From AI-based image analysis to surgical decision support in prostate cancer: interdisciplinary application of the international radiomics platform.

Objectives: Diagnosis and surgical therapy planning for prostate cancer patients are often hindered by fragmented workflows and a lack of integrated, data-driven analysis - barriers that specifically impede the effective deployment of machine learning (ML)-based risk stratification and clinical decision support. The aim of this exploratory study was to clinically implement and prospectively validate a platform-based multimodal data analysis pipeline within a radiological-urological collaboration. Materials and methods: In this single center analysis, a total of 249 patients (176 retrospectively, 73 prospectively) undergoing radical prostatectomy were included. Multimodal datasets, including preoperative multiparametric MRI, clinical, laboratory, and pathological data, were harmonized and imported into the International Radiomics Platform (IRP). Radiomics features were extracted and machine learning models were constructed to predict extracapsular extension (ECE), nerve-sparing approach decision, and positive surgical margin (PSM) risk. Results are reported as area under the curve (AUC) values including 95% confidence intervals. Results: A cloud-based software prototype was implemented based on the IRP, integrating prediction models for clinical decision support. Using a step-wise modeling approach, prediction of extracapsular extension (ECE) improved substantially when imaging-derived parameters (e.g. PI-RADS scores, tumor-capsule contact length) were added to conventional clinical parameters (AUC 0.90, 95% CI: 0.86-0.94 vs. 0.71, 95% CI: 0.63-0.77). In contrast, the addition of imaging-derived features provided no meaningful incremental value for predicting positive surgical margins (PSM; AUC 0.60, 95% CI: 0.52-0.68) or nerve-sparing approach decisions (AUC 0.79, 95% CI: 0.73-0.83), which were also unchanged by the further inclusion of quantitative radiomics features. Performance was consistent across internal cross-validation and prospective external validation. Conclusion: This exploratory study demonstrates the feasibility of a platform-based, multimodal data analysis workflow for prostate cancer surgical planning. Integration of imaging-derived parameters meaningfully enhanced ECE prediction, while radiomics offered no additional benefit beyond standard imaging. These findings highlight both the potential and current limitations of AI-driven workflow integration in routine clinical practice.