AB016. SOH26AB_0294. The use of CT radiomics for predicting the malignant potential of residual retroperitoneal masses post-chemotherapy in metastatic testicular cancer: a systematic review and meta-analysis
Urology Session

AB016. SOH26AB_0294. The use of CT radiomics for predicting the malignant potential of residual retroperitoneal masses post-chemotherapy in metastatic testicular cancer: a systematic review and meta-analysis

James Kelly1, Gavin Calpin2, Robert Kelly3, Mark Quinlan1

1Department of Urology, Connolly Hospital Blanchardstown, Dublin, Ireland; 2Department of Surgery, Royal College of Surgeons in Ireland, Dublin, Ireland; 3Department of Surgery, St. Vincent’s University Hospital, Dublin, Ireland

Background: Retroperitoneal lymph node dissection (RPLND) may be indicated in men post-chemotherapy for metastatic non-seminomatous germ-cell tumours (mNSGCT). In up to 50% of cases, retroperitoneal masses represent benign necrosis/fibrosis, indicating overtreatment and unnecessary morbidity. Radiomics has emerged as a potential predictor of the malignant potential of retroperitoneal masses. The aim of this study was to determine the use of radiomics in predicting the malignant potential of residual retroperitoneal masses post-chemotherapy in metastatic testicular cancer.

Methods: A systematic review was conducted as per Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A search was conducted of the PubMed, Embase, and Cochrane Library databases. After review by two independent authors, five studies were deemed eligible for inclusion.

Results: Five studies were included with a combined total of 392 patients. The mean age was 29.8 years (range, 26–36 years). The results highlighted the good performance of radiomics. Meta-analysis revealed a pooled sensitivity for the radiomics training model of 86.1% [95% confidence interval (CI): 76.3–92.2%], a specificity of 79.3% (95% CI: 65–88.8%), and an area under the curve (AUC) of 88.8% (95% CI: 78.7–93.2%). Meta-analysis of the test model revealed a pooled sensitivity of 82.3% (95% CI: 72.6–89.1%), a specificity of 68.9% (95% CI: 58.3–77.8%), and an AUC of 81.2% (95% CI: 65.3–86.9%).

Conclusions: The use of radiomics is an evolving field with potential application to reduce morbidity in RPLND in mNSGCT. Most radiomics in mNSGCT are computed tomography (CT) based with three-dimensional (3D) reconstruction. Combination of radiomics with other biochemical biomarkers to further predict the nature of residual retroperitoneal masses is a potential development that may aid surgical decision making. Further prospective, standardized studies are required to assess radiomic markers and allow integration into clinical practice.

Keywords: Artificial intelligence; germ cell tumour; radiomics; retroperitoneal mass; testicular cancer

Acknowledgments

None.

Footnote

Funding: None.

Conflicts of Interest: The authors have no conflicts of interest to declare.

Ethical Statement: The authors are accountable for all aspects of the work in ensuring that questions related to the accuracy or integrity of any part of the work are appropriately investigated and resolved.

Open Access Statement: This is an Open Access article distributed in accordance with the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International License (CC BY-NC-ND 4.0), which permits the non-commercial replication and distribution of the article with the strict proviso that no changes or edits are made and the original work is properly cited (including links to both the formal publication through the relevant DOI and the license). See: https://creativecommons.org/licenses/by-nc-nd/4.0/.

doi: 10.21037/map-26-ab016
Cite this abstract as: Kelly J, Calpin G, Kelly R, Quinlan M. AB016. SOH26AB_0294. The use of CT radiomics for predicting the malignant potential of residual retroperitoneal masses post-chemotherapy in metastatic testicular cancer: a systematic review and meta-analysis. Mesentery Peritoneum 2026;10:AB016.

Article Options

Download Citation

Share