Background

Radiomics or computer-extracted texture features derived from MRI have been shown to help quantitatively characterize prostate cancer (PCa). Radiomics have not been explored depth in the context of predicting biochemical recurrence (BCR) of PCa.

Purpose

 To identify a set of radiomic features derived from pretreatment biparametric MRI (bpMRI) that may be predictive of PCa BCR.

Study Type

Retrospective.

Subjects

In all, 120 PCa patients from two institutions, I-1 and I-2, partitioned into training set D-1 (N=70) from I-1 and independent validation set D-2 (N=50) from I-2. All patients were followed for 3 years.

Sequence

3T, T-2-weighted (T2WI) and apparent diffusion coefficient (ADC) maps derived from diffusion-weighted sequences.

Assessment

PCa regions of interest (ROIs) on T2WI were annotated by two experienced radiologists. Radiomic features from bpMRI (T2WI and ADC maps) were extracted from the ROIs. A machine-learning classifier (C-BCR) was trained with the best discriminating set of radiomic features to predict BCR (p(BCR)).

Statistical Tests

Wilcoxon rank-sum tests with P<0.05 were considered statistically significant. Differences in BCR-free survival at 3 years using p(BCR) was assessed using the Kaplan-Meier method and compared with Gleason Score (GS), PSA, and PIRADS-v2.

Results

Distribution statistics of co-occurrence of local anisotropic gradient orientation (CoLlAGe) and Haralick features from T2WI and ADC were associated with BCR (P<0.05) on D-1. C-BCR predictions resulted in a mean AUC=0.84 on D-1 and AUC=0.73 on D-2. A significant difference in BCR-free survival between the predicted classes (BCR+and BCR-) was observed (P=0.02) on D-2 compared to those obtained from GS (P=0.8), PSA (P=0.93) and PIRADS-v2 (P=0.23).

Data Conclusion

Radiomic features from pretreatment bpMRI can be predictive of PCa BCR after therapy and may help identify men who would benefit from adjuvant therapy.