Fig 1.
The T2-weighted images (T2w) are standardized, the monoexponential and kurtosis models are fitted to the diffusion weighted images (DWI), and the T2 relaxation values are obtained using a two parameter monoexponential function. Texture features are extracted subsequently. Top 1% of the features are selected by AUC. A logistic regression model is fitted to the selected features, and is used to predict the lesion’s Gleason score class.
Fig 2.
An example case with parametric maps.
A: Whole mount prostate histological section. B: ADCm (apparent diffusion coefficient, monoexponential model). C: ADCm (apparent diffusion coefficient, kurtosis model). D: K (kurtosis parameter, kurtosis model). E: T2w (T2-weighted imaging). F: T2 (T2-mapping). This is from patient #43 (see Table A in S1 File). The two lesions are outlined; their Gleason scores are 4+3 (lower, posterolateral region) and 3+4 (upper, anterior region).
Table 1.
Texture methods ranked in the best one percent.
Table 2.
Best texture feature per image type.
Table 3.
Best statistical feature per image type.
Fig 3.
An example of texture feature maps.
These are extracted from DWI parametric maps (ADCm, ADCk, K), T2-weighted imaging (T2w), and parametric map of T2 relaxation values (T2). Source image type, window size, and texture descriptor parameters are shown above the images. The two lesions are outlined; their Gleason scores are 4+3 (lower) and 3+4 (upper).
Fig 4.
ROC curves within each image type (T2w, ADCm, ADCk, K, T2).
A: The best statistical feature. B: The best texture feature. The final model of the best selected features from ADCm, K, and T2w obtained using L1 regularized logistic regression and validated with leave-pair-out cross-validation (LPOCV) is also included in both A and B.
Table 4.
Performance figures for each image type alone.
They are ROC AUC (receiver operating characteristic, area under curve) values estimated using outer leave-pair-out cross-validation (LPOCV) and different feature subsets.
Table 5.
Performance figures for image type combinations.
They are ROC AUC (receiver operating characteristic, area under curve) values estimated using outer leave-pair-out cross-validation (LPOCV) and different feature subsets.