Evaluation of a multiparametric MRI radiomic-based approach for stratification of equivocal PI-RADS 3 and upgraded PI-RADS 4 prostatic lesions

Abstract

Despite the key-role of the Prostate Imaging and Reporting and Data System (PI-RADS) in the diagnosis and characterization of prostate cancer (PCa), this system remains to be affected by several limitations, primarily associated with the interpretation of equivocal PI-RADS 3 lesions and with the debated role of Dynamic Contrast Enhanced-Magnetic Resonance Imaging (DCE-MRI), which is only used to upgrade peripheral PI-RADS category 3 lesions to PI-RADS category 4 if enhancement is focal. We aimed at investigating the usefulness of radiomics for detection of PCa lesions (Gleason Score ≥ 6) in PI-RADS 3 lesions and in peripheral PI-RADS 3 upgraded to PI-RADS 4 lesions (upPI-RADS 4). Multiparametric MRI (mpMRI) data of patients who underwent prostatic mpMRI between April 2013 and September 2018 were retrospectively evaluated. Biopsy results were used as gold standard. PI-RADS 3 and PI-RADS 4 lesions were re-scored according to the PI-RADS v2.1 before and after DCE-MRI evaluation. Radiomic features were extracted from T2-weighted MRI (T2), Apparent diffusion Coefficient (ADC) map and DCE-MRI subtracted images using PyRadiomics. Feature selection was performed using Wilcoxon-ranksum test and Minimum Redundancy Maximum Relevance (mRMR). Predictive models were constructed for PCa detection in PI-RADS 3 and upPI-RADS 4 lesions using at each step an imbalance-adjusted bootstrap resampling (IABR) on 1000 samples. 41 PI-RADS 3 and 32 upPI-RADS 4 lesions were analyzed. Among 293 radiomic features, the top selected features derived from T2 and ADC. For PI-RADS 3 stratification, second order model showed higher performances (Area Under the Receiver Operating Characteristic Curve-AUC- = 80%), while for upPI-RADS 4 stratification, first order model showed higher performances respect to superior order models (AUC = 89%). Our results support the significant role of T2 and ADC radiomic features for PCa detection in lesions scored as PI-RADS 3 and upPI-RADS 4. Radiomics models showed high diagnostic efficacy in classify PI-RADS 3 and upPI-RADS 4 lesions, outperforming PI-RADS v2.1 performance.

Figure 1

Flowchart showing how final cohort was selected. PI-RADS prostate imaging reporting and data system, upPI-RADS 4 lesions scored as PI-RADS 4 after mpMRI PI-RADS assignment but evaluated as PI-RADS 3 after biparametric MRI reading session.

Figure 2

PI-RADS 3 scored alterations. In the first row, an example of PI-RADS 3 lesion confirmed at biopsy as GS 3 + 3: mpMRI showed reduced T2 signal intensity in the left PZ (A), altered diffusivity at b1000 DWI (B) without contrast enhancement (C). In the second row, an example of PI-RADS 3 lesion not confirmed at biopsy: mpMRI showed reduced T2 signal intensity in the right PZ (D), altered diffusivity at b1000 DWI (E) without contrast enhancement (F). PI-RADS prostate imaging-reporting and data system, mpMRI multiparametric MRI, DWI diffusion weighted MRI, PZ peripheral zone.

Figure 3

upPI-RADS 4 scored alterations. In the first row, an example of upPI-RADS 4 lesion confirmed at biopsy as GS 4 + 4: mpMRI showed reduced T2 signal intensity in the right PZ (A), altered diffusivity at b1000 DWI (B) with focal contrast enhancement (C). In the second row, an example of upPI-RADS 4 lesion classified as inflammatory at biopsy: mpMRI showed reduced T2 signal intensity in the right PZ (D), altered diffusivity at b1000 DWI (E) with contrast enhancement (F). PI-RADS prostate imaging-reporting and data system, mpMRI multiparametric MRI, DWI diffusion weighted MRI, PZ peripheral zone.

Figure 4

Bar plots of radiomic features ranked according to their relevance-redundancy predictor importance score for PI-RADS 3 (left side) upPI-RADS4 (right side) lesion detection tasks. ADC apparent diffusion coefficient, glcm gray level co-occurrence matrix, glrlm grey level run length matrix, gldm gray level dependence matrix, glszm grey level size zone matrix, SDLGLE Small Dependence Low Gray Level Emphasis, SALGLE Small Area Low Gray Level Emphasis; SRLGLE Short Run Low Gray Level Emphasis; LAE Large Area Emphasis; IR Interquartile Range; LGLE Low Gray Level Emphasis; CS Cluster Shade; MCC Maximal Correlation Coefficient.

Figure 5

Prediction performances of models from order 1 to 5 for detection of PCa in PI-RADS 3 lesions (on the left) and in upPI-RADS 4 lesions (on the right).