Peritumoral Radiomics Strategy Based on Ensemble Learning for the Prediction of Gleason Grade Group of Prostate Cancer

Rationale and Objectives: To develop and evaluate a peritumoral radiomic-based machine learning model to differentiate low-Gleason grade group (L-GGG) and high-GGG (H-GGG) prostate lesions. Materials and Methods: In this retrospective study, a total of 175 patients with prostate cancer (PCa) confirmed by puncture biopsy were recruited and included 59 patients with L-GGG and 116 patients with H-GGG. The original PCa regions of interest (ROIs) were delineated on T2-weighted (T2WI), diffusion-weighted imaging (DWI), and apparent diffusion coefficient (ADC) maps, and then centra-tumoral and peritumoral ROIs were defined. Features were meticulously extracted from each ROI to establish radiomics models, employing distinct sequence datasets. Peritumoral radiomics models were specifically developed for both the peripheral zone (PZ) and transitional zone (TZ), utilizing dedicated PZ and TZ datasets, respectively. The performances of the models were evaluated by using the receiver operating characteristic (ROC) curve and precision-recall curve. Results The classification model with combined peritumoral features based on T2 + DWI + ADC sequence dataset demonstrated superior performance compared to the original tumor and centra-tumoral classification models. It achieved an area under the ROC curve (AUC) of 0.850 [95% confidence interval, 0.849, 0.860] and an average accuracy of 0.950. The combined peritumoral model out-performed the regional peritumoral models with AUC of 0.85 versus 0.75 for PZ lesions and 0.88 versus 0.69 for TZ lesions, respectively. The peritumoral classification models exhibit greater efficacy in predicting PZ lesions as opposed to TZ lesions. Conclusion: The peritumoral radiomics features showed excellent performance in predicting GGG in PCa patients and might be a valuable addition to the non-invasive assessment of PCa aggressiveness.

Automated summary

This study developed and evaluated a machine learning model based on peritumoral radiomic features to differentiate low-Gleason grade group (L-GGG) and high-GGG (H-GGG) prostate lesions. The model showed superior performance compared to the original tumor and centra-tumoral classification models.