Noninvasive, radiological image-based detection and stratification of Gleason patterns can impact clinical outcomes, treatment selection, and the determination of disease status at diagnosis without subjecting patients to surgical biopsies. We present machine learning-based automatic classification of prostate cancer aggressiveness by combining apparent diffusion coefficient (ADC) and T2-weighted (T2-w) MRI-based texture features. Our approach achieved reasonably accurate classification of Gleason scores (GS) 6(3 + 3) vs. ≥7 and 7(3 + 4) vs. 7(4 + 3) despite the presence of highly unbalanced samples by using two different sample augmentation techniques followed by feature selection-based classification. Our method distinguished between GS 6(3 + 3) and ≥7 cancers with 93% accuracy for cancers occurring in both peripheral (PZ) and transition (TZ) zones and 92% for cancers occurring in the PZ alone. Our approach distinguished the GS 7(3 + 4) from GS 7(4 + 3) with 92% accuracy for cancers occurring in both the PZ and TZ and with 93% for cancers occurring in the PZ alone. In comparison, a classifier using only the ADC mean achieved a top accuracy of 58% for distinguishing GS 6(3 + 3) vs. GS ≥7 for cancers occurring in PZ and TZ and 63% for cancers occurring in PZ alone. The same classifier achieved an accuracy of 59% for distinguishing GS 7(3 + 4) from GS 7(4 + 3) occurring in the PZ and TZ and 60% for cancers occurring in PZ alone. Separate analysis of the cancers occurring in TZ alone was not performed owing to the limited number of samples. Our results suggest that texture features derived from ADC and T2-w MRI together with sample augmentation can help to obtain reasonably accurate classification of Gleason patterns.

Objectives To investigate Haralick texture analysis of prostate MRI for cancer detection and differentiating Gleason Scores (GS). Methods One hundred and forty-seven patients underwent T2- weighted (T2WI) and diffusion-weighted prostate MRI. Cancers ≥0.5ml and non-cancerous peripheral (PZ) and transition zone (TZ) tissue were identified on T2WI and apparent diffusion coefficient (ADC) maps, using whole-mount pathology as reference. Texture features (Energy, Entropy, Correlation, Homogeneity, Inertia) were extracted and analyzed using generalized estimating equations. Results PZ cancers (n=143) showed higher Entropy and Inertia and lower Energy, Correlation and Homogeneity compared to non-cancerous tissue on T2WI and ADC maps (p-values: <.0001–0.008). In TZ cancers (n=43), we observed significant differences for all five texture features on the ADC map (all p-values: <.0001) and for Correlation (p=0.041) and Inertia (p=0.001) on T2WI. On ADC maps, GS was associated with higher Entropy (GS 6 vs 7: p=0.0225; 6 vs >7: p=0.0069) and lower Energy (GS 6 vs 7: p=0.0116, 6 vs >7: p=0.0039). ADC map Energy (p=0.0102) and Entropy (p=0.0019) were significantly different in GS ≤3+4 vs. ≥4+3 cancers; ADC map Entropy remained significant after controlling for the median ADC (p=0.0291). Conclusion Several Haralick based texture features appear useful for prostate cancer detection and GS assessment.

VMS imaging at approximately 70 keV yielded lower image noise and higher CNR than did 120-kVp CT for a given radiation dose. VMS imaging has the potential to replace 120-kVp CT as the standard CT imaging modality, since optimal VMS imaging may be expected to yield improved image quality in a patient with standard body habitus.

Objectives To evaluate the recommendations for multiparametric prostate MRI (mp-MRI) interpretation introduced in the recently updated Prostate Imaging Reporting and Data System version 2 (PI-RADSv2), and investigate the impact of pathologic tumour volume on prostate cancer (PCa) detectability on mpMRI. Methods This was an institutional review board (IRB)-approved, retrospective study of 150 PCa patients who underwent mp-MRI before prostatectomy; 169 tumours ≥0.5-mL (any Gleason Score [GS]) and 37 tumours <0.5-mL (GS ≥4+3) identified on whole-mount pathology maps were located on mp-MRI consisting of T2-weighted imaging (T2WI), diffusion-weighted (DW)-MRI, and dynamic contrast-enhanced (DCE)-MRI. Corresponding PI-RADSv2 scores were assigned on each sequence and combined as recommended by PI-RADSv2. We calculated the proportion of PCa foci on whole-mount pathology correctly identified with PI-RADSv2 (dichotomized scores 1–3 vs. 4–5), stratified by pathologic tumour volume. Results PI-RADSv2 allowed correct identification of 118/125 (94 %; 95 %CI: 90–99 %) peripheral zone (PZ) and 42/44 (95 %; 95 %CI: 89–100 %) transition zone (TZ) tumours ≥0.5 mL, but only 7/27 (26 %; 95 %CI: 10–42 %) PZ and 2/10 (20 %; 95 %CI: 0–52 %) TZ tumours with a GS ≥4+3, but <0.5 mL. DCE-MRI aided detection of 4/125 PZ tumours ≥0.5 mL and 0/27 PZ tumours <0.5 mL. Conclusions PI-RADSv2 correctly identified 94–95 % of PCa foci ≥0.5 mL, but was limited for the assessment of GS ≥4+3 tumours ≤0.5 mL. DCE-MRI offered limited added value to T2WI+DW-MRI.

No abstract