Evaluating the Predictive Value of Preoperative MRI for Erectile Dysfunction Following Radical Prostatectomy

2025-08-05

AI Summary

This study evaluates the predictive value of preoperative MRI for post-radical prostatectomy erectile dysfunction (ED). Method: Three modeling strategies were employed: (1) a clinical-variable-based logistic regression model, (2) an end-to-end deep learning model analyzing MRI directly, and (3) a multimodal fusion model integrating clinical and radiomic features. Model interpretability was enhanced using SHAP values and saliency maps. Contribution/Results: The clinical-only model achieved the highest performance (AUC = 0.663). The MRI-only model did not surpass the clinical baseline but demonstrated anatomically specific attention to the prostatic capsule and neurovascular bundles—validating its biological plausibility. This work constitutes the first systematic validation of preoperative MRI’s auxiliary role in ED prediction following radical prostatectomy. It establishes a methodological framework for interpretable, multimodal predictive modeling and provides preliminary biological evidence supporting MRI-informed risk stratification for postoperative sexual function.

Technology Category

• Machine Learning: Multimodal Learning
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Computer Vision: Multi-modal Vision

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Accurate preoperative prediction of erectile dysfunction (ED) is important for counseling patients undergoing radical prostatectomy. While clinical features are established predictors, the added value of preoperative MRI remains underexplored. We investigate whether MRI provides additional predictive value for ED at 12 months post-surgery, evaluating four modeling strategies: (1) a clinical-only baseline, representing current state-of-the-art; (2) classical models using handcrafted anatomical features derived from MRI; (3) deep learning models trained directly on MRI slices; and (4) multimodal fusion of imaging and clinical inputs. Imaging-based models (maximum AUC 0.569) slightly outperformed handcrafted anatomical approaches (AUC 0.554) but fell short of the clinical baseline (AUC 0.663). Fusion models offered marginal gains (AUC 0.586) but did not exceed clinical-only performance. SHAP analysis confirmed that clinical features contributed most to predictive performance. Saliency maps from the best-performing imaging model suggested a predominant focus on anatomically plausible regions, such as the prostate and neurovascular bundles. While MRI-based models did not improve predictive performance over clinical features, our findings suggest that they try to capture patterns in relevant anatomical structures and may complement clinical predictors in future multimodal approaches.

Problem

• Evaluating MRI's added value for predicting post-prostatectomy erectile dysfunction
• Comparing MRI-based models with clinical predictors for ED outcomes
• Assessing multimodal fusion of imaging and clinical data for ED prediction

Innovation

• Evaluating MRI's predictive value for ED
• Comparing four modeling strategies for ED prediction
• Analyzing MRI and clinical feature contributions