Towards quantitative analysis of coronary CTA

Automatic coronary artery segmentation of CCTA images using UNet with a local contextual transformer

Coronary artery segmentation is an essential procedure in the computer-aided diagnosis of coronary artery disease. It aims to identify and segment the regions of interest in the coronary circulation for further processing and diagnosis. Currently, automatic segmentation of coronary arteries is often unreliable because of their small size and poor distribution of contrast medium, as well as the problems that lead to over-segmentation or omission. To improve the performance of convolutional-neural-network (CNN) based coronary artery segmentation, we propose a novel automatic method, DR-LCT-UNet, with two innovative components: the Dense Residual (DR) module and the Local Contextual Transformer (LCT) module. The DR module aims to preserve unobtrusive features through dense residual connections, while the LCT module is an improved Transformer that focuses on local contextual information, so that coronary artery-related information can be better exploited. The LCT and DR modules are effectively integrated into the skip connections and encoder-decoder of the 3D segmentation network, respectively. Experiments on our CorArtTS2020 dataset show that the dice similarity coefficient (DSC), Recall, and Precision of the proposed method reached 85.8%, 86.3% and 85.8%, respectively, outperforming 3D-UNet (taken as the reference among the 6 other chosen comparison methods), by 2.1%, 1.9%, and 2.1%.

Effect of vessel wall segmentation on volumetric and radiomic parameters of coronary plaques with adverse characteristics

BACKGROUND

Quantitative coronary plaque parameters are increasingly being utilized as surrogate endpoints of pharmaceutical trials. However, little is known whether differences in segmentation significantly alter parameter values.

METHODS

Overall, 100 coronary plaques with adverse imaging characteristics were segmented automatically, by two experts (R₁-R₂) and three nonexperts (R₃-R₅). Low attenuation noncalcified (LANCP), noncalcified and calcified plaque volume were calculated and 4310 radiomic features were extracted. Intraclass correlation coefficient (ICC) values were calculated between the segmentations.

RESULTS

ICC values between expert readers were 0.84 [CI: 0.77-0.89] for total; 0.83 [CI: 0.76-0.88] for noncalcified; 0.96 [CI: 0.94-0.98] for calcified and 0.65 [CI: 0.51-0.75] for LANCP volumes. Comparing nonexperts' and experts' results, ICC ranged between 0.64 and 0.90 for total; 0.63-0.91 for noncalcified; 0.86-0.96 for calcified and 0.34-0.84 for LANCP volume. All readers (R₁-R₅) showed poor agreement with automatic segmentation (range: 0.00-0.27), except for calcified plaque volumes (range: 0.73-0.88). Regarding radiomic features, expert readers (R₁-R₂) achieved good reproducibility (ICC>0.80) in 88.6% (39/44) of first-order, 62.0% (424/684) of gray level co-occurrence matrix (GLCM), 75.8% (50/66) of gray level run length matrix (GLRLM) and 19.8% (696/3516) of geometrical parameters. Between experts and nonexperts, ICC ranged between: 70.5%-86.4% for first-order, 31.0%-58.3% for GLCM, 24.2%-78.8% for GLRLM and 6.2%-21.1% for geometrical features, while between all readers and automatic segmentation ICC ranged between: 25.0%-38.6%; 0.0%-0.0%; 0.0%-3.0% and 1.1%-1.4%, respectively.

CONCLUSIONS

Even among experts there is a considerable amount of disagreement in LANCP volumes. Nevertheless, expert readers have the best agreement which currently cannot be replaced with nonexperts' or automatic segmentation.

Automatic Coronary Wall and Atherosclerotic Plaque Segmentation from 3D Coronary CT Angiography

Coronary plaque burden measured by coronary computerized tomography angiography (CCTA), independent of stenosis, is a significant independent predictor of coronary heart disease (CHD) events and mortality. Hence, it is essential to develop comprehensive CCTA plaque quantification beyond existing subjective plaque volume or stenosis scoring methods. The purpose of this study is to develop a framework for automated 3D segmentation of CCTA vessel wall and quantification of atherosclerotic plaque, independent of the amount of stenosis, along with overcoming challenges caused by poor contrast, motion artifacts, severe stenosis, and degradation of image quality. Vesselness, region growing, and two sequential level sets are employed for segmenting the inner and outer wall to prevent artifact-defective segmentation. Lumen and vessel boundaries are joined to create the coronary wall. Curved multiplanar reformation is used to straighten the segmented lumen and wall using lumen centerline. In-vivo evaluation included CCTA stenotic and non-stenotic plaques from 41 asymptomatic subjects with 122 plaques of different characteristics against the individual and consensus of expert readers. Results demonstrate that the framework segmentation performed robustly by providing a reliable working platform for accelerated, objective, and reproducible atherosclerotic plaque characterization beyond subjective assessment of stenosis; can be potentially applicable for monitoring response to therapy.

Automatic Coronary Artery Segmentation Using Active Search for Branches and Seemingly Disconnected Vessel Segments from Coronary CT Angiography

We propose a Bayesian tracking and segmentation method of coronary arteries on coronary computed tomographic angiography (CCTA). The geometry of coronary arteries including lumen boundary is estimated in Maximum A Posteriori (MAP) framework. Three consecutive sphere based filtering is combined with a stochastic process that is based on the similarity of the consecutive local neighborhood voxels and the geometric constraint of a vessel. It is also founded on the prior knowledge that an artery can be seen locally disconnected and consist of branches which may be seemingly disconnected due to plaque build up. For such problem, an active search method is proposed to find branches and seemingly disconnected but actually connected vessel segments. Several new measures have been developed for branch detection, disconnection check and planar vesselness measure. Using public domain Rotterdam CT dataset, the accuracy of extracted centerline is demonstrated and automatic reconstruction of coronary artery mesh is shown.

Fast Marching and Runge-Kutta Based Method for Centreline Extraction of Right Coronary Artery in Human Patients

The CT angiography (CTA) is a clinically indicated test for the assessment of coronary luminal stenosis that requires centerline extractions. There is currently no centerline extraction algorithm that is automatic, real-time and very accurate. Therefore, we sought to (i) develop a hybrid approach by incorporating fast marching and Runge-Kutta based methods for the extraction of coronary artery centerlines from CTA; (ii) evaluate the accuracy of the present method compared to Van's method by using ground truth centerline as a reference; (iii) evaluate the coronary lumen area of our centerline method in comparison with the intravascular ultrasound (IVUS) as the standard of reference. The proposed method was found to be more computationally efficient, and performed better than the Van's method in terms of overlap measures (i.e., OV: [Formula: see text] vs. [Formula: see text]; OF: [Formula: see text] vs. [Formula: see text]; and OT: [Formula: see text] vs. [Formula: see text], all [Formula: see text]). In comparison with IVUS derived coronary lumen area, the proposed approach was more accurate than the Van's method. This hybrid approach by incorporating fast marching and Runge-Kutta based methods could offer fast and accurate extraction of centerline as well as the lumen area. This method may garner wider clinical potential as a real-time coronary stenosis assessment tool.

A fast seed detection using local geometrical feature for automatic tracking of coronary arteries in CTA

We propose a fast seed detection for automatic tracking of coronary arteries in coronary computed tomographic angiography (CCTA). To detect vessel regions, Hessian-based filtering is combined with a new local geometric feature that is based on the similarity of the consecutive cross-sections perpendicular to the vessel direction. It is in turn founded on the prior knowledge that a vessel segment is shaped like a cylinder in axial slices. To improve computational efficiency, an axial slice, which contains part of three main coronary arteries, is selected and regions of interest (ROIs) are extracted in the slice. Only for the voxels belonging to the ROIs, the proposed geometric feature is calculated. With the seed points, which are the centroids of the detected vessel regions, and their vessel directions, vessel tracking method can be used for artery extraction. Here a particle filtering-based tracking algorithm is tested. Using 19 clinical CCTA datasets, it is demonstrated that the proposed method detects seed points and can be used for full automatic coronary artery extraction. ROC (receiver operating characteristic) curve analysis shows the advantages of the proposed method.

Automated quantification of coronary plaque with computed tomography: comparison with intravascular ultrasound using a dedicated registration algorithm for fusion-based quantification

AIMS

Previous studies have used semi-automated approaches for coronary plaque quantification on multi-detector row computed tomography (CT), while an automated quantitative approach using a dedicated registration algorithm is currently lacking. Accordingly, the study aimed to demonstrate the feasibility and accuracy of automated coronary plaque quantification on cardiac CT using dedicated software with a novel 3D coregistration algorithm of CT and intravascular ultrasound (IVUS) data sets.

METHODS AND RESULTS

Patients who had undergone CT and IVUS were enrolled. Automated lumen and vessel wall contour detection was performed for both imaging modalities. Dedicated automated quantitative software (QCT) with a unique registration algorithm was used to fuse a complete IVUS run with a CT angiography volume using true anatomical markers. At the level of the minimal lumen area (MLA), percentage lumen area stenosis, plaque burden, and degree of remodelling were obtained on CT. Additionally, mean plaque burden was assessed for the whole coronary plaque. At the identical level within the coronary artery, the same variables were derived from IVUS. Fifty-one patients (40 men, 58 ± 11 years, 103 coronary arteries) with 146 lesions were evaluated. Quantitative computed tomography and IVUS showed good correlation for MLA (n = 146, r = 0.75, P < 0.001). At the level of the MLA, both techniques were well-correlated for lumen area stenosis (n = 146, r = 0.79, P < 0.001) and plaque burden (n = 146, r = 0.70, P < 0.001). Mean plaque burden (n = 146, r = 0.64, P < 0.001) and remodelling index (n = 146, r = 0.56, P < 0.001) showed significant correlations between QCT and IVUS.

CONCLUSION

Automated quantification of coronary plaque on CT is feasible using dedicated quantitative software with a novel 3D registration algorithm.

Automated quantification of carotid artery stenosis on contrast-enhanced MRA data using a deformable vascular tube model

The purpose of this study was to develop and validate a method for automated segmentation of the carotid artery lumen from volumetric MR Angiographic (MRA) images using a deformable tubular 3D Non-Uniform Rational B-Splines (NURBS) model. A flexible 3D tubular NURBS model was designed to delineate the carotid arterial lumen. User interaction was allowed to guide the model by placement of forbidden areas. Contrast-enhanced MRA (CE-MRA) from 21 patients with carotid atherosclerotic disease were included in this study. The validation was performed against expert drawn contours on multi-planar reformatted image slices perpendicular to the artery. Excellent linear correlations were found on cross-sectional area measurement (r = 0.98, P < 0.05) and on luminal diameter (r = 0.98, P < 0.05). Strong match in terms of the Dice similarity indices were achieved: 0.95 ± 0.02 (common carotid artery), 0.90 ± 0.07 (internal carotid artery), 0.87 ± 0.07 (external carotid artery), 0.88 ± 0.09 (carotid bifurcation) and 0.75 ± 0.20 (stenosed segments). Slight overestimation of stenosis grading by the automated method was observed. The mean differences was 7.20% (SD = 21.00%) and 5.2% (SD = 21.96%) when validated against two observers. Reproducibility in stenosis grade calculation by the automated method was high; the mean difference between two repeated analyses was 1.9 ± 7.3%. In conclusion, the automated method shows high potential for clinical application in the analysis of CE-MRA of carotid arteries.

Robust shape regression for supervised vessel segmentation and its application to coronary segmentation in CTA

This paper presents a vessel segmentation method which learns the geometry and appearance of vessels in medical images from annotated data and uses this knowledge to segment vessels in unseen images. Vessels are segmented in a coarse-to-fine fashion. First, the vessel boundaries are estimated with multivariate linear regression using image intensities sampled in a region of interest around an initialization curve. Subsequently, the position of the vessel boundary is refined with a robust nonlinear regression technique using intensity profiles sampled across the boundary of the rough segmentation and using information about plausible cross-sectional vessel shapes. The method was evaluated by quantitatively comparing segmentation results to manual annotations of 229 coronary arteries. On average the difference between the automatically obtained segmentations and manual contours was smaller than the inter-observer variability, which is an indicator that the method outperforms manual annotation. The method was also evaluated by using it for centerline refinement on 24 publicly available datasets of the Rotterdam Coronary Artery Evaluation Framework. Centerlines are extracted with an existing method and refined with the proposed method. This combination is currently ranked second out of 10 evaluated interactive centerline extraction methods. An additional qualitative expert evaluation in which 250 automatic segmentations were compared to manual segmentations showed that the automatically obtained contours were rated on average better than manual contours.

Automatic centerline extraction of coronary arteries in coronary computed tomographic angiography

Coronary computed tomographic angiography (CCTA) is a non-invasive imaging modality for the visualization of the heart and coronary arteries. To fully exploit the potential of the CCTA datasets and apply it in clinical practice, an automated coronary artery extraction approach is needed. The purpose of this paper is to present and validate a fully automatic centerline extraction algorithm for coronary arteries in CCTA images. The algorithm is based on an improved version of Frangi's vesselness filter which removes unwanted step-edge responses at the boundaries of the cardiac chambers. Building upon this new vesselness filter, the coronary artery extraction pipeline extracts the centerlines of main branches as well as side-branches automatically. This algorithm was first evaluated with a standardized evaluation framework named Rotterdam Coronary Artery Algorithm Evaluation Framework used in the MICCAI Coronary Artery Tracking challenge 2008 (CAT08). It includes 128 reference centerlines which were manually delineated. The average overlap and accuracy measures of our method were 93.7% and 0.30 mm, respectively, which ranked at the 1st and 3rd place compared to five other automatic methods presented in the CAT08. Secondly, in 50 clinical datasets, a total of 100 reference centerlines were generated from lumen contours in the transversal planes which were manually corrected by an expert from the cardiology department. In this evaluation, the average overlap and accuracy were 96.1% and 0.33 mm, respectively. The entire processing time for one dataset is less than 2 min on a standard desktop computer. In conclusion, our newly developed automatic approach can extract coronary arteries in CCTA images with excellent performances in extraction ability and accuracy.

Diagnostic accuracy of 320-row multidetector computed tomography coronary angiography to noninvasively assess in-stent restenosis

OBJECTIVES

Percutaneous coronary intervention with stent implantation is routinely performed to treat patients with obstructive coronary artery disease. However, thus far, noninvasive assessment of in-stent restenosis has been challenging. Recently, 320-row multidetector computed tomography coronary angiography (CTA) was introduced, allowing volumetric image acquisition of the heart in a single heart beat or gantry rotation. The aim of this study was to evaluate the diagnostic performance of 320-row CTA in the evaluation of significant in-stent restenosis. Invasive coronary angiography (ICA) served as the standard of reference, using a quantitative approach.

MATERIALS AND METHODS

The population consisted of patients with previous coronary stent implantation who were clinically referred for cardiac evaluation because of recurrent chest pain and who underwent both CTA and ICA. CTA studies were performed using a 320-row CTA scanner with 320 detector-rows, each 0.5 mm wide, and a gantry rotation time of 350 milliseconds. Tube voltage and current were adapted to body mass index and thoracic anatomy. The entire heart was imaged in a single heart beat, with a maximum of 16-cm craniocaudal coverage. During the scan, the ECG was registered simultaneously for prospective triggering of the data. First, CTA stent image quality was assessed using a 3-point grading scale: (1) good image quality, (2) moderate image quality, and (3) poor image quality. Subsequently, the presence of in-stent restenosis was determined on a stent and patient basis by a blinded observer. Significant in-stent restenosis was defined as >or=50% luminal narrowing in the stent lumen or the presence of significant stent edge stenosis. Overlapping stents were considered to represent a single stent. Results were compared with ICA using quantitative coronary angiography. In addition, CTA stent image quality and diagnostic accuracy were related to stent characteristics and heart rate during CTA image acquisition.

RESULTS

The population consisted of 53 patients (37 men, mean age: 65 +/- 13 years) with a total of 89 stents available for evaluation. ICA identified 12 stents (13%) with significant in-stent restenosis. A total of 7 stents (8%) were of nondiagnostic CTA stent image quality, and were considered positive. Sensitivity, specificity, positive, and negative predictive values were 92%, 83%, 46%, and 98%, respectively on a stent basis. Five CTA studies (9%) were of nondiagnostic quality for the evaluation of in-stent restenosis and were considered positive. Sensitivity, specificity, positive, and negative predictive values were 100%, 81%, 58%, and 100%, respectively on a patient level. Stent diameter <3 mm as well as stent strut thickness >or=140 mum were associated with decreased CTA stent image quality and diagnostic accuracy. Heart rate during CTA acquisition and stent overlap were not associated with image degradation.

CONCLUSIONS

The present results show that 320-row CTA allows accurate noninvasive assessment of significant in-stent restenosis. However, stents with a large diameter and thin struts allowed better in-stent visualization than stents with a small diameter or thick struts. Consequently, noninvasive assessment of in-stent restenosis using CTA may be an attractive and feasible alternative particularly in carefully selected patients.

Integrating automatic and interactive methods for coronary artery segmentation: let the PACS workstation think ahead

PURPOSE

To present newly developed software that can provide fast coronary artery segmentation and accurate centerline extraction for later lesion visualization and quantitative measurement while minimizing user interaction.

METHODS

Previously reported fully automatic and interactive methods for coronary artery extraction were optimized and integrated into a user-friendly workflow. The user's waiting time is saved by running the non-supervised coronary artery segmentation and centerline tracking in the background as soon as the images are received. When the user opens the data, the software provides an intuitive interactive analysis environment.

RESULTS

The average overlap between the centerline created in our software and the reference standard was 96.0%. The average distance between them was 0.38 mm. The automatic procedure runs for 1.4-2.5 min as a single-thread application in the background. Interactive processing takes 3 min in average.

CONCLUSION

In preliminary experiments, the software achieved higher efficiency than the former interactive method, and reasonable accuracy compared to manual vessel extraction.

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.

Novel clinical applications of state-of-the-art multi-slice computed tomography

Recent years have witnessed a rapid development of multi-slice computed tomography (MSCT) technology. The number of detector rows has increased from 4-slices to the current availability of 64-slice and even 320-slice systems. In addition, images are acquired with thinner slices and faster rotation times resulting in substantially improved image quality and diagnostic accuracy. Simultaneously, effective dose reduction acquisition techniques have been developed allowing considerable reduction of the radiation dose. Conceivably, these advancements may allow further expansion of the use of MSCT beyond the visual assessment of the presence or absence of significant coronary artery disease. Indeed, a particular advantage of the technique is that in addition to evaluation of the coronary arteries it also allows assessment of cardiac structures and function. The purpose of the current review is to discuss several novel applications of cardiac MSCT, including stenosis quantification, atherosclerotic plaque imaging and prognostification as well as imaging of left ventricular function, aortic and mitral valve anatomy using state-of-the-art technology.

Coronary artery segmentation and skeletonization based on competing fuzzy connectedness tree

We propose a new segmentation algorithm based on competing fuzzy connectedness theory, which is then used for visualizing coronary arteries in 3D CT angiography (CTA) images. The major difference compared to other fuzzy connectedness algorithms is that an additional data structure, the connectedness tree, is constructed at the same time as the seeds propagate. In preliminary evaluations, accurate result have been achieved with very limited user interaction. In addition to improving computational speed and segmentation results, the fuzzy connectedness tree algorithm also includes automated extraction of the vessel centerlines, which is a promising approach for creating curved plane reformat (CPR) images along arteries' long axes.

Anomalous origin of the three coronary arteries from the right aortic sinus Valsalva: role of MDCT coronary angiography

BACKGROUND

Monocuspal origin of all three coronary arteries through separate ostia from the right aortic sinus (RCS) is a rare occurrence. To date, the use of multidetector computed tomography (MDCT) for imaging of congenitally abnormal coronary arteries has been discussed only in few individual case reports.

OBJECTIVE

To describe the role of MDCT coronary angiography in the evaluation of two rare cases of monocuspal origin of all three coronary from RCS.

PATIENTS AND METHODS

We had a retrospective review of clinical information and imaging studies for two patients presented with chest pain. Both patients underwent conventional coronary angiography followed by noninvasive imaging with MDCT.

RESULTS

Both patients had anomalous origin of the all three coronary arteries from the RCS. In one case the LAD took an intramural course in between the aorta and the right ventricular outflow tract (RVOT) while it passed anterior to the RVOT in the other patient. In the first patient, there was also associated coronary fistula to the right ventricle along with right coronary artery (RCA) and left anterior descending coronary artery (LAD) narrowing. Both the stenosed segments were successfully stented and were demonstrated to be patent in the subsequent MDCT.

CONCLUSION

Monocuspal origin of all three coronary artery from the RCS is a rare anomaly, can be reliably diagnosed by MDCT. CT angiogram is a convenient complementary tool for the coronary arteriography.

Automatic initialization algorithm for carotid artery segmentation in CTA images

Analysis of CT datasets is commonly time consuming because of the required manual interaction. We present a novel and fast automatic initialization algorithm to detect the carotid arteries providing a fully automated approach of the segmentation and centerline detection. First, the volume of interest (VOI) is estimated using a shoulder landmark. The carotid arteries are subsequently detected in axial slices of the VOI by applying a circular Hough transform. To select carotid arteries related signals in the Hough space, a 3-D, direction dependent hierarchical clustering is used. To allow a successful detection for a wide range of vessel diameters, a feedback architecture was introduced. The algorithm was designed and optimized using a training set of 20 patients and subsequently evaluated using 31 test datasets. The detection algorithm, including VOI estimation, correctly detects 88% of the carotid arteries. Even though not all carotid arteries have been correctly detected, the results are very promising.