Interpretable machine learning model for predicting clinically significant prostate cancer: integrating intratumoral and peritumoral radiomics with clinical and metabolic features

Abstract

Background: To develop and validate an interpretable machine learning model based on intratumoral and peritumoral radiomics combined with clinicoradiological features and metabolic information from magnetic resonance spectroscopy (MRS), to predict clinically significant prostate cancer (csPCa, Gleason score ≥ 3 + 4) and avoid unnecessary biopsies.

Methods: This study retrospectively analyzed 350 patients with suspicious prostate lesions from our institution who underwent 3.0 Tesla multiparametric magnetic resonance imaging (mpMRI) prior to biopsy (training set, n = 191, testing set, n = 83, and a temporal validation set, n = 76). Intratumoral and peritumoral volumes of interest (VOI_intra, VOI_peri)) were manually segmented by experienced radiologists on T2-weighted imaging (T2WI) and apparent diffusion coefficient (ADC) maps. Radiomic features were extracted separately from the VOI_intra and VOI_peri. After feature selection via the recursive feature elimination (RFE) algorithm, intratumoral radiomic score (intra-rad-score) and peritumoral radiomic score (peri-rad-score) were constructed. The clinical model, MRS model, and combined model integrating radiomic, clinicoradiological and metabolic features were constructed via the eXtreme Gradient Boosting (XGBoost) algorithm. The predictive performance of the models was evaluated in both the training and testing sets using receiver operating characteristic (ROC) curve analysis. SHapley Additive exPlanations (SHAP) analysis was applied to the combined model to visualize and interpret the prediction process.

Results: A total of 350 patients were included, comprising 173 patients with csPCa (49.4%) and 177 patients with non-csPCa (50.6%). The intra-rad-score and peri-rad-score were constructed via 10 and 16 radiomic features. The combined model demonstrated the highest AUC, accuracy, F1 score, sensitivity, and specificity in the testing set (0.968, 0.928, 0.927, 0.932, and 0.923, respectively) and in the temporal validation set (0.940, 0.895, 0.890, 0.923, and 0.875, respectively). SHAP analysis revealed that the intra-rad-score, PSAD, peri-rad-score, and PI-RADS score were the most important predictors of the combined model.

Conclusion: We developed and validated a robust machine learning model incorporating intratumoral and peritumoral radiomic features, along with clinicoradiological and metabolic parameters, to accurately identify csPCa. The prediction process was visualized via SHAP analysis to facilitate clinical decision- making.

Keywords: Interpretability; Machine learning; Prostate cancer; Radiomics.

Fig. 1

Flow chat of patient selection

Fig. 2

Flow chat of model construction based on radiomics and machine learning

Fig. 3

Cross validation score plots of the training set (A) and testing set (B). A recursive feature elimination (RFE) algorithm based on logistic regression was employed for feature selection in both the training and testing sets. Five-fold cross-validation was performed, and the optimal feature subset was selected based on the average model accuracy in the validation set. For each number of features selected, the graph shows the mean and standard deviation of the model’s cross-validation accuracy. The best models in the training and testing sets are built with 10 and 16 features respectively (red dashed lines), respectively

Fig. 4

ROC curves and radar charts of the model evaluation parameters for the five models in the training, testing, and validation sets. The radar chart displays the AUC, accuracy, F1 score, sensitivity, and specificity of the five models

Fig. 5

Global visualization of the combined model through SHAP. (A) The SHAP bar chart shows the weights of the most important features in the model. (B) The SHAP bees-warm plot displays an information-dense summary illustrating the impact of top features on the model’s output

Fig. 6

Individual visualization of the combined model through SHAP. (A) and (B) show two examples of correctly predicted csPCa cases. (C) and (D) show two examples of correctly predicted non-csPCa cases. (A) for this specific sample, the PI-RADS score, Cit level, peri-rad-score, and intra-rad-score increase the prediction probability of csPCa, whereas the PSAD and PSA have the opposite effect. (B) exhibits a similar pattern. In contrast, (C) shows that the peri-rad-score, PSAD, and PSA increase the predicted probability of non-csPCa, whereas the intra-rad-score and PI-RADS score have the opposite effect. Figure (D) displays a comparable pattern to (C)