of Magnetic Resonance Imaging and Biomarkers; bpMRI-biparametric MRI).…”

“…For the radiomics analysis in this study, images were manually segmented by a single radiologist. 2 The uniformity in segmentation method reduces variability and improves feature selection but can impact the ability to identify features that remain robust across differing conditions. A large number of features were extracted, selected, and pruned to yield 22 features for each of the two data splits in the study.…”