Katalog Plus
Bibliothek der Frankfurt UAS
Bald neuer Katalog: sichern Sie sich schon vorab Ihre persönlichen Merklisten im Nutzerkonto: Anleitung.
Dieses Ergebnis aus BASE kann Gästen nicht angezeigt werden.  Login für vollen Zugriff.

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

Title: Evaluating the Predictive Value of Preoperative MRI for Erectile Dysfunction Following Radical Prostatectomy
Authors: Rouwendaal, Gideon N.L.; Boeke, Daniël; Cox, Inge L.; van der Poel, Henk G.; van Dijk-de Haan, Margriet C.; Beets-Tan, Regina G.H.; Boellaard, Thierry N.; Silva, Wilson; Sub AI Technology for Life; Sub Biology AI Technology For Life; Rekik, Islem; Adeli, Ehsan; Park, Sang Hyun; Cintas, Celia
Publication Year: 2026
Subject Terms: Deep Learning; Erectile Dysfunction; Medical Imaging; MRI; Prostate Cancer; Prostatectomy; Taverne; Theoretical Computer Science; General Computer Science; SDG 3 - Good Health and Well-being
Description: Accurate preoperative prediction of erectile dysfunction (ED) is important for counseling patients undergoing radical prostatectomy. While clinical features are well-established predictors, the added value of preoperative MRI remains underexplored. We assess whether MRI provides additional predictive value for ED at 12 months post-surgery, evaluating four strategies: (1) a clinical-only baseline; (2) classical models using handcrafted MRI-based features; (3) deep learning models trained on MRI slices; and (4) fusion of imaging and clinical inputs. Imaging-based models (AUC 0.569) slightly outperformed handcrafted 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 surpass clinical-only performance. SHAP analysis on the fusion method confirmed that clinical features were the primary drivers of predictive accuracy, while saliency maps suggested that imaging models focused on anatomically relevant regions. However, MRI offered limited added value beyond clinical data in prediction, likely due to dataset size, imaging-related variability, and missing clinical confounders. Larger, standardized datasets and improved integration strategies are needed to better evaluate MRI’s potential in ED prediction.
Document Type: book part
File Description: application/pdf
Language: English
ISSN: 0302-9743
Relation: https://dspace.library.uu.nl/handle/1874/483376
Availability: https://dspace.library.uu.nl/handle/1874/483376
Rights: info:eu-repo/semantics/EmbargoedAccess
Accession Number: edsbas.BFE805E6
Database: BASE