Cardiac

European Radiology

, Volume 20, Issue 5, pp 1160-1167

First online:

Automated computer-aided stenosis detection at coronary CT angiography: initial experience

  • Elisabeth ArnoldiAffiliated withDepartment of Radiology and Radiological Science, Medical University of South CarolinaDepartment of Clinical Radiology, University Hospitals Munich–Grosshadern Campus, Ludwig-Maximilians University
  • , Mulugeta GebregziabherAffiliated withDepartment of Biostatistics, Bioinformatics and Epidemiology, Medical University of South Carolina
  • , U. Joseph SchoepfAffiliated withDepartment of Radiology and Radiological Science, Medical University of South CarolinaDepartment of Medicine, Division of Cardiology, Medical University of South Carolina Email author 
  • , Roman GoldenbergAffiliated withDepartment of Research and Development, Rcadia Medical Imaging Ltd.
  • , Luis Ramos-DuranAffiliated withDepartment of Radiology and Radiological Science, Medical University of South Carolina
  • , Peter L. ZwernerAffiliated withDepartment of Radiology and Radiological Science, Medical University of South CarolinaDepartment of Medicine, Division of Cardiology, Medical University of South Carolina
  • , Konstantin NikolaouAffiliated withDepartment of Clinical Radiology, University Hospitals Munich–Grosshadern Campus, Ludwig-Maximilians University
  • , Maximilian F. ReiserAffiliated withDepartment of Clinical Radiology, University Hospitals Munich–Grosshadern Campus, Ludwig-Maximilians University
  • , Philip CostelloAffiliated withDepartment of Radiology and Radiological Science, Medical University of South Carolina
    • , Christian ThiloAffiliated withDepartment of Radiology and Radiological Science, Medical University of South CarolinaDepartment of Medicine, Division of Cardiology, Medical University of South CarolinaDepartment of Cardiology, Klinikum Augsburg, Herzzentrum Augsburg-Schwaben

Rent the article at a discount

Rent now

* Final gross prices may vary according to local VAT.

Get Access

Abstract

Objective

To evaluate the performance of a computer-aided algorithm for automated stenosis detection at coronary CT angiography (cCTA).

Methods

We investigated 59 patients (38 men, mean age 58 ± 12 years) who underwent cCTA and quantitative coronary angiography (QCA). All cCTA data sets were analyzed using a software algorithm for automated, without human interaction, detection of coronary artery stenosis. The performance of the algorithm for detection of stenosis of 50% or more was compared with QCA.

Results

QCA revealed a total of 38 stenoses of 50% or more of which the algorithm correctly identified 28 (74%). Overall, the automated detection algorithm had 74%/100% sensitivity, 83%/65% specificity, 46%/58% positive predictive value, and 94%/100% negative predictive value for diagnosing stenosis of 50% or more on per-vessel/per-patient analysis, respectively. There were 33 false positive detection marks (average 0.56/patient), of which 19 were associated with stenotic lesions of less than 50% on QCA and 14 were not associated with an atherosclerotic surrogate.

Conclusion

Compared with QCA, the automated detection algorithm evaluated has relatively high accuracy for diagnosing significant coronary artery stenosis at cCTA. If used as a second reader, the high negative predictive value may further enhance the confidence of excluding significant stenosis based on a normal or near-normal cCTA study.

Keywords

Coronary artery disease Coronary artery stenosis Computed tomography Computer-aided detection Computer-aided diagnosis