Published in:
01-03-2015 | Computed Tomography
Computer-aided stenosis detection at coronary CT angiography: effect on performance of readers with different experience levels
Authors:
Christian Thilo, Mulugeta Gebregziabher, Felix G. Meinel, Roman Goldenberg, John W. Nance Jr., Elisabeth M. Arnoldi, Lashonda D. Soma, Ullrich Ebersberger, Philip Blanke, Richard L. Coursey, Michael A. Rosenblum, Peter L. Zwerner, U. Joseph Schoepf
Published in:
European Radiology
|
Issue 3/2015
Login to get access
Abstract
Objectives
To evaluate the effect of a computer-aided detection (CAD) algorithm for coronary CT angiography (cCTA) on the performance of readers with different experience levels.
Methods
We studied 50 patients (18 women, 58 ± 11 years) who had undergone cCTA and quantitative coronary angiography (QCA). Eight observers with varying experience levels evaluated all studies for ≥50 % coronary artery stenosis. After 3 months, the same observers re-evaluated all studies, this time guided by a CAD system. Their performance with and without the CAD system (sensitivity, specificity, positive predictive value and negative predictive value) was assessed using the Likelihood Ratio Χ2 test both at the per-patient and per-vessel levels.
Results
The sensitivity of the CAD system alone for stenosis detection was 71 % per-vessel and 100 % per-patient. There were 54 false positive (FP) findings within 199 analyzed vessels, most of them associated with non-obstructive (<50 %) lesions. With CAD, one (out of three, 33 %) inexperienced reader’s per-patient sensitivity and negative predictive value significantly improved from 79 % to 100 % (P = 0.046) and from 90 % to 100 % (P = 0.034), respectively. Other readers’ performance indices showed no statistically significant change.
Conclusions
Our results suggest that CAD can improve some inexperienced readers’ sensitivity for diagnosing coronary artery stenosis at cCTA.
Key Points
• Computer-assisted algorithms can aid in detecting coronary artery stenosis at CT.
• The change in overall diagnostic performance is small across all experience levels.
• For some inexperienced readers a significant increase in sensitivity is observed.