Purpose: To evaluate four mathematical models for diffusion weighted imaging (DWI) of prostate cancer (PCa) in terms of PCa detection and characterization. Methods: Fifty patients with histologically confirmed PCa underwent two repeated 3 Tesla DWI examinations using 12 equally distributed b values, the highest b value of 2000 s/ mm 2 . Normalized mean signal intensities of regions-of-interest were fitted using monoexponential, kurtosis, stretched exponential, and biexponential models. Tumors were classified into low, intermediate, and high Gleason score groups. Areas under receiver operating characteristic curve (AUCs) were estimated to evaluate performance in PCa detection and Gleason score classifications. The fitted parameters were correlated with Gleason score groups by using the Spearman correlation coefficient (r). Coefficient of repeatability and intraclass correlation coefficient [specifically ICC(3,1)], were calculated to evaluate repeatability of the fitted parameters. Results: The AUC and r values were similar between parameters of monoexponential, kurtosis, and stretched exponential (with the exception of the a parameter) models. The absolute r values for ADC m , ADC k , K, and ADC s were in the range from 0.31 to 0.53 (P < 0.01). Parameters of the biexponential model demonstrated low repeatability. Conclusion: In region-of-interest based analysis, the monoexponential model for DWI of PCa using b values up to 2000 s/mm 2 was sufficient for PCa detection and characterization. Magn

Monoexponential model demonstrated the highest repeatability and clinical values in the regions-of-interest based analysis of prostate cancer DWI, b-values in the range of 0-500 s/mm . Magn Reson Med 77:1249-1264, 2017. © 2016 International Society for Magnetic Resonance in Medicine.

Purpose To develop and validate a classifier system for prediction of prostate cancer (PCa) Gleason score (GS) using radiomics and texture features of T 2 -weighted imaging (T 2 w), diffusion weighted imaging (DWI) acquired using high b values, and T 2 -mapping (T 2 ). Methods T 2 w, DWI (12 b values, 0–2000 s/mm 2 ), and T 2 data sets of 62 patients with histologically confirmed PCa were acquired at 3T using surface array coils. The DWI data sets were post-processed using monoexponential and kurtosis models, while T 2 w was standardized to a common scale. Local statistics and 8 different radiomics/texture descriptors were utilized at different configurations to extract a total of 7105 unique per-tumor features. Regularized logistic regression with implicit feature selection and leave pair out cross validation was used to discriminate tumors with 3+3 vs >3+3 GS. Results In total, 100 PCa lesions were analysed, of those 20 and 80 had GS of 3+3 and >3+3, respectively. The best model performance was obtained by selecting the top 1% features of T 2 w, ADC m and K with ROC AUC of 0.88 (95% CI of 0.82–0.95). Features from T 2 mapping provided little added value. The most useful texture features were based on the gray-level co-occurrence matrix, Gabor transform, and Zernike moments. Conclusion Texture feature analysis of DWI, post-processed using monoexponential and kurtosis models, and T 2 w demonstrated good classification performance for GS of PCa. In multisequence setting, the optimal radiomics based texture extraction methods and parameters differed between different image types.

No abstract