Coronary Angiogram Images Research Articles

Annotated computed tomography coronary angiogram images and associated data of normal and diseased arteries

Computed Tomography Coronary Angiography (CTCA) is a non-invasive method to evaluate coronary artery anatomy and disease. CTCA is ideal for geometry reconstruction to create virtual models of coronary arteries. To our knowledge there is no public dataset that includes centrelines and segmentation of the full coronary tree. We provide anonymized CTCA images, voxel-wise annotations and associated data in the form of centrelines, calcification scores and meshes of the coronary lumen in 20 normal and 20 diseased cases. Images were obtained along with patient information with informed, written consent as part of the Coronary Atlas. Cases were classified as normal (zero calcium score with no signs of stenosis) or diseased (confirmed coronary artery disease). Manual voxel-wise segmentations by three experts were combined using majority voting to generate the final annotations. Provided data can be used for a variety of research purposes, such as 3D printing patient-specific models, development and validation of segmentation algorithms, education and training of medical personnel and in-silico analyses such as testing of medical devices.

Spontaneous Coronary Artery Dissection (SCAD) and a family history of aortic artery dissection, a case series

Abstract Background/Introduction SCAD typically affects women in their fifth or sixth decade with a paucity of cardiovascular risk factors.(1) It is caused by a coronary artery intramural haematoma with or without intimal tear. Resultant luminal occlusion manifests as myocardial ischaemia/infarction or death. There are two published sporadic cases of SCAD who developed iatrogenic aortic dissection with coronary angiography.(2, 3) We are not aware of any SCAD cases with intercurrent or historical spontaneous aortic dissection. There is a published SCAD case with a familial history of aortic dissection, in her mother.(4) None of these cases reported a connective tissue disorder. Methods We searched our database of 338 SCAD cases, recruited via social media or cardiologist referral, for cases with a family history of aortic dissection. SCAD diagnosis was confirmed by review of coronary angiogram images by an expert interventional cardiologist blinded to the genetic analysis. Genomic DNA was extracted from buccal cells collected using a cheek swab or mouthwash sample. Whole genome sequencing was performed using the Illumina HiSeq X Ten platform with 30x coverage. These data are being analysed for rare variants in genes associated with familial aortopathies or connective tissue disorders (e.g. FBN1, COL3A1, TGFbR-1/2, SMAD3), as well as for novel gene associations with aortic dissection and/or SCAD. Results We identified 12 cases with a first- or second-degree relative with aortic dissection. Of these SCAD cases, 11 were female whereas 10 of 12 relatives with aortic dissection were male. In one instance, a maternal uncle, but not the index SCAD case, had Marfan's syndrome. Whole genome sequencing has been performed on the 12 SCAD cases, 2 living relatives with aortic dissection and 2 relatives linking the SCAD and aortic dissection cases. Conclusions Coronary and aortic dissections have serious consequences and in some families there may be a genetic association between the two conditions. Early identification of variant carriers is critical for disease prevention. Funding Acknowledgement Type of funding sources: Foundation. Main funding source(s): This work was supported in part by grants from the Cardiac Society of Australia and New Zealand, the National Health and Medical Research Council, Australia (APP1161200), the St Vincent's Clinic Foundation, the Catholic Archdiocese of Sydney, Perpetual Philanthropy, NSW Health and SCAD Research Inc. LMC is funded by a University Postgraduate Scholarship through University of NSW and a grant from the Avant Foundation.

Automatic vessel segmentation in X-ray angiogram using spatio-temporal fully-convolutional neural network

Vessel segmentation from X-ray coronary angiogram (CAG) is essential in computer-aided diagnosis of cardiovascular diseases. Automatic segmentation is a challenging task due to the complex vascular structures and poor quality of CAG images. A new deep learning method is presented to automatically extract coronary arteries from dynamic CAG sequences. A spatio-temporal fully-convolutional neural network (ST-FCN) is designed to provide an effective way for segmenting entire vessel trees from motion sequences. An improved post-processing method subsequently refines the segmentation results by making a good use of spatial connectivity and temporal coherence between the moving CAG images. The ST-FCN model outperformed the state-of-the-art segmentation methods with dice similarity coefficient (DSC) of 0.90, accuracy (AC) of 0.92, and sensitivity (SN) of 0.89. Moreover, the ST-FCN achieved superior results in the stenosis detection task with AC of 0.95, SN of 0.92, specificity of 0.95, F1-score of 0.90 among all the reference approaches. The experimental results demonstrated that the integration of spatial and temporal information into a deep learning framework could enhance the vessel segmentation and might be useful for early detection of cardiovascular diseases.

Women With Spontaneous Coronary Artery Dissection Are at Increased Risk of Iatrogenic Coronary Artery Dissection

Spontaneous coronary artery dissection (SCAD) is a non-atherosclerotic cause of acute coronary syndrome (ACS) that affects women disproportionately. Previous case series have found that patients with SCAD undergoing cardiac catheterisation have high rates of iatrogenic coronary damage. We formally compared the rate of iatrogenic coronary artery dissection in women with and without SCAD undergoing cardiac catheterisation over a 11-year period. Women with SCAD were identified by a search of the cardiac catheterisation database 2007-2017 for the keywords 'SCAD', 'spontaneous coronary artery dissection', 'spontaneous coronary dissection', and 'spontaneous dissection'. For each identified case, the medical record and the coronary angiogram images were reviewed to confirm spontaneous coronary dissection. For cases of recurrent SCAD, duplicates were removed so that each patient was included only once in this analysis. For each identified case of SCAD, a control case was chosen from women aged <70 years, without SCAD, undergoing cardiac catheterisation for an ACS during the same 10-year period. One control case was chosen to match each SCAD patient as closely as possible for age and year of cardiac catheterisation. Iatrogenic coronary dissection was defined as new, proximal, flow limiting coronary artery dissection in a different coronary segment to the presenting spontaneous coronary dissection. Eighty-five (85) cases of women with SCAD were identified. Mean age was not different between SCAD and non-SCAD women (51±11 and 51±10 years, respectively). The SCAD group had lower rates of ST elevation myocardial infarction, lower rises in serum creatine kinase (CK) and troponin levels, lower rates of diabetes and smoking, and far less placement of stents during the procedure than the control group. The rate of additional iatrogenic dissection relating to the cardiac catheterisation procedure was 4 of 85 (4.7%) versus 0 of 85 (0%), p=0.04 in SCAD and control groups, respectively, despite a much lower rate of percutaneous coronary intervention in the SCAD group. No common factors could be identified regarding particular equipment or procedural factors associated with iatrogenic dissection. The rate of iatrogenic dissection in women with SCAD during cardiac catheterisation is confirmed to be high and significantly higher than a contemporaneous age-matched group of women without SCAD. This observation likely indicates generalised coronary fragility in this disease, and emphasises the importance of the utmost care in the engagement, injection and intervention involving the coronary arteries in this disease. Development of a non-invasive coronary imaging modality or biomarker able to diagnose SCAD non-invasively would be a great advance in the care of patients with this condition, because it would avoid the need for invasive coronary angiography for diagnosis.

P5540Familial clustering of spontaneous coronary artery dissection

Abstract Background There is increasing evidence that patients with spontaneous coronary artery dissection (SCAD) have an underlying genetic susceptibility (Goel et al JAMA Intern Med175:821–826, 2015). Moreover, in a collaborative study involving 1,055 SCAD cases and 7,190 controls, we recently reported the first risk allele for SCAD, a variant (rs9349379-A) in the PHACTR1/EDN1 genetic locus (Adlam et al J Amer Coll Cardiol73:58–66, 2019). Purpose We sought to determine the clinical characteristics and initial genetic data for 11 families, in which more than one member has had an episode of SCAD. Methods Participants were recruited largely via a social media platform. Informed consent was obtained in all cases for analysis of genetic information using whole genome sequencing, as well as collection of clinical information. SCAD was confirmed by review of coronary angiogram images and clinical data collected by phone interview, as well as review of specialist letters and hospital records. Results Of 235 participants recruited to date, 23 cases showed familial clustering involving sister-sister pairs in six families, three first-degree cousins in one family (picture), two first-degree cousins in two families, a mother-son pair, and a family with concordant monozygotic twins, that is both twins having had SCAD. In an additional family, SCAD is discordant in monozygotic twins. A comparison of symptoms, age at SCAD, clinical syndrome, cardiovascular risk factors, SCAD risk factors, environmental triggers, SCAD location, acute management, left ventricular function and recurrent SCAD events in these families versus isolated cases, will be presented. Three sister-sister pairs have undergone whole genome sequencing and these data sets are undergoing segregation analysis to identify rare variants that are present exclusively in affected family members. Family E Pedigree. Shaded circles represent first cousins affected with SCAD. The top number represents age (in years) of the SCAD event and the bottom number represents current age (in years). Conclusions To our knowledge, this is the largest assembly of SCAD cases with familial clustering reported to date. It provides strong evidence supporting an underlying genetic basis for SCAD, which most likely is a multi-genic disorder that also involves important gene-environment interactions.

Automatic stenosis grading system for diagnosing coronary artery disease using coronary angiogram

The coronary angiogram is considered as the golden standard for diagnosing the coronary artery disease. The paper proposes a system that helps to describe the level of stenosis in coronary angiogram image by using mathematical morphology and thresholding technique. A novel method is introduced to determine the percentage of stenosis and its grading. Based on the diagnostic results, myocardial infarction (MI) is treated well-in-advance. A real time clinical dataset consisting of 25 conventional coronary angiographies with 865 frames is used to evaluate the performance of the proposed system. The execution of the proposed system is inspected by a cardiologist and confirmed the system has produced excellent segmentation and stenosis grading automatically. Sensitivity, specificity, accuracy and precision of the system are 94.74%, 83.33%, 92% and 94.74%, respectively with an average computational time of 0.84 sec. Kappa value also shows perfect system agreement for stenosis grading.

Low-rank and sparse decomposition with spatially adaptive filtering for sequential segmentation of 2D+t vessels

This letter proposes to extract contrast-filled vessels from overlapped noisy complex backgrounds in an x-ray coronary angiogram image sequence using low-rank and sparse decomposition. A refined vessel segmentation is finally achieved by implementing a radon-like feature filtering plus local-to-global adaptive thresholding to tackle the spatially varying noisy residuals in the extracted vessels. Based on real and synthetic XCA data, the experiment results demonstrate the superiority of the proposed method over the state-of-the-art methods.

Computer Aided Segmentation of Blockages in Coronary Heart Images Using Canfis Classifier

Coronary vessel blockage segmentation is the fundamental component which extracts significant features from angiogram images to detect heart disease. This paper proposes an automated method of blockage segmentation from coronary angiogram images using coactive adaptive neuro fuzzy inference system (CANFIS) classifier. The proposed method consists of preprocessing, feature extraction and classification. The vessels in the coronary image are enhanced using preprocessing technique and then features are extracted from these images which are given to the CANFIS classifier. This classifier classifies the given test coronary image into either normal or abnormal. Further, the blockage is detected and segmented if the proposed system classifies the test image as abnormal. The proposed method achieves 99.76% sensitivity, 99.9% specificity and 99.9% accuracy for blockage vessel pixel detection.

Zero Contrast Complex Percutaneous Coronary Intervention Via ‘Roadmap’

Advanced chronic kidney disease (CKD) often precludes complex percutaneous coronary interventions (PCI). The following complex PCI case series describes a simple ‘roadmap’ method of utilising previous coronary angiogram images to perform complex PCI without contrast.

Supervised method for blood vessel segmentation from coronary angiogram images using 7-D feature vector

With the recent advancement in medical image processing field and sophisticated simulation tools it has been possible to acquire useful information from raw images for different parts of the body. Coronary artery segmentation is the fundamental component which extract significant features from angiogram images. Cardiac catheterization is an invasive diagnostic procedure that provides important information about the structure and function of heart. The procedure usually involves X-ray images of heart, arteries using coronary angiography. The resultant images (coronary angiogram) are considered as best of way to diagnose cardiac heart disease. The main focus of coronary angiography is to find the blockage in major blood vessels, however if the blockage is not found in large blood vessels and patient persists to have pain (angina) then it is concluded that the patient is having micro vascular disease (MVD). MVD is caused by blockage or narrowing of small blood vessels in heart, unfortunately there is no specific test to diagnose MVD but it is common in people having diabetes and blood pressure. This paper proposes an automated method of vessel segmentation from coronary angiogram images using radial basis function and moment invariant-based features to extract the small blood vessel for diagnosis of MVD. Experimental results show that the proposed method is capable of extracting small blood vessels from coronary artery and can be a basis to identify key characteristics for MVD. The dataset of angiogram images have been provided by ISRA University Hospital and MATLAB is used for implementing the proposed method.

English

An automated classification of coronary artery disease using discrete wavelet watershed transform and back propagation neural network has been proposed which basically segments the blood vessels of the coronary angiogram image as a first step, which in turn&nbsp; involves various stages such as pre-processing, image enhancement, and segmentation using discrete wavelet transform and watershed transform along with morphological operations. Pre-processing is done to remove the noise using the bicubic interpolation method followed by Daubechies 4 discrete wavelet transform and Weiner filtering. Further, image enhancement is done to improve the quality of the image using the histogram equalization technique. Auto thresholding is done to segment the edges of the blood vessel accurately and efficiently using distance and watershed transforms followed by normalization and median filtering. Finally, morphological operations are performed to remove the noise due to segmentation. Features such as area, mean, standard deviation, variance, brightness, diameter, smoothness, compactness, skewness, kurtosis, eccentricity and circularity are extracted from the segmented coronary blood vessel to train the neural network using back propagation network. Thus, the system is able to achieve 93.75% normal classification and 83.33% abnormal classification. Also, 90% efficiency is achieved in classifying Type 1 and 92% efficiency is achieved in classifying Type 2 stenosis at a learning rate of 0.7 and Type 1 classification efficiency of 85% and Type 2 classification of 89% has been achieved for 50 hidden units of the neural network. Key words: Coronary artery disease, discrete wavelet transform, watershed transform, morphological operations, back propagation neural network.

Multi-row Detector Computed Tomography Coronary Angiogram Image of an Anomalous Left Coronary Artery from the Pulmonary Artery

Multi-row Detector Computed Tomography Coronary Angiogram Image of an Anomalous Left Coronary Artery from the Pulmonary Artery

Comparison of active contour models for image segmentation in X-ray coronary angiogram images

Snakes, or active contours, are used extensively in computer vision and image processing applications, particularly to locate object boundaries. However, most present snake models cannot provide better capture range and evolution stop mechanism. This project presents a new external force for active contours, largely solving both problems. An extension of the gradient vector flow snake (GVF snake) method is presented. First, the adaptive balloon force has been developed to increase the GVF snake's capture range and convergence speed. Then, a dynamic GVF force is introduced to provide an efficient evolution-stop mechanism. In this way, we prevent the snake from breaking through the correct surface and locking to other salient feature points. The active contour models have been applied on X-ray coronary angiogram images. The segmentation results demonstrate the potential of improved GVF method is comparison with all previous active contour methods. Texture parameters have been calculated and results are compared with all active contour models.

A novel segmentation method using multiresolution analysis with 3D visualization for X-ray coronary angiogram images

Coronary angiography is a widely used tool in the diagnosis and treatment of cardiac diseases. The main cause of coronary artery disease is atherosclerosis, which leads to the narrowing of artery lumen, resulting in decreased blood supply to heart muscles. Determination of narrowing of the lumens mainly depends upon the quality of the segmented image; with improved segmentation technique there is better accuracy in identification of blocks. The main purpose of the paper is to develop an automatic, accurate segmentation technique with 3D visualization for the segmented images. 3D visualization provides clearer information regarding the shape and severity of the lesion. The thresholding technique is one of the oldest and simplest techniques used for segmentation. This paper proposes a multithresholding approach using the entropy measure and multiresolution analysis to ensure automatic and accurate segmentation by overcoming some of the problems encountered in other techniques. Also, segmentation performance analysis was conducted for various segmentation methods. This method is tested with different real coronary angiographic images and was found to perform better than the other techniques.

Feature stabilized digital x-ray coronary angiograms improve human visual detection in JPEG compressed images

We evaluate the effect on human visual detection of a display method that stabilizes the motion of the feature of interest in sequential JPEG compressed x-ray coronary angiogram images. At all levels of image compression the feature stabilized display significantly improved performance with respect to the standard display where the artery is moving. In addition, for both the moving artery and stabilized display, human performance with images compressed at 15:1 was not significantly different from performance with the uncompressed images.