AI-based tumor and organ volumetry predicts early progression after Y-90 radioembolization in liver-dominant metastatic disease.
Authors
Affiliations (10)
Affiliations (10)
- School of Medicine and Health, Department of Diagnostic and Interventional Neuroradiology, Technical University of Munich, TUM University Hospital, Munich, Germany. [email protected].
- School of Medicine and Health, Department of Diagnostic and Interventional Neuroradiology, Technical University of Munich, TUM University Hospital, Munich, Germany.
- Department of Diagnostic and Interventional Radiology and Nuclear Medicine, University Medical Center Hamburg-Eppendorf, Hamburg, Germany.
- School of Medicine and Health, Department of Radiology, Technical University of Munich, TUM University Hospital, Munich, Germany.
- Chair for AI in Healthcare and Medicine, Technical University of Munich (TUM), TUM University Hospital, Munich, Germany.
- TUM School of Medicine and Health, Clinical Department of Internal Medicine II, TUM University Hospital, Munich, Germany.
- Department of Surgery, Klinikum Rechts der Isar, School of Medicine and Health, Technical University of Munich, Munich, Germany.
- School of Medicine and Health, Department of Nuclear Medicine, Technical University of Munich, TUM University Hospital Munich, Munich, Germany.
- Bavarian Cancer Research Center (BZKF), Erlangen, Germany.
- Partner Site Munich, A Partnership between DKFZ and School of Medicine, German Cancer Consortium (DKTK), Technical University of Munich, Munich, Germany.
Abstract
In patients with liver-dominant metastatic disease undergoing yttrium-90 (⁹⁰Y) transarterial radioembolization (TARE), response assessment remains challenging, particularly in multifocal disease where manual RECIST-based measurements may not adequately reflect overall hepatic tumor burden. In addition, the prognostic relevance of volumetric changes in tumor, liver, and spleen after TARE remains unclear. This retrospective study evaluated automated CT-based whole-liver tumor volumetry as a quantitative imaging biomarker for response assessment and progression risk stratification following TARE. We retrospectively analyzed imaging and clinical data from 57 adults with liver-dominant metastatic disease (colorectal, neuroendocrine, uveal melanoma, and breast cancer) treated with yttrium-90 (⁹⁰Y) resin TARE between January 2012 and December 2022. Inclusion criteria were age ≥ 18 years, availability of baseline contrast-enhanced CT imaging, and clinical follow-up. Patients undergoing liver resection, transplantation, or additional locoregional therapies during follow-up were excluded. Baseline tumor volume was a strong independent predictor of progression-free survival (PFS), demonstrating excellent discriminatory performance (ROC-AUC 0.91; 95% CI 0.82-1.00). A threshold of 270 mL most accurately identified early progression (< 12 months), with a sensitivity of 0.84 and specificity of 0.92. In contrast, lesion count, embolization strategy, and maximum tumor diameter were not significantly associated with PFS. Automated baseline tumor volumetry demonstrated promising prognostic performance compared with conventional clinical and procedural parameters in patients with liver-dominant metastases treated with ⁹⁰Y TARE. Automated quantification of intrahepatic tumor burden may serve as a useful and readily accessible imaging biomarker for early risk stratification, although external validation is required before clinical implementation.