Transition zone prostate cancer: Logistic regression and machine‐learning models of quantitative ADC, shape and texture features are highly accurate for diagnosis

Abstract

Background The limitation of diagnosis of transition zone (TZ) prostate cancer (PCa) using subjective assessment of multiparametric (mp) MRI with PI‐RADS v2 is related to overlapping features between cancers and stromal benign prostatic hyperplasia (BPH) nodules, particularly in small lesions. Purpose To evaluate modeling of quantitative apparent diffusion coefficient (ADC), texture, and shape features using logistic regression (LR) and support vector machine (SVM) models for the diagnosis of transition zone PCa. Study Type Retrospective. Population Ninety patients; 44 consecutive TZ PCa were compared with 61 consecutive BPH nodules (26 glandular/35 stromal). Field Strength/Sequence 3 T/T2‐weighted (T2W) fast spin‐echo, diffusion weighted imaging. Assessment A radiologist manually segmented lesions on axial images for quantitative ADC (mean, 10th, 25th‐centile‐ADC), T2W‐shape (circularity, convexity) and T2W‐texture (kurtosis, skewness, entropy, run‐length nonuniformity [RLNU], gray‐level nonuniformity [GLNU]) analysis. A second radiologist segmented one‐fifth of randomly selected lesions to determine the reproducibility of measurements. The reference standard was histopathology for all lesions. Statistical Tests Quantitative features were selected a priori and were compared using univariate and multivariate analysis. LR and SVM models of statistically significant features were constructed and evaluated using receiver operator characteristic (ROC) analysis. Subgroup analysis of TZ PCa vs. only stromal BPH and in lesions measuring <15 mm was performed. Agreement in measurements was assessed using the Dice similarity coefficient (DSC). Results Mean, 25th and 10th‐centile ADC, circularity, and texture (entropy, RLNU, GLNU) features differed between groups (P < 0.0001–0.0058); however, at multivariate analysis only circularity and ADC metrics (P < 0.001) remained significant. LR and SVM models were highly accurate for the diagnosis of TZ PCa (sensitivity/specificity/AUC): 93.2%/98.4%/0.989 and 93.2%/96.7%/0.949, respectively, with no significance difference between the LR and SVM models (P = 0.2271). Reproducibility of segmentation was excellent (DSC 0.84 tumors and 0.87 BPH). Subgroup analyses of TZ PCa vs. stromal BPH (AUC = 0.976) and in <15 mm lesions (AUC = 0.990) remained highly accurate. Data Conclusion LR and SVM models incorporating previously described quantitative ADC, shape and texture analysis features are highly accurate for the diagnosis of TZ PCa and remained accurate when comparing TZ PCa with stromal BPH and in smaller lesions. Level of Evidence: 3 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;50:940–950.

Multiparametric MRI may Help to Identify Patients With Prostate Cancer in a Contemporary Cohort of Patients With Clinical Bladder Outlet Obstruction Scheduled for Holmium Laser Enucleation of the Prostate (HoLEP)

“…Of those, PCa was found in one fourth after mpMRI fusion biopsy of the prostate. Although this rate seems rather low, it should be taken into account that more than one third of the patients scheduled for HoLEP presented with a history of one or more negative biopsies (8)(9)(10). In contrast to our findings, Preisser et al observed a detection rate of 71.6% in biopsy naïve, 50.9% in patients after one negative biopsy, and 43.5% after two negative biopsies for mpMRI fusion biopsy (11).…”

Identification of Tumor-Specific MRI Biomarkers Using Machine Learning (ML)

“…Another useful application of ML MRI has been reported for the accurate distinction of stromal benign prostatic hyperplasia from PCa in the transition zone, a challenging diagnosis particularly in the presence of small lesions. Using ML based statistical analysis of quantitative features such as ADC maps, shape, and image texture, immense diagnostic accuracy in the of differentiation between small neoplastic lesions from benign ones was demonstrated [ 202 ].…”

Radiomics in prostate cancer: basic concepts and current state-of-the-art

“…Database and model construction are a breakthrough point of radiomics analysis that could be applied as a powerful assistant tool for diagnosis and treatment effect prediction. After that, the classifier or prediction model is usually built with machine learning algorithms, which mainly known as Support Vector Machine (SVM) [47,48], Logistic Regression [49], Random Forest (RF), Decision Tree (DT), clustering analysis, etc. Besides, Convolutional Neural Network (CNN), Artificial Neural Network (ANN), K-Nearest Neighbor (KNN), Holistically Nested Network (HNN) [50,51], etc., which belong to rapiddeveloping deep learning, really accelerated the pace of radiomics progress.…”