Fully automatic model-based calcium segmentation and scoring in coronary CT angiography.

PURPOSE: The paper presents new methods for automatic coronary calcium detection, segmentation and scoring in coronary CT angiography (cCTA) studies. METHODS: Calcium detection and segmentation are performed by modeling image intensity profiles of coronary arteries. The scoring algorithm is based on a simulated unenhanced calcium score (CS) CT image, constructed by virtually removing the contrast media from cCTA. The methods are implemented as part of a fully automatic system for CS assessment from cCTA. RESULTS: The system was tested in two independent clinical trials on 263 studies and demonstrated 0.95/0.91 correlation between the CS computed from cCTA and the standard Agatston score derived from unenhanced CS CT. The mean absolute percent difference (MAPD) of 36/39 % between the two scores lies within the error range of the standard CS CT (15-65 %). CONCLUSIONS: High diagnostic performance, combined with the benefits of the fully automatic solution, suggests that the proposed technique can be used to eliminate the need in a separate CS CT scan as part of the cCTA examination, thus reducing the radiation exposure and simplifying the procedure.

Fully automated derivation of coronary artery calcium scores and cardiovascular risk assessment from contrast medium-enhanced coronary CT angiography studies.

OBJECTIVES: Performance evaluation of a fully automated system for calculating computed tomography (CT) coronary artery calcium scores from contrast medium-enhanced coronary CT angiography (cCTA) studies. METHODS: One hundred and twenty-seven patients (58 ± 11 years, 71 men) who had undergone cCTA as well as an unenhanced CT calcium scoring study where included. Calcium scores were computed from cCTA by an automated image processing algorithm and compared with calcium scores obtained by standard manual assessment of unenhanced CT calcium scoring studies. Results were compared vis-a-vis (1) absolute calcium score values, (2) age-, gender- and race-dependent percentiles, and (3) commonly used calcium score risk classification categories. RESULTS: One hundred and nineteen out of 127 (93.7%) studies were successfully processed. Mean Agatston calcium score values obtained by traditional non-contrast CT calcium scoring studies and derived from contrast medium-enhanced cCTA did not significantly differ (235.6 ± 430.5 vs 262.0 ± 499.5; P > 0.05). Calcium score risk categories and Multi-Ethnic Study of Atherosclerosis (MESA) percentiles showed very high correlation (Spearman rank correlation coefficient = 0.97, P < 0.0001/0.95, P < 0.0001) between the two approaches. CONCLUSIONS: Calcium score values automatically computed from cCTA are highly correlated with standard unenhanced CT calcium scoring studies. These results suggest a radiation dose- and time-saving potential when deriving calcium scores from cCTA studies without a preceding unenhanced CT calcium scoring study.

Computer-aided simple triage (CAST) for coronary CT angiography (CCTA).

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.

Computer-aided simple triage.

PURPOSE: Computer-aided detection (CAD) established its role in medical imaging as second reader aimed to boost the diagnostic accuracy of human interpreter. As the diagnostic performance of CAD systems improves and more imaging modalities are covered, CAD steps forward to fill new, more demanding positions in medical practice. In this paper, we investigate how the introduction of CAD for emergency diagnostic imaging shifts the use case paradigm from second reader to initial interpreter and triage tool. METHODS: We start from extracting common characteristics of exiting CAD systems and compare them to those for emergency diagnostic imaging modalities. Based on the deduced requirements, we define a new class of CAD systems-Computer-aided simple triage (CAST) and explore its properties, use case scenarios and clinical benefits. We also discuss the differences between the CAST, CAD, and automated computer diagnosis. RESULTS: A CAST system should serve as a simple triage tool performing a fully automatic analysis and providing initial classification at "per study" level. Positive studies are then immediately analyzed by expert reader, thus reducing delay for patients with critical conditions, while negative studies can be initially dealt with by less experienced staff. Automatic image quality and study complexity assessment can serve as reading prioritization key. CAST system should exhibit sufficiently high specificity, while not compromising the high sensitivity per study. CONCLUSIONS: CAST systems have a potential to become an "enabling technology" allowing introduction of advanced imaging techniques into the emergency workflow protocols by addressing the reader unavailability and reading prioritization problems.