Automatic stratification of prostate tumour aggressiveness using multiparametric MRI: a horizontal comparison of texture features.

Previous studies have identified apparent diffusion coefficient (ADC) from diffusion-weighted imaging (DWI) can stratify prostate cancer into high- and low-grade disease (HG and LG, respectively). In this study, we consider the improvement of incorporating texture features (TFs) from T2-weighted (T2w) multiparametric magnetic resonance imaging (mpMRI) relative to mpMRI alone to predict HG and LG disease. mpMRI was acquired from 30 patients prior to radical prostatectomy. Sequences included T2w imaging, DWI and dynamic contrast enhanced (DCE) MRI. mpMRI data were co-registered with 'ground truth' histology. Tumours were delineated on the histology with Gleason scores (GSs) and classed as HG if GS ≥ 4 + 3, or LG if GS ≤ 3 + 4. Texture features based on three statistical families, namely the grey-level co-occurrence matrix (GLCM), grey-level run length matrix (GLRLM) and the grey-level size zone matrix (GLSZM), were computed from . Logistic regression models were trained using different feature subsets to classify each lesion as either HG or LG. To avoid overfitting, fivefold cross validation was applied on feature selection, model training and performance evaluation. Performance of all models generated was evaluated using the area under the curve (AUC) method. Consistent with previous studies, ADC was found to discriminate between HG and LG with an AUC of 0.76. Of the three statistical TF families, GLCM (plus select mpMRI features including ADC) scored the highest AUC (0.84) with GLRLM plus mpMRI similarly performing well (AUC  =  0.82). When all TFs were considered in combination, an AUC of 0.91 (95% confidence interval 0.87-0.95) was achieved. Incorporating T2w TFs significantly improved model performance for classifying prostate tumour aggressiveness. This result, however, requires further validation in a larger patient cohort.