Evaluation of Local Tumor Outcomes Following Microwave Ablation of Colorectal Liver Metastases Using CT Imaging: A Comparison of Visual versus Quantitative Methods.

Abstract

Purpose To compare visual versus quantitative ablation confirmation for identifying local tumor progression and residual tumor following microwave ablation (MWA) of colorectal liver metastases (CRLM). Materials and Methods This retrospective study included patients undergoing MWA of CRLM from October 2014 to February 2018. Two independent readers visually assessed pre- and postprocedure images and semiquantitatively scored for incomplete ablation, using a six-point Likert scale, and extracted quantitative imaging metrics of minimal ablative margin (MAM) and percentage of tumor outside of the ablation zone, using both rigid and deformable registration. Diagnostic accuracy and intra- and interobserver agreement were assessed. Results The study included 60 patients (median age, 71 years [IQR, 60-74.5 years]; 38 male) with 97 tumors with a median diameter of 1.3 cm (IQR, 1.0-1.8 cm). Median follow-up time was 749 days (IQR, 330-1519 days). Median time to complete rigid and deformable workflows was 3.0 minutes (IQR, 3.0-3.2 minutes) and 14.0 minutes (IQR,13.9-14.4 minutes), respectively. MAM with deformable registration had the highest intra- and interobserver agreement, with Gwet AC1 of 0.92 and 0.67, respectively, significantly higher than interobserver agreement of visual assessment (Gwet AC1, 0.18; P < .0001). Overall, quantitative methods using MAM had generally higher sensitivity, of up to 95.6%, than visual methods (67.3%, P < .001), at a cost of lower specificity (40% vs 71.1%, P < .001), using deformable image registration. Conclusion Quantitative ablation margin metrics provide more reliable assessment of outcomes than visual comparison using pre- and postprocedure diagnostic images following MWA of CRLM. Keywords: Interventional-Body, Liver, Neoplasms, Ablation Techniques Supplemental material is available for this article. Published under a CC BY 4.0 license.