From AI-based image analysis to surgical decision support in prostate cancer: interdisciplinary application of the international radiomics platform - Summary - MDSpire
Advertisement
From AI-based image analysis to surgical decision support in prostate cancer: interdisciplinary application of the international radiomics platform
To clinically implement and prospectively validate a platform-based multimodal data analysis pipeline within a radiological-urological collaboration for prostate cancer surgical planning, addressing fragmented workflows.
Key Findings:
Prediction of ECE improved significantly with the addition of imaging-derived parameters (AUC 0.90, 95% CI: 0.86–0.94) compared to conventional clinical parameters (AUC 0.71, 95% CI: 0.63–0.77).
Imaging-derived features did not provide meaningful value for predicting PSM (AUC 0.60, 95% CI: 0.52–0.68) or nerve-sparing approach decisions (AUC 0.79, 95% CI: 0.73–0.83).
Performance of models was consistent across internal cross-validation and prospective external validation.
Interpretation:
The study demonstrates the feasibility of a multimodal data analysis workflow for surgical planning in prostate cancer, with enhanced ECE prediction through imaging-derived parameters.
Limitations:
The study is limited to a single center and may not be generalizable to other settings, potentially affecting the applicability of the findings.
The addition of radiomics features did not enhance predictive capabilities for PSM or nerve-sparing decisions.
Conclusion:
The exploratory study highlights both the potential and limitations of AI-driven workflow integration in routine clinical practice for prostate cancer management, suggesting areas for future research.
by Fabian Tollens, Niklas Westhoff, Jan Moltz, Tim Hartenstein, Anne Sophie Michel, Mahnoosh Naeimi, Johannes Ludwig, Peter Kohlmann, Judith Herrmann, Konstantin Nikolaou, Stefan O. Schoenberg, Dominik Nörenberg
