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

<p><b>Background:</b> 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). <br></p><p><b>Purpose:</b> To develop and validate radiomics and kallikrein models for the detection of csPCa. Study Type Retrospective. <br></p><p><b>Population:</b> 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. <br></p><p><b>Field strength/Sequence:</b> A 3 T/1.5 T, TSE T2-weighted imaging, 3x SE DWI. <br></p><p><b>Assessment:</b> 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. <br></p><p><b>Statistical Tests: </b>For the detection of csPCa, area under receiver operating curve (AUC) was calculated using the DeLong's method. A multivariate analysis was conducted to determine the predictive power of combining variables. The values of P-value < 0.05 were considered significant. <br></p><p><b>Results:</b> The highest prediction performance was achieved by IMPROD bpMRI Likert and PI-RADSv2.1 score with AUC = 0.85 and 0.85 in split 1, 0.85 and 0.83 in split 2, respectively. bpMRI WG and/or kallikreins demonstrated AUCs ranging from 0.62 to 0.73 in split 1 and from 0.68 to 0.76 in split 2. AUC of bpMRI lesion-derived radiomics model was not statistically different to IMPROD bpMRI Likert score (split 1: AUC = 0.83, P-value = 0.306; split 2: AUC = 0.83, P-value = 0.488). Data Conclusion The use of radiomics and kallikreins failed to outperform PI-RADSv2.1/IMPROD bpMRI Likert and their combination did not lead to further performance gains.<br></p><p><b>Level of Evidence:</b> 1 <br></p><p><b>Technical Efficacy:</b> Stage 2<br></p>