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.
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 painpatient 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 painpatient 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.
Authors: Edward A Hulten; Salvatore Carbonaro; Sara P Petrillo; Joshua D Mitchell; Todd C Villines Journal: J Am Coll Cardiol Date: 2010-12-08 Impact factor: 24.094
Authors: Robert C Hendel; Manesh R Patel; Christopher M Kramer; Michael Poon; Robert C Hendel; James C Carr; Nancy A Gerstad; Linda D Gillam; John McB Hodgson; Raymond J Kim; Christopher M Kramer; John R Lesser; Edward T Martin; Joseph V Messer; Rita F Redberg; Geoffrey D Rubin; John S Rumsfeld; Allen J Taylor; Wm Guy Weigold; Pamela K Woodard; Ralph G Brindis; Robert C Hendel; Pamela S Douglas; Eric D Peterson; Michael J Wolk; Joseph M Allen; Manesh R Patel Journal: J Am Coll Cardiol Date: 2006-10-03 Impact factor: 24.094
Authors: James A Goldstein; Michael J Gallagher; William W O'Neill; Michael A Ross; Brian J O'Neil; Gilbert L Raff Journal: J Am Coll Cardiol Date: 2007-02-12 Impact factor: 24.094
Authors: Mark J Boogers; Joanne D Schuijf; Pieter H Kitslaar; Jacob M van Werkhoven; Fleur R de Graaf; Eric Boersma; Joëlla E van Velzen; Jouke Dijkstra; Isabel M Adame; Lucia J Kroft; Albert de Roos; Joop H M Schreur; Mark W Heijenbrok; J Wouter Jukema; Johan H C Reiber; Jeroen J Bax Journal: JACC Cardiovasc Imaging Date: 2010-07
Authors: Jeffrey L Anderson; Cynthia D Adams; Elliott M Antman; Charles R Bridges; Robert M Califf; Donald E Casey; William E Chavey; Francis M Fesmire; Judith S Hochman; Thomas N Levin; A Michael Lincoff; Eric D Peterson; Pierre Theroux; Nanette Kass Wenger; R Scott Wright; Sidney C Smith; Alice K Jacobs; Cynthia D Adams; Jeffrey L Anderson; Elliott M Antman; Jonathan L Halperin; Sharon A Hunt; Harlan M Krumholz; Frederick G Kushner; Bruce W Lytle; Rick Nishimura; Joseph P Ornato; Richard L Page; Barbara Riegel Journal: J Am Coll Cardiol Date: 2007-08-14 Impact factor: 24.094
Authors: Dongwoo Kang; Damini Dey; Piotr J Slomka; Reza Arsanjani; Ryo Nakazato; Hyunsuk Ko; Daniel S Berman; Debiao Li; C-C Jay Kuo Journal: J Med Imaging (Bellingham) Date: 2015-03-06
Authors: Ullrich Ebersberger; Dov Eilot; Roman Goldenberg; Alon Lev; J Reid Spears; Garrett W Rowe; Nicholas Y Gallagher; William T Halligan; Philipp Blanke; Marcus R Makowski; Aleksander W Krazinski; Justin R Silverman; Fabian Bamberg; Alexander W Leber; Ellen Hoffmann; U Joseph Schoepf Journal: Eur Radiol Date: 2012-09-16 Impact factor: 5.315
Authors: Alessandro Jatoba; Catherine Marie Burns; Mario Cesar Rodriguez Vidal; Paulo Victor Rodrigues Carvalho Journal: JMIR Hum Factors Date: 2016-08-15