Noninvasive Prediction of High‐Grade Prostate Cancer via Biparametric MRI Radiomics

Abstract

Background Gleason score (GS) is a histologic prognostic factor and the basis of treatment decision‐making for prostate cancer (PCa). Treatment regimens between lower‐grade (GS ≤7) and high‐grade (GS >7) PCa differ largely and have great effects on cancer progression. Purpose To investigate the use of different sequences in biparametric MRI (bpMRI) of the prostate gland for noninvasively distinguishing high‐grade PCa. Study Type Retrospective. Population In all, 489 patients (training cohort: N = 326; test cohort: N = 163) with PCa between June 2008 and January 2018. Field Strength/Sequence 3.0T, pelvic phased‐array coils, bpMRI including T₂‐weighted imaging (T₂WI) and diffusion‐weighted imaging (DWI); apparent diffusion coefficient map extracted from DWI. Assessment The whole prostate gland was delineated. Radiomic features were extracted and selected using the Kruskal–Wallis test, the minimum redundancy‐maximum relevance, and the sequential backward elimination algorithm. Two single‐sequence radiomic (T₂WI, DWI) and two combined (T₂WI‐DWI, T₂WI‐DWI‐Clinic) models were respectively constructed and validated via logistic regression. Statistical Tests The Kruskal–Wallis test and chi‐squared test were utilized to evaluate the differences among variable groups. P < 0.05 determined statistical significance. The area under the receiver operating characteristic curve (AUC), specificity, sensitivity, and accuracy were used to evaluate model performance. The Delong test was conducted to compare the differences between the AUCs of all models. Result All radiomic models showed significant (P < 0.001) predictive performances. Between the single‐sequence radiomic models, the DWI model achieved the most encouraging results, with AUCs of 0.801 and 0.787 in the training and test cohorts, respectively. For the combined models, the T₂WI‐DWI models acquired an AUC of 0.788, which was almost the same with DWI in the test cohort, and no significant difference was found between them (training cohort: P = 0.199; test cohort: P = 0.924). Data Conclusion Radiomics based on bpMRI can noninvasively identify high‐grade PCa before the operation, which is helpful for individualized diagnosis of PCa. Level of Evidence 4 Technical Efficacy Stage 2