arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2508.03461eess.IVcs.CV

术前MRI对根治性前列腺切除术后勃起功能障碍预测价值的评估

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

University of Amsterdam（阿姆斯特丹大学）；Antoni van Leeuwenhoek-Netherlands Cancer Institute（安托尼·范·列文霍克-荷兰癌症研究所）；Department of Urology（泌尿科部）；AI Technology for Life（人工智能技术生命）；Utrecht University（乌特勒支大学）；GROW School for Oncology and Developmental Biology（GROW肿瘤学与发育生物学学院）

Gideon N. L. Rouwendaal, Daniël Boeke, Inge L. Cox, Henk G. van der Poel, Margriet C. van Dijk-de Haan, Regina G. H. Beets-Tan, Thierry N. Boellaard, Wilson Silva

备注：
13 pages, 5 figures, 2 tables. Accepted at PRedictive Intelligence in MEdicine workshop @ MICCAI 2025 (PRIME-MICCAI). This is the submitted manuscript with added link to github repo, funding acknowledgements and authors' names and affiliations. No further post submission improvements or corrections were integrated. Final version not published yet
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本研究评估了术前MRI对根治性前列腺切除术后勃起功能障碍预测价值，发现MRI模型在某些方面略优于传统方法，但未超越临床特征。

摘要：

准确的术前预测勃起功能障碍（ED）对接受根治性前列腺切除术的患者咨询非常重要。尽管临床特征是已确立的预测因素，但术前MRI的附加价值仍待探索。我们研究了MRI是否能为术后12个月的ED提供额外的预测价值，评估了四种建模策略：（1）仅临床特征的基线模型，代表当前最先进的状态；（2）使用手工制作的解剖特征的经典模型，这些特征来源于MRI；（3）直接在MRI切片上训练的深度学习模型；以及（4）图像和临床输入的多模态融合。基于图像的模型（最大AUC 0.569）略微优于手工制作的解剖学方法（AUC 0.554），但未能达到仅临床特征的基线模型（AUC 0.663）。融合模型提供了微小的提升（AUC 0.586），但未超过仅临床特征的性能。SHAP分析确认临床特征对预测性能贡献最大。最佳图像模型的显著性图显示其主要关注解剖上合理的区域，如前列腺和神经血管束。虽然基于MRI的模型在预测性能上未超过临床特征，但我们的发现表明它们试图捕捉相关解剖结构中的模式，并可能在未来的多模态方法中补充临床预测因素。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑