Population-Specific Radiomics From Biparametric Magnetic Resonance Imaging Improves Prostate Cancer Risk...

To quantify population-specific differences in prostate cancer (PCa) presentation between African American (AA) and White (W) men on MRI using radiomics.

We identified N = 149 men with PCa who underwent 3T MRI, a confirmatory biopsy and for whom self-reported race was available. Patient studies were partitioned into training (D_Tr) and hold-out test set (D_Te). Three hundred radiomic features quantifying textural patterns were extracted from radiologist delineated PCa regions of interest (ROI) on biparametric MRI. Features with significant differences (P < .05) between clinically significant (csPCa) and insignificant (ciPCa) PCa were identified. Machine learning models were trained separately for AA and W men (C_AA, C_W) on D_Tr to distinguish csPCa and ciPCa. Validation on D_Te was assessed for AUC and compared against a population agnostic model (C_PA) in combination with clinical parameters (age, PSA, Prostate Imaging Reporting and Diagnostic System and tumor volume).

Radiomic features from PCa ROIs on biparametric MRI associated with csPCa were observed to be different in AA compared with W men, especially in the peritumoral region. Population-specific radiomic models outperformed similarly trained C_PA models (AUC = 0.84, 0.57 with C_AA, C_PA; P < .05) in AA men on D_Te. Similar findings were observed for W men (AUC = 0.71, 0.60 with C_W, C_PA; P < .05). Integrating clinical and radiomics further improved the risk stratification for AA men (AUC = 0.90) and W men (AUC = 0.75).

Accounting for population-specific differences in radiomics may enable improved PCa risk stratification at MRI among AA men compared with a population agnostic approach.