Utility of T2-weighted MRI texture analysis in assessment of peripheral zone prostate cancer aggressiveness: a single-arm, multicenter study

Abstract

T₂-weighted (T₂W) MRI provides high spatial resolution and tissue-specific contrast, but it is predominantly used for qualitative evaluation of prostate anatomy and anomalies. This retrospective multicenter study evaluated the potential of T₂W image-derived textural features for quantitative assessment of peripheral zone prostate cancer (PCa) aggressiveness. A standardized preoperative multiparametric MRI was performed on 87 PCa patients across 6 institutions. T₂W intensity and apparent diffusion coefficient (ADC) histogram, and T₂W textural features were computed from tumor volumes annotated based on whole-mount histology. Spearman correlations were used to evaluate association between textural features and PCa grade groups (i.e. 1-5). Feature utility in differentiating and classifying low-(grade group 1) vs. intermediate/high-(grade group ≥ 2) aggressive cancers was evaluated using Mann-Whitney U-tests, and a support vector machine classifier employing "hold-one-institution-out" cross-validation scheme, respectively. Textural features indicating image homogeneity and disorder/complexity correlated significantly (p < 0.05) with PCa grade groups. In the intermediate/high-aggressive cancers, textural homogeneity and disorder/complexity were significantly lower and higher, respectively, compared to the low-aggressive cancers. The mean classification accuracy across the centers was highest for the combined ADC and T₂W intensity-textural features (84%) compared to ADC histogram (75%), T₂W histogram (72%), T₂W textural (72%) features alone or T₂W histogram and texture (77%), T₂W and ADC histogram (79%) combined. Texture analysis of T₂W images provides quantitative information or features that are associated with peripheral zone PCa aggressiveness and can augment their classification.

Figure 1

Illustration of tumor volume-of-interest (VOI) delineation and grey level co-occurrence matric (GLCM) texture feature extraction. (a) Histopathology slides were visually matched to the T₂-weighted (T₂W) images using anatomical landmarks. Peripheral (red) and transition (yellow) zone tumors were manually outlined on the T₂W images based on their location on histology and appearance on T₂W images, and then transformed to corresponding apparent diffusion coefficient (ADC) maps via registration or manually if the registration was deemed suboptimal. (b) Textural feature extraction from T₂W VOIs using 2D average approach. For illustration purposes, the number of grey level bins was limited to four in this schematic, instead of the 32 used in actual computations.

Figure 2

Schematic of the cross-validation scheme employed in support vector machine classifier training and testing across six institutional centers. At each iteration, data from one institution was held out for testing, and data from the remaining 5 institutions used for training.

Figure 3

Flow chart of patients and datasets included in study. mpMRI multiparametric MRI, PCa prostate cancer, TZ transition zone.

Figure 4

Box plots showing the distributions of apparent diffusion coefficient (ADC) and T₂-weighted (T₂W) histogram (10^th percentile), and T₂W textural (angular second moment) features between low-aggressive (L) and intermediate/high-aggressive (I/H) prostate cancers at the participating institutions or sites. Notice that, where the T₂W histogram feature (middle; Site F) overlap between the two cancer groups, an improved separation is observed for the textural feature (right; Site F), and vice-versa, indicating that the feature sets contain complementary information. *Indicates mean value.

Figure 5

Performance of apparent diffusion coefficient (ADC), T₂-weighted (T₂W) histogram and T₂W textual features in SVM classification of low-aggressive (grade group 1) versus intermediate/high-aggressive (grade group ≥ 2) prostate cancers. (a) Receiver operating characteristic curves showing the added value of T₂W image textural features over traditional intensity histogram features alone. (b) Box plot comparing classification accuracies. * indicates significant difference.