Prediction of Clinically Significant Cancer Using Radiomics Features of Pre-Biopsy of Multiparametric MRI in Men Suspected of Prostate Cancer

Abstract

Background: Texture features based on the spatial relationship of pixels, known as the gray-level co-occurrence matrix (GLCM), may play an important role in providing the accurate classification of suspected prostate cancer. The purpose of this study was to use quantitative imaging parameters of pre-biopsy multiparametric magnetic resonance imaging (mpMRI) for the prediction of clinically significant prostate cancer.

Methods: This was a prospective study, recruiting 200 men suspected of having prostate cancer. Participants were imaged using a protocol-based 3T MRI in the pre-biopsy setting. Radiomics parameters were extracted from the T2WI and ADC texture features of the gray-level co-occurrence matrix were delineated from the region of interest. Radical prostatectomy histopathology was used as a reference standard. A Kruskal-Wallis test was applied first to identify the significant radiomic features between the three groups of Gleason scores (i.e., G1, G2 and G3). Subsequently, the Holm-Bonferroni method was applied to correct and control the probability of false rejections. We compared the probability of correctly predicting significant prostate cancer between the explanatory GLCM radiomic features, PIRADS and PSAD, using the area under the receiver operation characteristic curves.

Results: We identified the significant difference in radiomic features between the three groups of Gleason scores. In total, 12 features out of 22 radiomics features correlated with the Gleason groups. Our model demonstrated excellent discriminative ability (C-statistic = 0.901, 95%CI 0.859-0.943). When comparing the probability of correctly predicting significant prostate cancer between explanatory GLCM radiomic features (Sum Variance T2WI, Sum Entropy T2WI, Difference Variance T2WI, Entropy ADC and Difference Variance ADC), PSAD and PIRADS via area under the ROC curve, radiomic features were 35.0% and 34.4% more successful than PIRADS and PSAD, respectively, in correctly predicting significant prostate cancer in our patients (p < 0.001). The Sum Entropy T2WI score had the greatest impact followed by the Sum Variance T2WI.

Conclusion: Quantitative GLCM texture analyses of pre-biopsy MRI has the potential to be used as a non-invasive imaging technique to predict clinically significant cancer in men suspected of having prostate cancer.

Keywords: Gleason score; PIRADS; biomarkers; cancer; imaging; mpMRI; prostate; radiomics.

Figure 1

Research workflow. (A) mpMR images showing the segmented region of interest (ROI) marked red in both the T2WI and ADC images for extraction of quantitative imaging texture features (a,b). (B) Microscopic view of clinically significant prostate cancer on histological grading (Gleason’s score) (c,d). (C) Correlation showing significance analysis and AUC obtained by the linear regression models for predicting radiomic features with PIRADS: (e) Heatmap of the Kruskal–Wallis (after applying the Holm–Bonferroni correction) significant test p-values using radiomics features to identify patients of different GS. Significant features that were compared with the GS groups are shown in the colour black (corrected p-value < 0.05). (f) Receiver operating characteristics (ROC) curve and area under the curve (AUC) for model discriminative ability (the areas under the ROC are 0.551 for PIRADS, 0.901 for significant RF and 0.557 for PSAD).

Figure 1

Research workflow. (A) mpMR images showing the segmented region of interest (ROI) marked red in both the T2WI and ADC images for extraction of quantitative imaging texture features (a,b). (B) Microscopic view of clinically significant prostate cancer on histological grading (Gleason’s score) (c,d). (C) Correlation showing significance analysis and AUC obtained by the linear regression models for predicting radiomic features with PIRADS: (e) Heatmap of the Kruskal–Wallis (after applying the Holm–Bonferroni correction) significant test p-values using radiomics features to identify patients of different GS. Significant features that were compared with the GS groups are shown in the colour black (corrected p-value < 0.05). (f) Receiver operating characteristics (ROC) curve and area under the curve (AUC) for model discriminative ability (the areas under the ROC are 0.551 for PIRADS, 0.901 for significant RF and 0.557 for PSAD).

Figure 2

Study flowchat.

Figure 3

Spearman’s rank correlation between each of the radiomics features and the GS groups.

Figure 4

The statistically significant variables from the multivariable logistic regression model (Sum Variance T2WI, Sum Entropy T2WI, Difference Variance T2WI, Entropy ADC and Difference Variance ADC) were used to develop a nomogram to predict the probability of significant PCa.

Figure 5

Calibration curves and internal validation of the nomogram (B = 200 boot repetitions, mean absolute error = 0.034. n = 200).