Non-invasive visualization of coronary atherosclerosis: state-of-art

Continuous extraction of coronary artery centerline from cardiac CTA images using a regression-based method

Coronary artery centerline extraction in cardiac computed tomography angiography (CTA) is an effectively non-invasive method to diagnose and evaluate coronary artery disease (CAD). The traditional method of manual centerline extraction is time-consuming and tedious. In this study, we propose a deep learning algorithm that continuously extracts coronary artery centerlines from CTA images using a regression method. In the proposed method, a CNN module is trained to extract the features of CTA images, and then the branch classifier and direction predictor are designed to predict the most possible direction and lumen radius at the given centerline point. Besides, a new loss function is developed for associating the direction vector with the lumen radius. The whole process starts from a point manually placed at the coronary artery ostia, and terminates until tracking the vessel endpoint. The network was trained using a training set consisting of 12 CTA images and the evaluation was performed using a testing set consisting of 6 CTA images. The extracted centerlines had an average overlap (OV) of 89.19%, overlap until first error (OF) of 82.30%, and overlap with clinically relevant vessel (OT) of 91.42% with manually annotated reference. Our proposed method can efficiently deal with multi-branch problems and accurately detect distal coronary arteries, thereby providing potential help in assisting CAD diagnosis.

Machine learning for diagnosis of coronary artery disease in computed tomography angiography: A survey

Coronary artery disease (CAD) has become a major illness endangering human health. It mainly manifests as atherosclerotic plaques, especially vulnerable plaques without obvious symptoms in the early stage. Once a rupture occurs, it will lead to severe coronary stenosis, which in turn may trigger a major adverse cardiovascular event. Computed tomography angiography (CTA) has become a standard diagnostic tool for early screening of coronary plaque and stenosis due to its advantages in high resolution, noninvasiveness, and three-dimensional imaging. However, manual examination of CTA images by radiologists has been proven to be tedious and time-consuming, which might also lead to intra- and interobserver errors. Nowadays, many machine learning algorithms have enabled the (semi-)automatic diagnosis of CAD by extracting quantitative features from CTA images. This paper provides a survey of these machine learning algorithms for the diagnosis of CAD in CTA images, including coronary artery extraction, coronary plaque detection, vulnerable plaque identification, and coronary stenosis assessment. Most included articles were published within this decade and are found in the Web of Science. We wish to give readers a glimpse of the current status, challenges, and perspectives of these machine learning-based analysis methods for automatic CAD diagnosis.

Geometrical force constraint method for vessel and x-ray angiogram simulation

This study proposes a novel geometrical force constraint method for 3-D vasculature modeling and angiographic image simulation. For this method, space filling force, gravitational force, and topological preserving force are proposed and combined for the optimization of the topology of the vascular structure. The surface covering force and surface adhesion force are constructed to drive the growth of the vasculature on any surface. According to the combination effects of the topological and surface adhering forces, a realistic vasculature can be effectively simulated on any surface. The image projection of the generated 3-D vascular structures is simulated according to the perspective projection and energy attenuation principles of X-rays. Finally, the simulated projection vasculature is fused with a predefined angiographic mask image to generate a realistic angiogram. The proposed method is evaluated on a CT image and three generally utilized surfaces. The results fully demonstrate the effectiveness and robustness of the proposed method.

Normal anatomy and variants of the venous cardiac system in MDCT coronary angiography

Three separate venous systems drain the blood returning from the heart walls. These veins are characterised by remarkable variability in terms of frequency, size and course. The knowledge of cardiac venous anatomy is of primary importance during interventional cardiac procedures that require catheterisation of cardiac veins. Some anatomical variants may hinder or contraindicate access to target veins. Coronary angiography (CA) with multidetector computed tomography (MDCT-CA) and multiplanar reformations (MPR), maximum intensity projection (MIP) and 3D reconstructions provides noninvasive visualisation of normal cardiac veins and anatomical variants. The purpose of this pictorial review is to describe by MDCT-CA the anatomy and main variants of the cardiac venous system.

Role of MDCT coronary angiography in the clinical setting: economic implications

PURPOSE

This study evaluated the incremental value and cost-effectiveness ratio of introducing coronary angiography (CA) with multidetector computed tomography (MDCT-CA) in the diagnostic management of patients with suspected coronary artery disease (CAD) compared with the traditional diagnostic workup.

MATERIAL AND METHODS

Five hundred and fifty consecutive patients who underwent MDCT-CA between January 2009 and June 2011 were considered. Patients with atypical chest pain and suspected obstructive CAD were directed to one of two diagnostic pathways: the traditional protocol (examination, stress test, CA) and the current protocol (examination, stress test, MDCT-CA, and CA, if necessary). The costs of each protocol and for the individual method were calculated. Based on the results, the cost-effectiveness ratio of the two diagnostic pathways was compared. A third, modified, diagnostic pathway has been proposed with its relative cost-effectiveness ratio (examination, MDCT-CA, stress test, and CA, if necessary).

RESULTS

Stress test vs. MDCT-CA had an accuracy of 66%, a sensitivity and specificity of 21% and 87%, respectively, and a positive (PPV) and negative (NPV) predictive value of 40% and 70%, respectively. Comparison between conventional CA (CCA) and MDCT-CA showed a sensitivity and specificity of 92% and 89%, respectively, a PPV and NPV of 89%, and an accuracy of 92%. The traditional protocol has higher costs than the second protocol: 1,645 euro against 322 euro (mean), but it shows a better cost-effectiveness ratio. The new proposed protocol has lower costs, mean 261 euro, with a better costeffectiveness ratio than the traditional protocol.

CONCLUSIONS

The diagnostic protocol for patients with suspected CAD has been modified by the introduction of MDCT-CA. Our study confirms the greater diagnostic performance of MDCT-CA compared with stress test and its similar accuracy to CCA. The use of MDCT-CA to select patients for CCA has a favourable cost-effectiveness profile.

Role of coronary angiography MDCT in the clinical setting: changes in diagnostic workup in the real world

PURPOSE

The authors sought to evaluate the incremental value of introducing coronary angiography with multidetector computed tomography (MDCT-CA) compared with the conventional diagnostic workup in managing patients with suspected coronary artery disease (CAD) workup.

MATERIALS AND METHODS

A total of 531 consecutive patients underwent MDCT-CA between April 2008 and August 2010. For each patient the pretest probability of CAD was obtained by using the Morise score as well as the diagnostic performance of the exercise test and of MDCT-CA, considering conventional coronary angiography (CCA) as the gold standard. Based on these results, we calculated the posttest likelihood of CAD after stress testing, comparing the incremental diagnostic value for each category of cardiovascular risk with data obtained with MDCT-CA. The conventional diagnostic workup (without MDCT-CA) was then compared with the modified workup (including MDCT-CA).

RESULTS

The diagnostic performance of the exercise test for identifying patients with significant lesions had a sensitivity and specificity of 20% and 88%, respectively, with positive (PPV) and negative (NPV) predictive value of 41% and 72%, respectively. Taking CA as the gold standard, MDCT-CA had 93% sensitivity, 89% specificity, 88% PPV and 93% NPV compared with CCA in evaluating significant stenoses in the per-patient analysis. The overall diagnostic accuracy of MDCT-CA was 91%. The exercise tests provided no significant incremental diagnostic value compared with cardiovascular history in patients with a low to intermediate risk. Comparison of the diagnostic accuracy of these protocols showed improved performance results for the modified protocol.

CONCLUSIONS

MDCT-CA is the reference modality for the noninvasive exclusion of critical CAD. It provides a very high incremental diagnostic value compared with exercise testing in patients with a low to intermediate risk of CAD. The use of diagnostic protocols based on MDCT-CA ensures improved diagnostic performance compared with those involving conventional exercise electrocardiograms.

Relation of coronary plaque composition determined by 64-slice multidetector computed tomography in patients with suspected coronary heart disease

Sixty-four-slice multidetector row computed tomography is a noninvasive method of assessing coronary artery stenosis and plaque composition. The aim of this study was to clarify the relation between plaque composition and coronary heart disease. Three hundred sixty consecutive patients and 1,085 plaques were evaluated using 64-slice multidetector row computed tomography. On axial or cross-sectional multiplanar reconstruction images, 3 regions of interest were randomly selected within each plaque. Soft plaques and calcified plaques were defined as having computed tomographic densities <50 and >130 Hounsfield units, respectively. The association between coronary risk factors and plaque composition was analyzed. The number of plaques and the mean computed tomographic density of plaques were significantly higher in men than in women (p = 0.002 and p = 0.04, respectively). Coronary plaques were more frequent in patients with stroke, diabetes, hypertension, and dyslipidemia than in patients without these conditions (all p values <0.001). Calcified plaques were more frequent in patients with hypertension (p = 0.02), and patients with calcified plaques also had significantly lower low-density lipoprotein cholesterol levels (p <0.001). Soft plaques were more frequent in patients with dyslipidemia (p <0.001). Patients with soft plaques had significantly higher low-density lipoprotein cholesterol levels (p = 0.02) and lower high-density lipoprotein cholesterol levels (p <0.001) than those without soft plaques. In conclusion, 64-slice multidetector row computed tomography is a useful noninvasive method for quantifying coronary plaques.

Relationship between obstructive coronary artery disease and abnormal stress testing in patients with paroxysmal or persistent atrial fibrillation

Atrial fibrillation (AF) has been linked to the presence of underlying coronary artery disease (CAD). However, whether the higher burden of CAD observed in AF patients translates into higher burden of myocardial ischemia is unknown. In 87 patients (71% male, mean age 61 ± 10 years) with paroxysmal or persistent AF and without history of CAD, MSCT coronary angiography and stress testing (exercise ECG test or myocardial perfusion imaging) were performed. CAD was classified as obstructive (≥50% luminal narrowing) or not. Stress tests were classified as normal or abnormal. A population of 122 patients without history of AF, similar to the AF group as to age, gender, symptomatic status and pre-test likelihood, served as a control group. Based on MSCT, 17% of AF patients were classified as having no CAD, whereas 43% showed non-obstructive CAD and the remaining 40% had obstructive CAD. A positive stress test was observed in 49% of AF patients with obstructive CAD. Among non-AF patients, 34% were classified as having no CAD, while 41% showed non-obstructive CAD and 25% had obstructive CAD (P = 0.013 compared to AF patients). A positive stress test was observed in 48% of non-AF patients with obstructive CAD. In conclusion, the higher burden of CAD observed in AF patients is not associated to higher burden of myocardial ischemia.

Quantification of calcifications in endarterectomy samples by means of high-resolution ultra-short echo time imaging

OBJECTIVE

Magnetic resonance imaging (MRI) has proven its value for noninvasive assessment and classification of atherosclerotic lesions. MRI provides excellent access to soft tissue information, but its capability for assessing calcified segments of the lesion remains limited. The aim of this study was to investigate the ultra-short echo time (UTE) sequence for accurate quantification of the plaque volumes and qualitative assessment of the calcium density.

MATERIAL AND METHODS

Images of 35 endarterectomy samples were acquired by a high-resolution UTE sequence (TE = 50 micros) technique and compared with the conventional gradient echo (fast field echo) approach, volume computed tomography, and histology.

RESULTS

The UTE technique yielded accurate quantification of the volume of the calcification as well as enabled qualitative assessment of the calcium density according to the resulting relative signal intensity. In comparison, the fast field echo technique yielded an average overestimation of the lesion size by about 35% and the low signal intensity did not allow a clear delineation of the different calcium densities.

CONCLUSIONS

The presented data provide evidence that incorporation of the UTE technique in today's MRI protocols for plaque classification holds the potential to add the missing important information on calcium volume and density solely based on MRI data.

Coronary centerline extraction from CT coronary angiography images using a minimum cost path approach

PURPOSE

The application and large-scale evaluation of minimum cost path approaches for coronary centerline extraction from computed tomography coronary angiography (CTCA) data and the development and evaluation of a novel method to reduce the user-interaction time.

METHODS

A semiautomatic method based on a minimum cost path approach is evaluated for two different cost functions. The first cost function is based on a frequently used vesselness measure and intensity information, and the second is a recently proposed cost function based on region statistics. User interaction is minimized to one or two mouse clicks distally in the coronary artery. The starting point for the minimum cost path search is automatically determined using a newly developed method that finds a point in the center of the aorta in one of the axial slices. This step ensures that all computationally expensive parts of the algorithm can be precomputed.

RESULTS

The performance of the aorta localization procedure was demonstrated by a success rate of 100% in 75 images. The success rate and accuracy of centerline extraction was quantitatively evaluated on 48 coronary arteries in 12 images by comparing extracted centerlines with a manually annotated reference standard. The method was able to extract 88% and 47% of the vessel center-lines correctly using the vesselness/intensity and region statistics cost function, respectively. For only the proximal part of the vessels these values were 97% and 86%, respectively. Accuracy of centerline extraction, defined as the average distance from correctly automatically extracted parts of the centerline to the reference standard, was 0.64 mm for the vesselness/intensity and 0.51 mm for the region statistics cost function. The interobserver variability was 99% for the success rate measure and 0.42 mm for the accuracy measure. Qualitative evaluation using the best performing cost function resulted in successful centerline extraction for 233 out of the 252 coronaries (92%) in 63 additional CTCA images.

CONCLUSIONS

The presented results, in combination with minimal user interaction and low computation time, show that minimum cost path approaches can effectively be applied as a preprocessing step for subsequent analysis in clinical practice and biomedical research.

Relation between Framingham risk categories and the presence of functionally relevant coronary lesions as determined on multislice computed tomography and stress testing

Noninvasive assessment of subclinical atherosclerosis by multislice computed tomographic (MSCT) coronary angiography and demonstration of significant, flow-limiting coronary artery disease (CAD) by stress testing may improve patients' risk stratification. However, data relating the complementary information provided by these noninvasive techniques to traditional risk assessment are scarce. In 255 subjects (45% women, mean age 54 +/- 12 years) without known CAD, 64-slice MSCT coronary angiography and stress testing (exercise electrocardiographic test or myocardial perfusion imaging) were performed. Framingham risk score (FRS) was calculated from baseline characteristics (50% low, 22% intermediate, 28% high). Angiograms showing atherosclerosis were classified as obstructive (> or =50% luminal narrowing) CAD or not. Stress tests were classified as normal or abnormal. Multislice computed tomogram identified 155 patients (61%) with CAD, of whom 78 (31%) showed obstructive CAD. A positive stress test result was observed in 36 patients (46%) with obstructive CAD. In line with increasing FRS categories, a significant increase in the prevalence of functionally relevant obstructive CAD was observed (6% low vs 45% intermediate vs 63% high, p <0.001). In conclusion, a strong positive relation exists between FRS and prevalence of functionally relevant obstructive CAD. Selective use of MSCT coronary angiography and stress testing may refine the traditional risk assessment of CAD events, especially in patients deemed at intermediate and high risk.

Standardized evaluation methodology and reference database for evaluating coronary artery centerline extraction algorithms

Efficiently obtaining a reliable coronary artery centerline from computed tomography angiography data is relevant in clinical practice. Whereas numerous methods have been presented for this purpose, up to now no standardized evaluation methodology has been published to reliably evaluate and compare the performance of the existing or newly developed coronary artery centerline extraction algorithms. This paper describes a standardized evaluation methodology and reference database for the quantitative evaluation of coronary artery centerline extraction algorithms. The contribution of this work is fourfold: (1) a method is described to create a consensus centerline with multiple observers, (2) well-defined measures are presented for the evaluation of coronary artery centerline extraction algorithms, (3) a database containing 32 cardiac CTA datasets with corresponding reference standard is described and made available, and (4) 13 coronary artery centerline extraction algorithms, implemented by different research groups, are quantitatively evaluated and compared. The presented evaluation framework is made available to the medical imaging community for benchmarking existing or newly developed coronary centerline extraction algorithms.

Effort angina in a patient with advanced coronary artery disease. Role played by coronary angiography, Ivus and cardiac CT: case report

Coronary angiography is considered to be the gold standard technique for assessing the severity of obstructive luminal narrowing; however, in a few circumstances it may be misleading. In these cases, cardiac computed tomography (CT) and intravascular ultrasound (IVUS) may help to give a correct interpretation.

In this report, we describe the case of a 62-year-old man whose effort angina was first evaluated with coronary angiography, but whose severe stenosis of the right coronary artery was only observed on cardiac CT and IVUS. This additional diagnosis promptly resulted in a therapeutic approach with percutaneous transluminal coronary angioplasty (PTCA).