X-ray Coronary Angiograms Research Articles

Online tree-structure-constrained RPCA for background subtraction of X-ray coronary angiography images

Background and objectiveBackground subtraction of X-ray coronary angiograms (XCA) can significantly improve the diagnosis and treatment of coronary vessel diseases. The XCA background is complex and dynamic due to structures with different intensities and independent motion patterns, making XCA background subtraction challenging. MethodsThe current work proposes an online tree-structure-constrained robust PCA (OTS-RPCA) method to subtract the XCA background. A morphological closing operation is used as a pre-processing step to remove large-scale structures like the spine, chest and diaphragm. In the following, the XCA sequence is decomposed into three different subspaces: low-rank background, residual dynamic background and vascular foreground. A tree-structured norm is introduced and applied to the vascular submatrix to guarantee the vessel spatial coherency. Moreover, the residual dynamic background is separately extracted to remove noise and motion artifacts from the vascular foreground. The proposed algorithm also employs an adaptive regularization coefficient that tracks the vessel area changes in the XCA frames. ResultsThe proposed method is evaluated on two datasets of real clinical and synthetic low-contrast XCA sequences of 38 patients using the global and local contrast-to-noise ratio (CNR) and structural similarity index (SSIM) criteria. For the real XCA dataset, the average values of global CNR, local CNR and SSIM are 6.27, 3.07 and 0.97, while these values over the synthetic low-contrast dataset are obtained as 5.15, 2.69 and 0.94, respectively. The implemented quantitative and qualitative experiments verify the superiority of the proposed method over seven selected state-of-the-art methods in increasing the coronary vessel contrast and preserving the vessel structure. ConclusionsThe proposed OTS-RPCA background subtraction method accurately subtracts backgrounds from XCA images. Our method might provide the basis for reducing the contrast agent dose and the number of needed injections in coronary interventions.

Perceptual Data Augmentation for Biomedical Coronary Vessel Segmentation.

Sufficient annotated data is critical to the success of deep learning methods. Annotating for vessel segmentation in X-ray coronary angiograms is extremely difficult because of the small and complex structures to be processed. Although unsupervised domain adaptation methods can be utilized to alleviate the annotation burden by using data in other domains, e.g., eye fundus images, these methods cannot perform well due to the characteristic of medical images. Data augmentation can help improve the similarity of source domain and target domain in unsupervised domain adaptation tasks. Existing data augmentation methods play a limited role in improving domain adaptation performance, especially for special medical image segmentation tasks. In this paper, we propose an effective perceptual data augmentation method to improve the similarity between eye fundus images and coronary angiograms by synthesizing virtual samples. Auto Foreground Augment method is designed to search for geometric transformations that improve the similarity between foreground vessels of eye fundus images and coronary angiograms. The Haar Wavelet-Based Perceptual Similarity Index is utilized to guide the synthesis of virtual samples in foreground and background mixup. Extensive experiments show that our data augmentation method can synthesize high-quality virtual samples and thus improve the domain adaptation performance. To our best knowledge, this is the first work to apply perceptual data augmentation to vessel segmentation in coronary angiograms.

Automatic Classification of Coronary Stenosis Using Feature Selection and a Hybrid Evolutionary Algorithm

In this paper, a novel method for the automatic classification of coronary stenosis based on a feature selection strategy driven by a hybrid evolutionary algorithm is proposed. The main contribution is the characterization of the coronary stenosis anomaly based on the automatic selection of an efficient feature subset. The initial feature set consists of 49 features involving intensity, texture and morphology. Since the feature selection search space was O(2n), being n=49, it was treated as a high-dimensional combinatorial problem. For this reason, different single and hybrid evolutionary algorithms were compared, where the hybrid method based on the Boltzmann univariate marginal distribution algorithm (BUMDA) and simulated annealing (SA) achieved the best performance using a training set of X-ray coronary angiograms. Moreover, two different databases with 500 and 2700 stenosis images, respectively, were used for training and testing of the proposed method. In the experimental results, the proposed method for feature selection obtained a subset of 11 features, achieving a feature reduction rate of 77.5% and a classification accuracy of 0.96 using the training set. In the testing step, the proposed method was compared with different state-of-the-art classification methods in both databases, obtaining a classification accuracy and Jaccard coefficient of 0.90 and 0.81 in the first one, and 0.92 and 0.85 in the second one, respectively. In addition, based on the proposed method’s execution time for testing images (0.02 s per image), it can be highly suitable for use as part of a clinical decision support system.

Incremental robust PCA for vessel segmentation in DSA sequences

In intervention surgery, DSA images provide a new way to observe the vessels and catheters inside the patient. Extracting coronary artery from the dynamic complex background fast improves the effectiveness directly in clinical interventional surgery. This article proposes an incremental robust principal component analysis (IRPCA) method to extract contrast-filled vessels from x-ray coronary angiograms. RPCA is a matrix decomposition method that decomposes a video matrix into foreground and background, commonly used to model complex backgrounds and extract target objects. IRPCA pre-optimizes an x-ray image sequence. When a new x-ray sequence is received, IRPCA optimizes it based on the pre-optimized matrix according to the strategy of minimizing the energy function to obtain the foreground matrix of the new sequence. Besides, based on the idea that the new x-ray sequence introduces new information to the pre-optimized matrix, we propose UIRPCA to improve the performence of IRPCA. Compared with the traditional RPCA method, IRPCA and UIRPCA save much time while ensuring that other indicators remain basically unchanged. The experiment results based on real data show the superiority of the proposed method over other RPCA algorithms.

Automatic Feature Selection for Stenosis Detection in X-ray Coronary Angiograms

The automatic detection of coronary stenosis is a very important task in computer aided diagnosis systems in the cardiology area. The main contribution of this paper is the identification of a suitable subset of 20 features that allows for the classification of stenosis cases in X-ray coronary images with a high performance overcoming different state-of-the-art classification techniques including deep learning strategies. The automatic feature selection stage was driven by the Univariate Marginal Distribution Algorithm and carried out by statistical comparison between five metaheuristics in order to explore the search space, which is O(249) computational complexity. Moreover, the proposed method is compared with six state-of-the-art classification methods, probing its effectiveness in terms of the Accuracy and Jaccard Index evaluation metrics. All the experiments were performed using two X-ray image databases of coronary angiograms. The first database contains 500 instances and the second one 250 images. In the experimental results, the proposed method achieved an Accuracy rate of 0.89 and 0.88 and Jaccard Index of 0.80 and 0.79, respectively. Finally, the average computational time of the proposed method to classify stenosis cases was ≈0.02 s, which made it highly suitable to be used in clinical practice.

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.

Automatic Segmentation of Coronary Arteries in X-ray Angiograms using Multiscale Analysis and Artificial Neural Networks

This paper presents a novel method for the automatic segmentation of coronary arteries in X-ray angiograms, based on multiscale analysis and neural networks. The multiscale analysis is performed by using Gaussian filters in the spatial domain and Gabor filters in the frequency domain, which are used as inputs by a multilayer perceptron (MLP) for the enhancement of vessel-like structures. The optimal design of the MLP is selected following a statistical comparative analysis, using a training set of 100 angiograms, and the area under the ROC curve ( A z ) for assessment of the detection performance. The detection results of the proposed method are compared with eleven state-of-the-art blood vessel enhancement methods, obtaining the highest performance of A z = 0.9775 , with a test set of 30 angiograms. The database of 130 X-ray coronary angiograms has been outlined by a specialist and approved by a medical ethics committee. On the other hand, the vessel extraction technique was selected from fourteen binary classification algorithms applied to the multiscale filter response. Finally, the proposed segmentation method is compared with twelve state-of-the-art vessel segmentation methods in terms of six binary evaluation metrics, where the proposed method provided the most accurate coronary arteries segmentation with a classification rate of 0.9698 and Dice coefficient of 0.6857 , using the test set of angiograms. In addition to the experimental results, the performance in the detection and segmentation steps of the proposed method have also shown that it can be highly suitable for systems that perform computer-aided diagnosis in X-ray imaging.

Accurate vessel extraction via tensor completion of background layer in X-ray coronary angiograms

This paper proposes an effective method for accurately recovering vessel structures and intensity information from the X-ray coronary angiography (XCA) images of moving organs or tissues. Specifically, a global logarithm transformation of XCA images is implemented to fit the X-ray attenuation sum model of vessel/background layers into a low-rank, sparse decomposition model for vessel/background separation. The contrast-filled vessel structures are extracted by distinguishing the vessels from the low-rank backgrounds by using a robust principal component analysis and by constructing a vessel mask via Radon-like feature filtering plus spatially adaptive thresholding. Subsequently, the low-rankness and inter-frame spatio-temporal connectivity in the complex and noisy backgrounds are used to recover the vessel-masked background regions using tensor completion of all other background regions, while the twist tensor nuclear norm is minimized to complete the background layers. Finally, the method is able to accurately extract vessels’ intensities from the noisy XCA data by subtracting the completed background layers from the overall XCA images. We evaluated the vessel visibility of resulting images on real X-ray angiography data and evaluated the accuracy of vessel intensity recovery on synthetic data. Experiment results show the superiority of the proposed method over the state-of-the-art methods.

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.

Vesselness-constrained robust PCA for vessel enhancement in x-ray coronary angiograms

Effective vessel enhancement in x-ray coronary angiograms (XCA) is essential for the diagnosis of coronary artery disease, yet challenged by complex background structures of varying intensities as well as motion patterns. As a typical layer-separation method, robust principal component analysis (RPCA) has been proposed to automatically improve vessel visibility via sparse and low-rank decomposition. However, the attenuated motion of vessels in x-ray angiograms leads to the unsatisfactory vessel enhancement performance of the decomposition framework.To address this problem, we propose a vesselness-constrained RPCA method (VC-RPCA), where a vessel-like appearance prior is incorporated into the layer separation framework for accurate vessel enhancement. We first pre-compute the vessel-like appearance prior based on a Frangi filter to highlight the curvilinear structures. After removing large-scale background structures via a morphological closing operation, we then integrate the pre-computed vessel-like appearance prior into a low-rank decomposition framework to separate the fine vessel structures. In addition, we develop an adaptive regularization strategy that imposes structured-sparse constraints to solve the scale issue and capture vessels without salient motion.The proposed method was validated on 13 clinical XCA sequences containing 777 images in total. The contrast-to-noise ratio, Dice coefficient and area under the ROC curve were employed for quantitative evaluation of the vessel enhancement performance. Experiments show that (1) the adaptive regularization strategy helps to obtain a complete coronary tree in the separated vessel layer; (2) our low-rank decomposition framework is robust against false positive/negative responses of the Frangi filter; and (3) the proposed VC-RPCA is computationally fast and outperforms other state-of-the-art RPCA methods for vessel enhancement in the full-contrast and low-contrast scenarios. The results demonstrate that the proposed VC-RPCA can accurately separate coronary arteries and prominently improve vessel visibility in x-ray angiograms.

A Novel Multiscale Gaussian-Matched Filter Using Neural Networks for the Segmentation of X-Ray Coronary Angiograms.

The accurate and efficient segmentation of coronary arteries in X-ray angiograms represents an essential task for computer-aided diagnosis. This paper presents a new multiscale Gaussian-matched filter (MGMF) based on artificial neural networks. The proposed method consists of two different stages. In the first stage, MGMF is used for detecting vessel-like structures while reducing image noise. The results of MGMF are compared with those obtained using six GMF-based detection methods in terms of the area (Az) under the receiver operating characteristic (ROC) curve. In the second stage, ten thresholding methods of the state of the art are compared in order to classify the magnitude of the multiscale Gaussian response into vessel and nonvessel pixels, respectively. The accuracy measure is used to analyze the segmentation methods, by comparing the results with a set of 100 X-ray coronary angiograms, which were outlined by a specialist to form the ground truth. Finally, the proposed method is compared with seven state-of-the-art vessel segmentation methods. The vessel detection results using the proposed MGMF method achieved an Az = 0.9357 with a training set of 50 angiograms and Az = 0.9362 with the test set of 50 images. In addition, the segmentation results using the intraclass variance thresholding method provided a segmentation accuracy of 0.9568 with the test set of coronary angiograms.

Extracting contrast-filled vessels in X-ray angiography by graduated RPCA with motion coherency constraint

X-ray coronary angiography can provide rich dynamic information of cardiac and vascular function. Extracting contrast-filled vessel from the complex dynamic background (caused by the movement of diaphragm, lung, bones, etc.) in X-ray coronary angiograms has great clinical significance in assisting myocardial perfusion evaluation, reconstructing vessel structures for diagnosis and treatment of heart disease. Considering the angiography image sequence is a sum of a low-rank background matrix and a sparse flowing contrast agent matrix, we propose a novel graduated robust principal component analysis (RPCA) with spatio-temporal motion coherency constraint to accurately extract contrast-filled vessel from the X-ray coronary angiograms: (1) We first use a statistically structured RPCA with complex noise model exploiting the complex structural connectivity of vessel regions to identify all candidate foreground contrast-filled vessels; (2) To eliminate the background remained in the candidates, we further introduce trajectory decomposition on the candidate foregrounds to accurately extract contrast-filled vessels using motion coherency regularized RPCA, which imposes total variation minimization on the foreground trajectories to model the spatio-temporal contiguity and smoothness of the foreground trajectories. The graduated RPCA with motion coherency constraint shows to consistently outperform other state-of-the-art methods, in particular on real-world X-ray coronary angiograms that contain a significant amount of complex dynamic background motion. Experimental results on twelve sequences of real X-ray coronary angiograms are evaluated using both qualitative and quantitative methods to demonstrate the obvious advantages of our method over the state-of-the-art alternatives.

On the performance of nature inspired algorithms for the automatic segmentation of coronary arteries using Gaussian matched filters

This paper presents a comparative analysis of four nature inspired algorithms to improve the training stage of a segmentation strategy based on Gaussian matched filters (GMF) for X-ray coronary angiograms. The statistical results reveal that the method of differential evolution (DE) outperforms the considered algorithms in terms of convergence to the optimal solution. From the potential solutions acquired by DE, the area (Az) under the receiver operating characteristic curve is used as fitness function to establish the best GMF parameters. The GMF-DE method demonstrated high accuracy with Az=0.9402 with a training set of 40 angiograms. Moreover, to evaluate the performance of the coronary artery segmentation method compared to the ground-truth vessels hand-labeled by a specialist, measures of sensitivity, specificity and accuracy have been adopted. According to the experimental results, GMF-DE has obtained high coronary artery segmentation rate compared with six state-of-the-art methods provided an average accuracy of 0.9134 with a test set of 40 angiograms. Additionally, the experimental results in terms of segmentation accuracy, have also shown that the GMF-DE can be highly suitable for clinical decision support in cardiology.

Repositioning precision of coronary arteries measured on X-ray angiography and its implications for coronary MR angiography.

To test the hypothesis that intervals with superior beat-to-beat coronary artery repositioning precision exist in the cardiac cycle, to design a coronary MR angiography (MRA) methodology in response, and to ascertain its performance. Coronary repositioning precision in consecutive heartbeats was measured on x-ray coronary angiograms of 17 patients and periods with the highest repositioning precision were identified. In response, the temporal order of coronary MRA pulse sequence elements required modification and the T2 -prep now follows (T2 -post) rather than precedes the imaging part of the sequence. The performance of T2 -post was quantitatively compared (signal-to-noise [SNR], contrast-to-noise [CNR], vessel sharpness) to that of T2 -prep in vivo. Coronary repositioning precision is <1 mm at peak systole and in mid diastole. When comparing systolic T2 -post to diastolic T2 -prep, CNR and vessel sharpness remained unchanged (both P = NS) but SNR for muscle and blood increased by 104% and 36% (both P < 0.05), respectively. Windows with improved coronary repositioning precision exist in the cardiac cycle: one in peak systole and one in mid diastole. Peak-systolic imaging necessitates a re-design of conventional coronary MRA pulse sequences and leads to image quality very similar to that of conventional mid-diastolic data acquisition but improved SNR.

Assessing Cardiac Dynamics based on X-Ray Coronary Angiograms

The problem of quantitatively assessing cardiac motion including global and local dynamic performances during cardiac cycles is addressed. In vivo X-ray coronary angiographic image sequences covering several cardiac cycles are used as source image data. The three-dimensional (3-D) surface of the heart based on extended superquadrics (ESQ) surface model in each phase is constructed from 3-D coronary vessel skeletons, which are reconstructed from a pair of nearly orthogonal angiographic sequences. Complex dynamic performances of the heart are decomposed into global and local components according to a priori anatomical and dynamic knowledge that have been confirmed by medical observations and non-rigid motion theory. Parameters of all components are quantitatively estimated through motion decomposition and compensation. Consequently, cardiac dynamics during cardiac cycles are comprehensively depicted with quantitative parameters. Validation of the proposed method with clinically acquired in vivo image data has been carried out, the results of which have verified the feasibility and accuracy of the proposed method.

Correlation between an angiographic and a cardiac magnetic resonance score of myocardial jeopardy using standard and high-resolution perfusion sequences

Background High temporal resolution required for CMR perfusion imaging results in compromised spatial resolution. However, recent advances, including the use of the advanced acceleration method k-t sensitivity encoding, allow myocardial perfusion imaging with unprecedented spatial resolution. The associated benefits remain to be fully described. The BCIS-1 Myocardial Jeopardy Score (JS) quantifies the amount of myocardium in jeopardy from severe CAD (0= no jeopardy; 12 = maximum jeopardy). It accommodates patients with CABG and left main disease, is prognostically relevant and can easily be calculated by visual analysis of the X-ray coronary angiogram (XCA). Combined perfusion and scar CMR imaging should provide equivalent functional information on myocardial jeopardy. High-resolution perfusion imaging may improve the correlation between JS and CMR findings.

Myocardium selective densitometric perfusion assessment after acute myocardial infarction

Myocardial perfusion is an important prognostic factor after recanalisation in acute myocardial infarction patients. We present a computerized, densitometric measurement method to assess myocardial perfusion on phase-matched digitally subtracted coronary angiograms. Quantitative myocardial perfusion was assessed by the G(max)/T(max) parameter of the time-density curves (TDCs) in infarct-related myocardial regions on X-ray coronary angiograms. Arteries were masked out from regions of measurement. This novel method has been compared with enzymatic infarct size, ST-segment resolution, and ejection fraction after successful revascularization of 62 patients with acute myocardial infarction. Significant correlations were found between G(max)/T(max) and enzymatic infarct size (R=-0.445, P<.001), ST-segment resolution (R=0.364, P=.004), and ejection fraction (R=0.278, P=.029). Bland and Altman plot of G(max)/T(max) reveals good interobserver agreement. G(max)/T(max) of the TDC measured in the infarct-related myocardial area is a reliable parameter to assess clinical indicators of myocardial reperfusion. Therefore, results suggest that it could be used to immediately assess the success of recanalisation at the tissue perfusion level during coronary intervention, and as an objective end point in clinical trials of new interventional devices and drugs.

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.

Evaluation of internal noise methods for Hotelling observer models

The inclusion of internal noise in model observers is a common method to allow for quantitative comparisons between human and model observer performance in visual detection tasks. In this article, we studied two different strategies for inserting internal noise into Hotelling model observers. In the first strategy, internal noise was added to the output of individual channels: (a) Independent nonuniform channel noise, (b) independent uniform channel noise. In the second strategy, internal noise was added to the decision variable arising from the combination of channel responses. The standard deviation of the zero mean internal noise was either constant or proportional to: (a) the decision variable's standard deviation due to the external noise, (b) the decision variable's variance caused by the external noise, (c) the decision variable magnitude on a trial to trial basis. We tested three model observers: square window Hotelling observer (HO), channelized Hotelling observer (CHO), and Laguerre-Gauss Hotelling observer (LGHO) using a four alternative forced choice (4AFC) signal known exactly but variable task with a simulated signal embedded in real x-ray coronary angiogram backgrounds. The results showed that the internal noise method that led to the best prediction of human performance differed across the studied model observers. The CHO model best predicted human observer performance with the channel internal noise. The HO and LGHO best predicted human observer performance with the decision variable internal noise. The present results might guide researchers with the choice of methods to include internal noise into Hotelling model observers when evaluating and optimizing medical image quality.