Semi-automatic software increases CT measurement accuracy but not response classification of colorectal liver
Charlotte S van Kessel1, Maarten S van Leeuwen, Petronella O Witteveen
1Department of Radiology, University Medical Center Utrecht, Heidelberglaan 100, 3584 CX Utrecht, The Netherlands. c.s.vankessel@umcutrecht.nl
Objectives:
This study evaluates intra- and interobserver variability of automatic diameter and volume measurements of colorectal liver metastases (CRLM) before and after chemotherapy and its influence on response classification.
Methods:
Pre-and post-chemotherapy CT-scans of 33 patients with 138 CRLM were evaluated. Two observers measured all metastases three times on pre-and post-chemotherapy CT-scans, using three different techniques: manual diameter (MD), automatic diameter (AD) and automatic volume (AV). RECIST 1.0 criteria were used to define response classification. For each technique, we assessed intra- and interobserver reliability by determining the intraclass correlation coefficient (α-level 0.05). Intra-observer agreement was estimated by the variance coefficient (%). For inter-observer agreement the relative measurement error (%) was calculated using Bland-Altman analysis. In addition, we compared agreement in response classification by calculating kappa-scores (κ) and estimating proportions of discordance between methods (%).
Results:
Intra-observer variability was 6.05%, 4.28% and 12.72% for MD, AD and AV, respectively. Inter-observer variability was 4.23%, 2.02% and 14.86% for MD, AD and AV, respectively. Chemotherapy marginally affected these estimates. Agreement in response classification did not improve using AD or AV (MD κ=0.653, AD κ=0.548, AV κ=0.548) and substantial discordance between observers was observed with all three methods (MD 17.8%, AD 22.2%, AV 22.2%).
Conclusion:
Semi-automatic software allows repeatable and reproducible measurement of both diameter and volume measurements of CRLM, but does not reduce variability in response classification.
