X-ray Angiography Research Articles

In situ isotropic 3D imaging of vasculature perfusion specimens using x-ray microscopic dual-energy CT.

Ex vivo x-ray angiography provides high-resolution, three-dimensional information on vascular phenotypes down to the level of capillaries. Sample preparation for ex vivo angiography starts with the removal of blood from the vascular system, followed by perfusion with an x-ray dense contrast agent mixed with a carrier such as gelatine or a polymer. Subsequently, the vascular micro-architecture of harvested organs is imaged in the intact fixed organ. In the present study, we present novel microscopic dual-energy CT (microDECT) imaging protocols that allow to visualise and analyse microvasculature in situ with reference to the morphology of hard and soft tissue. We show that the spectral contrast of µAngiofil and Micropaque barium sulphate in perfused specimens allows for the effective separation of vasculature from mineralised skeletal tissues. Furthermore, we demonstrate the counterstaining of perfused specimens using established x-ray dense contrast agents to depict blood vessels together with the morphology of soft tissue. Phosphotungstic acid (PTA) is used as a counterstain that shows excellent spectral contrast in both µAngiofil and Micropaque barium sulphate-perfused specimens. A novel Sorensen-buffered PTA protocol is introduced as a counterstain for µAngiofil specimens, as the polyurethane polymer is susceptible to artefacts when using conventional staining solutions. Finally, we demonstrate that counterstained samples can be automatically processed into three separate image channels (skeletal tissue, vasculature and stained soft tissue), which offers multiple new options for data analysis. The presented microDECT workflows are suited as tools to screen and quantify microvasculature and can be implemented in various correlative imaging pipelines to target regions of interest for downstream light microscopic investigation.

Hypoxia-Inducible Factor-1α Potentiates Multiterritory Perforator Flap Survival by Augmenting Vascular Endothelial Growth Factor Expression in the Choke II Zone.

Hypoxia-inducible factor-1α (HIF-1α), regulated by prolyl hydroxylase, plays a central role in tissue adaptation to ischemia. This study investigates the impact of HIF-1α on angiogenesis in the Choke II zone of multiterritory perforator flaps. Ninety male Wistar rats were allocated into 3 groups, with 30 rats in each group: the dimethyloxalylglycine (DMOG) group, the 3-(5-hydroxymethyl-2-furyl)-1-benzylindazole (YC-1) group, and the normal saline (NS) group. All rats underwent multiterritory perforator flap surgeries on their dorsal side. Subsequently, they received intraperitoneal injections of DMOG (40 mg/kg), YC-1 (10 mg/kg), and normal saline on postoperative days 1, 2, and 3, respectively. After treatment, angiogenesis in the Choke II zone of the flap on day 7 was observed through transillumination tests and lead oxide/gelatin x-ray angiography. Histological features were determined using hematoxylin and eosin staining, and the expression of HIF-1α and vascular endothelial growth factor (VEGF) in the Choke II region of the flap was assessed via immunohistochemistry and western blotting. Compared to the YC-1 and NS groups, the DMOG group exhibited significant angiogenesis, resulting in a denser vascular network in the Choke II zone of the flap. The DMOG group showed significantly higher microvessel density in the Choke II zone than the YC-1 and NS groups (7.10 ± 0.99 vs 24.30 ± 3.65; 14.30 ± 2.40 vs 24.30 ± 3.65, both P<0.05). Additionally, the DMOG group demonstrated higher expression of VEGF and HIF-1α in the flaps than the other groups (P < 0.05). In summary, HIF-1α enhances the expression of VEGF, promoting angiogenesis in the Choke II zone of the multiterritory perforator flap, thus increasing the survival area.

A novel translational model of atherosclerosis, the ex vivo pump-perfused amputated human limb model

The preclinical study of atherosclerosis has traditionally centred around the use of small animal models, translating to large animal models, prior to first-in-man studies. We propose to disrupt this paradigm by designing an ex vivo pump perfused human limb model. The novel model consists of taking a freshly amputated limb and incorporating it into an ex situ pump-perfused bypass system (akin to extracorporeal membrane oxygenation), circulating warmed, oxygenated blood. The circuit incorporates an introducer sheath and guiding catheter for intravascular imaging and X-ray angiography. Regular monitoring is performed using blood gas analysis, aiming for physiological parameters. The model maintains oxygen saturations > 99% for the length of perfusion (up to 6-h). Clinical grade X-ray angiography, intravascular ultrasound and optical coherence tomography have been successfully performed. Indocyanine green, a near-infrared fluorescent dye that localises to atherosclerotic plaque, has been injected into the system and left to circulate for 90-min. Fluorescence reflectance imaging of the dissected arterial bed confirmed uptake in areas of calcific atherosclerotic plaque on intravascular imaging. This is the first demonstration of an ex vivo pump-perfused “living” limb experimental model of atherosclerosis, which shows promise for future studies in translational interventional imaging and molecular targeting.

Optimizing neurointerventional procedures: an algorithm for embolization coil detection and automated collimation to enable dose reduction.

Monitoring radiation dose and time parameters during radiological interventions is crucial, especially in neurointerventional procedures, such as aneurysm treatment with embolization coils. The algorithm presented detects the presence of these embolization coils in medical images. It establishes a bounding box as a reference for automated collimation, with the primary objective being to enhance the efficiency and safety of neurointerventional procedures by actively optimizing image quality while minimizing patient dose. Two distinct methodologies are evaluated in our study. The first involves deep learning, employing the Faster R-CNN model with a ResNet-50 FPN as a backbone and a RetinaNet model. The second method utilizes a classical blob detection approach, serving as a benchmark for comparison. We performed a fivefold cross-validation, and our top-performing model achieved mean mAP@75 of 0.84 across all folds on validation data and mean mAP@75 of 0.94 on independent test data. Since we use an upscaled bounding box, achieving 100% overlap between ground truth and prediction is not necessary. To highlight the real-world applications of our algorithm, we conducted a simulation featuring a coil constructed from an alloy wire, effectively showcasing the implementation of automatic collimation. This resulted in a notable reduction in the dose area product, signifying the reduction of stochastic risks for both patients and medical staff by minimizing scatter radiation. Additionally, our algorithm assists in avoiding extreme brightness or darkness in X-ray angiography images during narrow collimation, ultimately streamlining the collimation process for physicians. To our knowledge, this marks the initial attempt at an approach successfully detecting embolization coils, showcasing the extended applications of integrating detection results into the X-ray angiography system. The method we present has the potential for broader application, allowing its extension to detect other medical objects utilized in interventional procedures.

Influence of anatomical structure on antiscatter grid performance in 2D: application to x-ray angiography and a prototype 29:1 ratio grid

Objective. The use of uniform phantoms to assess the influence of x-ray scatter and antiscatter grids on x-ray angiography and fluoroscopy image quality disregards the influence of spatially variable x-ray attenuation of patients. The purpose of this work was to measure scatter to primary ratio (SPR) and antiscatter grid SNR improvement factor (K SNR) using experimental conditions which better mimic patient imaging conditions. Approach. Three adult-sized anthropomorphic phantoms were used. AP and lateral projection images of the thorax and abdomen were acquired with and without an antiscatter grid. Grids with ratio 15:1 and 29:1 (r15, r29) and x-ray fields of view 20, 25 (thorax) and 32, 42 cm (abdomen) were tested. Combined with a-priori measurements of grid scatter and primary transmission fractions, these images were used to calculate 2D SPR and K SNR maps. Main results. Results demonstrated that measurements by uniform phantom do not describe the complex 2D SPR and K SNR distributions associated with anthropomorphic phantoms. The regions of the images with the lowest primary x-ray intensity (greatest attenuation) had the highest SPR and the highest K SNR attributable to the grids. Considering all conditions, the 95th percentile of the SPR maps was in the range 42%–185% greater than the median values and that of the K SNR maps was 4%–20% higher than the median values. The combined influences of SID 120 vs. 107 cm and r29 vs. r15 grid resulted in K SNR in the range 1.05–1.49. Significance. Performance of anti-scatter grids using anatomically complex phantoms highlights the substantial variation of SPR and K SNR within 2D images. Also, this work demonstrates the benefit of the prototype r29 grid for thoracic and abdominal angiography imaging conditions is substantial, especially for large patients and radiodense image regions.

Retrospective Comparative Analysis Of Accuracy Of Ct Angiography Versus X-ray Angiography In Patients With Severe Peripheral Artery Disease In An Outpatient Cardiology Private Practice

Retrospective Comparative Analysis Of Accuracy Of Ct Angiography Versus X-ray Angiography In Patients With Severe Peripheral Artery Disease In An Outpatient Cardiology Private Practice

Coronary Vessel Segmentation in X-ray Angiography Images Using Edge-Based Tracking Method

Automated extraction of coronary arteries is an essential process in the diagnosis of treatment for coronary artery disease (CAD) with computer assistance. Accurately outlining the coronary artery is difficult when using X-ray coronary angiography (XCA) because of the low signal-to-noise ratio and the presence of interfering background structures. In this paper, a new approach for segmenting vessels in angiograms is presented, specifically designed to tackle the difficulties arising from non-uniform illumination, artifacts, and noise present in angiographic images. The proposed method employs an edge-based tracking tool to generate an initial probability map for segmentation. A segmentation method based on coronary vessel tracking is presented for finding the border and centerline of the vessel. The proposed method is designed based on two main components: preprocessing and tracking. In the preprocessing stage, a guided filter and edge-sharpening algorithms are used to enhance the features of the original image. In the tracking stage, an initial point is selected, and using the Gaussian property, a semi-circle operator is applied to track the line perpendicular to the vessel. The proposed method demonstrated remarkable performance in terms of sensitivity and specificity, achieving values of 86.93 and 99.61, respectively. Additionally, the method achieved an accuracy rate of 97.81. Notably, the proposed method outperformed existing state-of-the-art segmentation methods, as indicated by its higher dice score. These impressive results signify a significant advancement in the field of vessel segmentation, highlighting the effectiveness and superiority of the proposed approach.

Deep Belief Bayesian Joint Conditional Detection of coronary artery plaque and stenosis in X-ray angiography images

Deep Belief Bayesian Joint Conditional Detection of coronary artery plaque and stenosis in X-ray angiography images

The Epidemiological Burden of Neurovascular Pathology in Nigeria: A Systematic Review and Pooled Patient-Level Analysis

Vascular neurosurgery has developed significantly in Nigeria, but its burden and challenges remain unclear. This study systematically reviewed vascular neurosurgical literature from Nigeria. Four research databases and gray literature sources were searched from 1962-2021. ROBINS-I tool was used to assess risk of bias. Descriptive, narrative, and statistical analyses were conducted on all variables. Where appropriate, paired t-tests and Chi-squared independence tests were used (α= 0.05). 56 articles were included and 3203 patients pooled for analysis. Risk of bias was moderate-high. Most articles were published over the last 20 years with retrospective cohort studies and case reports being the most common study designs. The cohort had a relatively even gender split and an average age of 49 years (±22). Cerebrovascular accidents accounted for over 85% of diagnoses, with most etiologies being traumatic. Headache and motor deficit were the most prevalent clinical features. X-ray and carotid angiography were the most commonly reported imaging modalities, closely followed by computed tomography (CT) and CT angiography. The top two radiological diagnoses were ischemic cerebrovascular disease and intracerebral hematoma. Aneurysmal clipping and hematoma evacuation were the most commonly reported treatment modalities. Outcome at last follow-up was favorable in 48%. The mortality rate was 6%. Post-treatment complications included chest infection and rebleeding. This study illustrates the epidemiological burden of neurovascular pathology (based on the available data in published literature) in Nigeria, and raises awareness amongst service providers and researchers of the attendant challenges and epochal trends seen within vascular neurosurgery in Nigeria.

DFA-Net: Dual multi-scale feature aggregation network for vessel segmentation in X-ray digital subtraction angiography

Even though deep learning is fascinated in fields of coronary vessel segmentation in X-ray angiography and achieves prominent progresses, most of those models probably bring high false and missed detections due to indistinct contrast between coronary vessels and background, especially for tiny sub-branches. Image improvement technique is able to better such contrast, while boosting extraneous information, e.g., other tissues with similar intensities and noise. If incorporating features derived from original and enhanced images, the segmentation performance is improved because those images comprise complementary information from different contrasts. Accordingly, inspired from advantages of contrast improvement and encoding-decoding architecture, a dual multi-scale feature aggregation network (named DFA-Net) is introduced for coronary vessel segmentation in digital subtraction angiography (DSA). DFA-Net integrates the contrast improvement using exponent transformation into a semantic segmentation network that individually accepts original and enhanced images as inputs. Through parameter sharing, multi-scale complementary features are aggregated from different contrasts, which strengthens leaning capabilities of networks, and thus achieves an efficient segmentation. Meanwhile, a risk cross-entropy loss is enforced on the segmentation, for availably decreasing false negatives, which is incorporated with Dice loss for joint optimization of the proposed strategy during training. Experimental results demonstrate that DFA-Net can not only work more robustly and effectively for DSA images under diverse conditions, but also achieve better performance, in comparison with state-of-the-art methods. Consequently, DFA-Net has high fidelity and structure similarity to the reference, providing a way for early diagnosis of cardiovascular diseases.

Digital variance angiography in patients undergoing lower limb arterial recanalization: cost-effectiveness analysis within the English healthcare setting.

Aim: Digital variance angiography (DVA) is a recently developed image processing method capable of improving image quality compared with the traditionally used digital subtraction angiography (DSA), among patients undergoing lower limb x-ray angiography. This study aims to explore the potential cost-effectiveness of DVA from an English National Health Service perspective. Materials & methods: A two-part economic model, consisting of a decision tree and a Markov model, was developed to consider the costs and health outcomes associated with the use of DVA as part of current practice imaging, compared with x-ray angiography using standard DSA. The model explored the impact of DVA on the development of acute kidney injury (AKI), chronic kidney disease and radiation-induced cancer over a lifetime horizon. Both deterministic and probabilistic analyses were performed to assess the cost per quality-adjusted life-year (QALY). Results: Base-case results indicate that DVA results in cost savings of £309 per patient, with QALYs also improving (+0.025) over a lifetime. As shown in sensitivity analysis, a key driver of model results is the relative risk (RR) reduction of contrast-associated acute kidney injury associated with use of DVA. The intervention also decreases the risk of carcinoma over a lifetime. Scenario analyses show that cost savings range from £310 to £553, with QALY gains ranging from 0.048 to 0.109 per patient. Conclusion: The use of DVA could result in a decrease in costs and an increase in QALYs over a lifetime, compared with existing imaging practice. The potential for this technology to offer an economically viable alternative to existing image processing methods, through a reduction in contrast media volume and radiation exposure, has been demonstrated.

Experience of Morphologic Left Ventricle Training in Congenitally Corrected Transposition of the Great Arteries in Children: Evaluation of the Operation Results

The aim. To evaluate the efficacy of morphologic left ventricle (mLV) training through pulmonary artery banding (PAB) in pediatric patients with congenitally corrected transposition of the great arteries.&#x0D; Materials and methods. From 2003 to 2023, 12 patients underwent PAB for mLV training at the Ukrainian Children`s Cardiac Center. The mean age of the patients was 30.3 ± 25.1 months, the mean weight was 11.6 ± 5.2 kg. Hemodynamic parameters were assessed to determine the size of the band applied to the pulmonary artery (PA) trunk during the operation. Intraoperative transesophageal echocardiography was performed in 6 patients. Transthoracic echocardiography (TTE) was performed in the early postoperative period. In the remote period, all the patients underwent TTE and X-ray angiography.&#x0D; Results. During PAB, the mLV pressure averaged 58 ± 12.6% (from 40% to 80%) of the systemic arterial pressure. PAB dilatation was required for one patient in the early postoperative period (postoperative day 2) because of significant hemodynamic changes. In the early postoperative period, the maximum gradient across PA measured by TTE averaged 39.3 ± 10.0 mm Hg (from 25 to 60 mm Hg). There was no hospital mortality.&#x0D; The follow-up period averaged 47.2 ± 26.0 months (8 to 113 months). In the long-term observation period, 2 patients (16.6%) died, one 8 months and the other 5 years after the operation. The double switch operation was performed in 6 patients, on average, 48.2 ± 6.9 months after PAB. According to angiography, the mLV pressure before the double switch operation was 90.2 ± 11.6% of that in the systemic right ventricle. The end-diastolic pressure in the mLV averaged 14 ± 4.1 mm Hg. The peak pressure gradient across the PA measured by echo was 81.3 ± 28.8 mm Hg. The mLV mass index averaged 62.9 ± 8.8 g/m2, the mLV ejection fraction averaged 61.2 ± 2.9%. Overall radiographic and echocardiographic data in these patients indicated that mLV is trained and capable of performing the role of a systemic ventricle after anatomical correction.&#x0D; Conclusions. PA banding as a method of mLV training can be used in patients with congenitally corrected transposition of the great arteries with intact ventricular septum, restrictive ventricular septal defects and severe tricuspid regurgitation.&#x0D; To evaluate the effectiveness of PAB for mLV training, a multimodal diagnostic approach is used, including non-invasive and invasive methods such as TTE, transesophageal echocardiography, and cardiac catheterization. The optimal age for PAB in patients of this group for the purpose of training the LV was on average 2-2.5 years.

Coronary physiology instantaneous wave-free ratio (iFR) derived from x-ray angiography using artificial intelligence deep learning models: a pilot study.

Coronary angiography (CAG)-derived physiology methods have been developed in an attempt to simplify and increase the usage of coronary physiology, based mostly on dynamic fluid computational algorithms. We aimed to develop a different approach based on artificial intelligence methods, which has seldom been explored. Consecutive patients undergoing invasive instantaneous free-wave ratio (iFR) measurements were included. We developed artificial intelligence (AI) models capable of classifying target lesions as positive (iFR ≤ 0.89) or negative (iFR > 0.89). The predictions were then compared to the true measurements. Two hundred-fifty measurements were included, and 3 models were developed. Model 3 had the best overall performance: accuracy, negative predictive value (NPV), positive predictive value (PPV), sensitivity, and specificity were 69%, 88%, 44%, 74%, and 67%, respectively. Performance differed per target vessel. For the left anterior descending artery (LAD), model 3 had the highest accuracy (66%), while model 2 the highest NPV (86%) and sensitivity (91%). PPV was always low/modest. Model 1 had the highest specificity (68%). For the right coronary artery, model 1's accuracy was 86%, NPV was 97%, and specificity was 87%, but all models had low PPV (maximum 25%) and low/modest sensitivity (maximum 60%). For the circumflex, model 1 performed best: accuracy, NPV, PPV, sensitivity, and specificity were 69%, 96%, 24%, 80%, and 68%, respectively. We developed 3 AI models capable of binary iFR estimation from CAG images. Despite modest accuracy, the consistently high NPV is of potential clinical significance, as it would enable avoiding further invasive maneuvers after CAG. This pivotal study offers proof of concept for further development.

Co-registered optical coherence tomography and X-ray angiography for the prediction of fractional flow reserve.

Cardiovascular disease (CVD) stands as the leading global cause of mortality, and coronary artery disease (CAD) has the highest prevalence, contributing to 42% of these fatalities. Recognizing the constraints inherent in the anatomical assessment of CAD, Fractional Flow Reserve (FFR) has emerged as a pivotal functional diagnostic metric. Herein, we assess the potential of employing an ensemble approach with deep neural networks (DNN) to predict invasively measured Fractional Flow Reserve (FFR) using raw anatomical data extracted from both optical coherence tomography (OCT) and X-ray coronary angiography (XA). In this study, we used a challenging dataset, with 46% of the lesions falling within the FFR range of 0.75 to 0.85. Despite this complexity, our model achieved an accuracy of 84.3%, demonstrating a sensitivity of 87.5% and a specificity of 81.4%. Our results demonstrate that incorporating both OCT and XA signals, co-registered, as inputs for the DNN model leads to an important increase in overall accuracy.

CIDN: A context interactive deep network with edge-aware for X-ray angiography images segmentation

Accurate segmentation of X-ray angiography images is imperative for cardiovascular disease diagnosis. Despite significant strides in segmentation through deep learning, challenges persist in precisely delineating vessel edges. This paper introduces a Context Interactive Deep Network (CIDN) tailored for coronary vessel segmentation. CIDN integrates a Bio-inspired Attention Block (BAB) and a Multi-scale Interactive Block (MIB) to optimize the capture of spatial and edge information. The encoder-decoder facilitates optimal interaction between low-level features and high-level semantics. A compound loss function, amalgamating binary cross-entropy and active contour elasticity loss, enhances the recognition of intricate vessel edges. In experiments conducted on both public and private X-ray contrast images, the CIDN exhibits superior performance compared to the state-of-the-art Spatial Multi-scale Attention U-improved Network (SMAU-Net). Specifically, on dataset DCA1, the F1 value reached 0.7675, with an accuracy of 0.9795. Furthermore, on dataset JMA, the CIDN model achieved an F1 value of 0.8732, coupled with an accuracy of 0.9757. Accurate segmentation provides clinicians with precise vessel depictions, aiding in the identification of coronary stenosis and facilitating more informed diagnostic and therapeutic decisions.

DYNAMICS OF CHANGES IN THE VASCULAR BED AND ORGANOMETRICAL INDICATORS OF WHITE RATS TESTICLES DURING EXPERIMENTAL SKIN THERMAL INJURY AND UNDER THE CORRECTION WITH A XENODERMAL SUBSTRATE

DYNAMICS OF CHANGES IN THE VASCULAR BED AND ORGANOMETRICAL INDICATORS OF WHITE RATS TESTICLES DURING EXPERIMENTAL SKIN THERMAL INJURY AND UNDER THE CORRECTION WITH A XENODERMAL SUBSTRATE

Signal-difference-to-noise comparison of temporal subtraction, kV-switching dual-energy and photon-counting dual-energy x-ray angiography.

Dual-energy (DE) x-ray angiography with photon-counting detectors (PCDs) may enable single-exposure DE imaging of coronaryvasculature. To compare the iodine signal-difference-to-noise ratio (SDNR) of single-exposure DE angiography with digital subtraction angiography (DSA) and kV-switching DE angiography for matched patient x-rayexposure. In a phantom study, we determined the technique parameters that maximized the iodine SDNR per root entrance air kerma for DSA, kV-switching DE angiography and single-exposure DE angiography. We measured SDNR from images of a phantom consisting of an iodine step-wedge immersed in a water tank of either 20 or 30cm in thickness. We also imaged a phantom with simulated vessels embedded in background clutter and measured vessel SDNR. For this second phantom, we also applied anti-correlated noise reduction (ACNR) and calculated the resulting iodine SDNR. All images were acquired using a cadmium telluride PCD with two energy bins and analog charge summing for charge sharing suppression. The energy-discrimination capabilities were only used for the single-exposure DE approach. Optimized techniques were compared in terms of SDNR per root air kerma for two levels of x-rayscatter. For the same patient x-ray exposure, the SDNR of single-exposure DE imaging without ACNR was 75% to 85% of that of kV-switching DE imaging (also without ACNR) and DSA, the latter two of which had nearly equal SDNR. The single-exposure DE approach required ∼50% of the tube load of the kV-switching approach to achieve the same SDNR. For matched patient air kermas, the single exposure approach required only ∼25% of the tube load of the kV-switching approach. ACNR increased SDNR by 2.4 and 3.0 for kV-switching and single-exposure DE imaging,respectively. Photon-counting, single-exposure DE angiography can suppress soft tissues and provide iodine SDNR levels comparable to DSA and kV-switching DE angiography for matched patient radiation exposures. When ACNR is used to reduce DE image noise, the SDNR of single-exposure DE imaging and kV-switching DE imaging exceed that of DSA by more than a factor of two. Compared to kV-switching DE imaging, single-exposure DE imaging requires substantially lower tube loading to achieve the sameSDNR.

A framework of myocardial bridge detection with x-ray angiography sequence

BackgroundMyocardial bridges are congenital anatomical abnormalities in which myocardium covers a segment of coronary arteries, leading to stenocardia, myocardial ischemia, and sudden cardiac death in severe cases. However, automatic diagnosis of myocardial bridge presents significant challenges.MethodA novel framework of myocardial bridge detection with x-ray angiography sequence is proposed, which can realize automatic detection of vessel stenosis and myocardial bridge. Firstly, we employ a novel neural network model for coronary vessel segmentation, which consists of both CNNs and transformer structures to effectively extract both local and global information of the vessels. Secondly, we describe the vessel segment information, establish the vessel tree in the image, and fuse the vessel tree information between sequences. Finally, based on vessel stenosis detection, we realize automatic detection of the myocardial bridge by querying the blood vessels between the image sequence information.ResultsIn experiment, we evaluate the segmentation results using two metrics, Dice and ASD, and achieve scores of 0.917 and 1.39, respectively. In the stenosis detection, we achieve an average accuracy rate of 92.7% in stenosis detection among 262 stenoses. In multi-frame image processing, vessels in different frames can be well-matched, and the accuracy of myocardial bridge detection achieves 75%.ConclusionsOur experimental results demonstrate that the algorithm can automatically detect stenosis and myocardial bridge, providing a new idea for subsequent automatic diagnosis of coronary vessels.

A multi-stage neural network approach for coronary 3D reconstruction from uncalibrated X-ray angiography images

We present a multi-stage neural network approach for 3D reconstruction of coronary artery trees from uncalibrated 2D X-ray angiography images. This method uses several binarized images from different angles to reconstruct a 3D coronary tree without any knowledge of image acquisition parameters. The method consists of a single backbone network and separate stages for vessel centerline and radius reconstruction. The output is an analytical matrix representation of the coronary tree suitable for downstream applications such as hemodynamic modeling of local vessel narrowing (i.e., stenosis). The network was trained using a dataset of synthetic coronary trees from a vessel generator informed by both clinical image data and literature values on coronary anatomy. Our multi-stage network achieved sub-pixel accuracy in reconstructing vessel radius (RMSE = 0.16 ± 0.07 mm) and stenosis radius (MAE = 0.27 ± 0.18 mm), the most important feature used to inform diagnostic decisions. The network also led to 52% and 38% reduction in vessel centerline reconstruction errors compared to a single-stage network and projective geometry-based methods, respectively. Our method demonstrated robustness to overcome challenges such as vessel foreshortening or overlap in the input images. This work is an important step towards automated analysis of anatomic and functional disease severity in the coronary arteries.

Assessment of the Dimensions of Coronary Arteries for the Manifestation of Coronary Artery Disease.

The size of the coronary artery influences the effective outcome of therapeutic measures like coronary artery bypass graft (CABG) surgery, percutaneous coronary interventions (PCI), and diagnosis of coronary artery disease. Patients' age, gender, BMI, anatomical variations, and increased left ventricular size all have an effect on coronary artery parameters. This study aims to compare the average size of the coronary arteries of the Pakistani population in both sexes for manifestation of coronary artery disease. For the analysis of the coronary arteries, 100 patients of both sexes, male and female, were taken. X-ray angiography was performed for two-dimensional images of coronary arteries. For diameter measurement, images were visualized on quantitative coronary angiography (QCA) in different views (caudal and cranial views). The diameters of the left main coronary artery (left main stem/LMS), left anterior descending (LAD), left circumflex (LCx), and right coronary artery (RCA) were measured on angiograms. Data about the dimensions of the coronary artery was gathered through quantitative angiography. Data analysis was done throughSPSS version 26 (IBM Corp., Armonk, NY). There is a notable distinction in the average diameters among the proximal LAD (3.12), mid-LAD (2.40), and distal LAD (1.29). A statistically significant difference is evident among mid-LCx, distal LCx, and proximal LCx (p-value < 0.001). Likewise, the average diameter of the distal RCA (1.89) was smaller when compared to the mid-RCA (3.19) and proximal RCA (3.78). However, there was no significant difference in the average diameter among mid-LMS, distal LMS, and proximal LMS (p-value = 0.09). The average diameter of distal RCA was smaller when compared to mid-RCA and proximal RCA. The average size of proximal LAD and proximal LCx was comparatively larger than mid- and distal LAD and LCx. The findings of current research will be beneficial for the diagnosis and management of coronary artery disease patients.