Abstract
Purpose
Following a recent introduction of computer-aided simple triage (CAST) as a new subclass of computer-aided detection/diagnosis (CAD), we present a CAST software system for a fully automatic initial interpretation of coronary CT angiography (CCTA). We show how the system design and diagnostic performance make it CAST-compliant and suitable for chest pain patient triage in emergency room (ER).
Methods
The processing performed by the system consists of three major steps: segmentation of coronary artery tree, labeling of major coronary arteries, and detection of significant stenotic lesions (causing > 50% stenosis). In addition, the system performs an automatic image quality assessment to discards low-quality studies. For multiphase studies, the system automatically chooses the best phase for each coronary artery. Clinical evaluation results were collected in 14 independent trials that included more than 2000 CCTA studies. Automatic diagnosis results were compared with human interpretation of the CCTA and to cath lab results.
Results
The presented system performs a fully automatic initial interpretation of CCTA without any human interaction and detects studies with significant coronary artery disease. The system demonstrated higher than 90% per patient sensitivity and 40–70% per patient specificity. For the chest pain, ER population, the specificity was 60–70%, yielding higher than 98% NPV.
Conclusions
The diagnostic performance of the presented CCTA CAD system meets the CAST requirements, thus enabling efficient, 24/7 utilization of CCTA for chest pain patient triage in ER. This is the first fully operational, clinically validated, CAST-compliant CAD system for a fully automatic analysis of CCTA and detection of significant stenosis.
Similar content being viewed by others
References
Goldenberg R, Peled N (2011) Computer aided simple triage. Int J Comput Assist Radiol Surg 6(5): 705–711
Gallagher M et al (2007) The diagnostic accuracy of 64-Slice computed tomography coronary angiography compared with stress nuclear imaging in emergency department low-risk chest pain patients. Ann Emerg Med 49(2): 125–136
Hulten E, Carbonaro S, Petrillo S, Mitchell J, Villines T (2011) Prognostic value of cardiac computed tomography angiography: a systematic review and meta-analysis. J Am Coll Cardiol 57: 1237–1247
Goldstein J, Gallagher M, O’Neill W, Ross M, O’Neil B, Raff G (2007) A randomized controlled trial of multi-slice coronary computed tomography for evaluation of acute chest pain. J Am Coll Cardiol 49: 863–871
Anderson J, Adams C, Antman E et al (2007) ACC/AHA 2007 guidelines for the management of patients with unstable angina/non-ST-Elevation myocardial infarction: a report of the American college of cardiology. J Am Coll Cardiol 50(7): e1–e157
Hendel R, Patel M, Kramer C et al (2006) ACCF/ACR/SCCT/ SCMR/ASNC/NASCI/SCAI/SIR 2006 appropriateness criteria for cardiac computed tomography and cardiac magnetic resonance imaging: a report of the American college of cardiology foundation quality strategic directions committee. J Am Coll Cardiol 48(7): 1475–1497
Duda RO, Hart PE (1972) Use of the Hough transform to detect lines and curves in pictures. Commun ACM 15(1): 11–15
Hough V, Paul C (1962) Methods and means for recognizing complex patterns. U.S. Patent 3069654
Goldenberg R, Kimmel R, Rivlin E, Rudzsky M (2001) Fast geodesic active contours. IEEE Trans Image Proces 10(10): 1467–1475
Laguitton S, Grady L, Lesage D, Funka-lea G (2008) Automatic coronary tree modeling. Blood Vessel Midas J. http://hdl.handle.net/10380/1426
Frangi AF, Niessen WJ, Vincken KL, Viergever MA (1998) Multiscale vessel enhancement filtering. In: MICCAI’98, Cambridge, MA
Lucas E (1882) Récréations mathématiques, vol I. Gauthier-Villars et fils, Imprimeurs-Libraires, Paris
Begelman G, Goldenberg R, Levanon S, Ohayon S, Walach E (2011) Creating a blood vessel tree from imaging data. United States Patent 7,983,459
Kirbas C, Quek FKH (2004) A review of vessel extraction techniques and algorithms. ACM Comput Surv 36(2): 81–121
Lesage D, Angelini ED, Bloch I, Funka-Lea G (2009) A review of 3D vessel lumen segmentation techniques: models, features and extraction schemes. Med Image Anal 13(6): 819–845
Zhang X, Collins S, Sonka M (1995) Tree pruning strategy in automated detection of coronary trees in cineangiograms. In: International conference on image processing, Washington
Kelm B, Mittal S, Zheng Y, Tsymbal A, Bernhardt D, Vega-Higuera F, Zhou S, Meer P, Comaniciu D (2011) Detection, grading and classification of coronary stenoses in computed tomography angiography. In: MICCAI’11, Toronto
Yang G, et al (2011) Automatic labeling of coronary artery tree in CCTA. In: Computing in cardiology, Hangzhou
Kanitsar A, Fleischmann D, Wegenkittl R, Gröller ME (2005) Diagnostic relevant visualization of vascular structures. In: Scientific visualization: the visual extraction of knowledge from data. Springer, pp 207–228
Xu C, Prince JL (1998) Snakes, shapes, and gradient vector flow. IEEE Trans Image Proces 7(3): 359–369
Chan TF, Vese LA (2001) Active contours without edges. IEEE Trans Image Proces 10(2): 266–277
Begelman G, Goldenberg R, Levanon S, Ohayon S, Walach E (2011) Method and system for automatic analysis of blood vessel structures to identify calcium or soft plaque pathologies. United States Patent 7,940,977
Zadeh L (1965) Fuzzy sets. Inf Control 8(3): 338–353
Dey D, Schepis T, Marwan M, Slomka P, Berman D, Achenbach S (2010) Automated three-dimensional quantification of noncalcified coronary plaque from coronary CT angiography: comparison with intravascular US. Radiology 257(2): 516–522
Wang Y, Liatsis P (2009) A fully automated framework for segmentation and stenosis quantification of coronary arteries in 3D CTA imaging. In: Second International Conference on Developments in eSystems Engineering Abu Dhabi
Cline HE, Krishnan K, Napel S, Rubin GD, Turner WD, Avila RS (2009) Automated coronary CT angiography plaque-lumen segmentation. Proc SPIE Med Imaging 7260: 726003–72600310
Boogers MJ et al (2010) Automated quantification of stenosis severity on 64-slice CT: a comparison with quantitative coronary angiography. JACC Cardiovasc imaging 3(7): 699–709
Rinck D, Kruger S, Reimann A, Scheuering M (2006) Shape-based segmentation and visualization techniques for evaluation of atherosclerotic plaques in coronary artery disease. Proc SPIE Int Soc Opt Eng 6141: 61410G–61410G-9
Levanon S, Goldenberg R, Levy M (2011) Method and system for automatic quality control used in computerized analysis of CT angiography. United States Patent 7,940,970
Weisman J, Yuz M (2008) Fully automated coronary CTA analysis. In: SCCT’08, Orlando
Lopez C, Weissman G, Joshi S, Weigold W (2008) Automatic computerized evaluation of 64 multislice coronary CTA. A comparison between COR Analyzer II software and visual evaluation. In: SCCT’08, Orlando
Poon M (2009) The role of computed aided diagnosis in the management of acute chest pain. In: SCCT’09, Orlando
Malhotra V (2009) COR analyzer diagnostic performance analysis. In: SCCT’09, Orlando
Tyagi G, et al (2009) Segmental accuracy of an automated analyzer of coronary CT angiography (CCTA) in ED patients: (initial experience). In: RSNA’09, Chicago
Arnoldi E, Gebregziabher M, Schoepf U, Goldenberg R, Ramos-Duran L, Zwerner P, Nikolaou K, Reiser M, Costello P, Thilo C (2010) Automated computer-aided stenosis detection at coronary CT angiography: initial experience. Eur Radiol 20(5): 1160–1167
Daubert M, Malhotra V, Ferraro S, Goldenberg R, Kam M, Wu H, Kam D, Minton A, Poon M (2010) Computer-aided analysis of 64-slice coronary computed tomography angiography: a comparison with manual interpretation. In: SCCT’10, Las Vegas
Malhotra V, Poon M, Krishnan U, Mcnerthney M, Goldenberg R, WN (2010) Computer aided detection for coronary CT angiography in low to intermediate risk population. In: SCCT’10, Las Vegas
Mehta C, et al (2010) Validation of an automated cardiac CT angiography analysis system: initial experience at an academic center. In: SCCT’10, Las Vegas
Anders K, Petit I, Achenbach S, Pflederer T (2010) Diagnostic utility of automated stenosis detection in dual source CT coronary angiography as a stand alone or add-on tool. In: SCCT’10, Las Vegas
Halpern E, Halpern D (2010) Diagnosis of coronary stenosis with CT angiography: comparison of automated computer diagnosis with expert readings. Acad Radiol 18(3): 324–333
Henzler T, Meyer M, Apfaltrer P, Schönberg S, Fink C (2012) Computed-aided stenosis detection on coronary CT angiography in chest pain patients with an intermediate pre-test likelihood for acute coronary syndrome. In: ECR’12, Vienna
Kang K, Chang H, Shim H, Kim Y, Choi B, Yang W, Shim J, Ha J, Chung N (2012) Feasibility of an automatic computer-assisted algorithm for the detection of significant coronary artery disease in patients presenting with acute chest pain. Eur J Radiol 81(4): e640–e646
Schaap M, Metz C et al (2009) Standardized evaluation methodology and reference database for evaluating coronary artery centerline extraction algorithms. Med Image Anal 13(5): 701–714
Rotterdam Coronary Artery Algorithm Evaluation Framework, Biomedical Imaging Group Rotterdam, [Online]. Available: http://coronary.bigr.nl/centerlines/results/results.php
Sansoni E, Schoepf U, Nance J, Barraza J, Henzler T, Deml K (2010) Computer aided detection of coronary artery disease in the CT-based triage of acute chest pain patients—validation by patient outcome. In: RSNA’10, Chicago
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Goldenberg, R., Eilot, D., Begelman, G. et al. Computer-aided simple triage (CAST) for coronary CT angiography (CCTA). Int J CARS 7, 819–827 (2012). https://doi.org/10.1007/s11548-012-0684-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11548-012-0684-7