Detection Of Coronary Artery Stenosis Research Articles

A Preprocessing Method for Coronary Artery Stenosis Detection Based on Deep Learning

The detection of coronary artery stenosis is one of the most important indicators for the diagnosis of coronary artery disease. However, stenosis in branch vessels is often difficult to detect using computer-aided systems and even radiologists because of several factors, such as imaging angle and contrast agent inhomogeneity. Traditional coronary artery stenosis localization algorithms often only detect aortic stenosis and ignore branch vessels that may also cause major health threats. Therefore, improving the localization of branch vessel stenosis in coronary angiographic images is a potential development property. In this study, we propose a preprocessing approach that combines vessel enhancement and image fusion as a prerequisite for deep learning. The sensitivity of the neural network to stenosis features is improved by enhancing the blurry features in coronary angiographic images. By validating five neural networks, such as YOLOv4 and R-FCN-Inceptionresnetv2, our proposed method can improve the performance of deep learning network applications on the images from six common imaging angles. The results showed that the proposed method is suitable as a preprocessing method for coronary angiographic image processing based on deep learning and can be used to amend the recognition ability of the deep model for fine vessel stenosis.

Relationship between Coronary Artery Calcium Score and Coronary Stenosis.

The coronary artery calcium score (CACS) is commonly employed to quantify the degree of calcification in coronary atherosclerosis. Indeed, increased coronary stenosis severity is associated with a progressive increase in CACS. This study sought to explore the association between CACS and coronary stenosis of ≥50% and ≥70%. We conducted a retrospective analysis of patient data collected between July 1, 2017, and March 3, 2022, at Jiangmen Central Hospital. A total of 208 patients, presenting with both symptomatic and asymptomatic manifestations and suspected coronary artery disease (CAD), were included. Statistical analyses included ROC curve assessments, subgroup analyses based on age, and comparisons of CACS values against the presence of coronary stenosis ≥50% and ≥70%. Ultimately, 208 patients were included, with a median age of 65.0 years and a median CACS of 115.7 (interquartile range: 13.7-369.4). A CACS threshold of ≥1300 demonstrated a specificity of 100% for coronary stenosis of ≥50%. Notably, the percentage of patients with obstructive CAD showing CACS = 0 was significantly higher in those under 65 years (15.1%) compared to patients over 65 years (3.8%) (P=0.005). The inflection point, at which the risk probability for coronary stenosis of ≥50% shifted from being a protective factor to a risk factor, was observed when CACS fell within the range of 63.3 to 66.0. CACS demonstrates good performance for the detection of coronary artery stenosis.

Abstract 14804: Automated Semantic Segmentation and Stenosis Detection of Coronary Arteries on Invasive Coronary Angiograms Using Hypergraph Matching and Information Fusion

Background: Invasive coronary angiography (ICA) remains the gold standard for diagnosing CAD. Our objective was to develop a machine learning method for coronary semantic segmentation and stenosis detection in ICA. Method: We first extract coronary artery branches using ICAs and convert the vascular tree into ICA graphs. Then, we construct the hyper association graph from two individual ICA graphs. The vertex in the hyper association graph encodes the correspondence between two artery branches, and each hyperedge represents the correspondence between multiple artery branches. Hypergraph matching is used to find feature correspondence by considering higher-order structural information, and the artery semantic labeling task is converted into a vertex classification. Ultimately, by learning the semantic mapping of artery branches between ICAs, the unlabeled arteries are categorized by labeled arteries so that semantic segmentation is achieved. After performing the semantic labeling, a deterministic network performs stenosis detection. More specifically, a convolution long-short-term network is employed to extract imaging features, and an LSTM is employed to extract the radius features along the artery. The late fusion technology is employed to fuse the feature representation, and a softmax classifier is employed to detect the stenosis. Results: 310 ICAs from 179 subjects were collected and utilized for data analysis. Our graph-matching model achieved an average accuracy of 0.86 for coronary artery semantic labeling. The deterministic network achieved an accuracy of 0.80 for coronary artery stenosis detection. Conclusion: We have developed and validated a hypergraph-based graph-matching algorithm for coronary semantic labeling and a fusion network for artery stenosis detection. This has important implications for integrating AI software in ICA, potentially resulting in automated report generation or as an assistant for clinical decision-making.

Artificial intelligence-based opportunistic detection of coronary artery stenosis on aortic computed tomography angiography in emergency department patients with acute chest pain.

To evaluate a deep-learning model (DLM) for detecting coronary stenoses in emergency room patients with acute chest pain (ACP) explored with electrocardiogram-gated aortic computed tomography angiography (CTA) to rule out aortic dissection. This retrospective study included 217 emergency room patients (41% female, mean age 67.2 years) presenting with ACP and evaluated by aortic CTA at our institution. Computed tomography angiography was assessed by two readers, who rated the coronary arteries as 1 (no stenosis), 2 (<50% stenosis), or 3 (≥50% stenosis). Computed tomography angiography was categorized as high quality (HQ), if all three main coronary arteries were analysable and low quality (LQ) otherwise. Curvilinear coronary images were rated by a DLM using the same system. Per-patient and per-vessel analyses were conducted. One hundred and twenty-one patients had HQ and 96 LQ CTA. Sensitivity, specificity, positive predictive value, negative predictive value (NPV), and accuracy of the DLM in patients with high-quality image for detecting ≥50% stenoses were 100, 62, 59, 100, and 75% at the patient level and 98, 79, 57, 99, and 84% at the vessel level, respectively. Sensitivity was lower (79%) for detecting ≥50% stenoses at the vessel level in patients with low-quality image. Diagnostic accuracy was 84% in both groups. All 12 patients with acute coronary syndrome (ACS) and stenoses by invasive coronary angiography (ICA) were rated 3 by the DLM. A DLM demonstrated high NPV for significant coronary artery stenosis in patients with ACP. All patients with ACS and stenoses by ICA were identified by the DLM.

A U-Shaped Network Based on Multi-level Feature and Dual-Attention Coordination Mechanism for Coronary Artery Segmentation of CCTA Images.

Computed tomography coronary angiography (CCTA) images provide optimal visualization of coronary arteries to aid in diagnosing coronary heart disease (CHD). With the deep convolutional neural network, this work aims to develop an intelligent and lightweight coronary artery segmentation algorithm that can be deployed in hospital systems to assist clinicians in quantitatively analyzing CHD. With the multi-level feature fusion, we proposed Dual-Attention Coordination U-Net (DAC-UNet) that achieves automated coronary artery segmentation in 2D CCTA images. The coronary artery occupies a small region, and the foreground and background are extremely unbalanced. For this reason, the more original information can be retained by fusing related features between adjacent layers, which is conducive to recovering the small coronary artery area. The dual-attention coordination mechanism can select valid information and filter redundant information. Moreover, the complementation and coordination of double attention factors can enhance the integrity of features of coronary arteries, reduce the interference of non-coronary arteries, and prevent over-learning. With gradual learning, the balanced character of double attention factors promotes the generalization ability of the model to enhance coronary artery localization and contour detail segmentation. Compared with existing related segmentation methods, our method achieves a certain degree of improvement in 2D CCTA images for the segmentation accuracy of coronary arteries with a mean Dice index of 0.7920. Furthermore, the method can obtain relatively accurate results even in a small sample dataset and is easy to implement and deploy, which is promising. The code is available at: https://github.com/windfly666/Segmentation . Our method can capture the coronary artery structure end-to-end, which can be used as a fundamental means for automatic detection of coronary artery stenosis, blood flow reserve fraction analysis, and assisting clinicians in diagnosing CHD.

An Increased Diagnostic Accuracy of Significant Coronary Artery Stenosis Using 320-slice Computed Tomography with Model-based Iterative Reconstruction in Cases with Severely calcified Coronary Arteries.

Purpose High-quality images can be obtained with 320-slice computed tomography (CT) with model-based iterative reconstruction (MBIR). We therefore investigated the diagnostic accuracy of 320-slice CT with MBIR for detecting significant coronary artery stenosis. Methods This was a retrospective study of 160 patients who underwent coronary CT and invasive coronary angiography (ICA). The first 100 consecutive patients (Group 1) underwent 320-slice CT without MBIR or small-focus scanning. The next 60 consecutive patients (Group 2) underwent 320-slice CT with both MBIR and small-focus scanning. Patients who underwent coronary artery bypass surgery were excluded. The diagnostic performance of 320-slice CT without MBIR or small-focus scanning and 320-slice CT with both of them, with ICA regarded as a reference standard, was compared to detect significant coronary artery stenosis (≥70% on CT, ≥75% on ICA). Results In a patient-based analysis, the sensitivity, specificity, and overall accuracy of detection of significant stenosis on CT against ICA were 95%, 85%, and 91% in Group 1, and 93%, 83%, and 90% in Group 2, respectively. No significant differences were observed between the two groups in the patient- and segment-based analyses. However, among cases with a severe coronary artery calcium score >400 (31 cases in Group 1 and 28 in Group 2), the specificity and overall accuracy were significantly higher (all p<0.01) in Group 2 than in Group 1 according to the segment-based analysis. Conclusion The diagnostic accuracy of the detection of coronary artery stenosis on CT was improved using 320-slice CT with MBIR.

Coronary artery stenosis detection via proposal-shifted spatial-temporal transformer in X-ray angiography

Accurate detection of coronary artery stenosis in X-ray angiography (XRA) images is crucial for the diagnosis and treatment of coronary artery disease. However, stenosis detection remains a challenging task due to complicated vascular structures, poor imaging quality, and fickle lesions. While devoted to accurate stenosis detection, most methods are inefficient in the exploitation of spatio-temporal information of XRA sequences, leading to a limited performance on the task. To overcome the problem, we propose a new stenosis detection framework based on a Transformer-based module to aggregate proposal-level spatio-temporal features. In the module, proposal-shifted spatio-temporal tokenization (PSSTT) scheme is devised to gather spatio-temporal region-of-interest (RoI) features for obtaining visual tokens within a local window. Then, the Transformer-based feature aggregation (TFA) network takes the tokens as the inputs to enhance the RoI features by learning the long-range spatio-temporal context for final stenosis prediction. The effectiveness of our method was validated by conducting qualitative and quantitative experiments on 233 XRA sequences of coronary artery. Our method achieves a high F1 score of 90.88%, outperforming other 15 state-of-the-art detection methods. It demonstrates that our method can perform accurate stenosis detection from XRA images due to the strong ability to aggregate spatio-temporal features.

DIAGNOSTIC ACCURACY OF CT CORONARY ANGIOGRAPHY.

Coronary Artery Disease (CAD) is an emerging and commonest type of heart disease resulting in morbidity and mortality globally. Coronary angiography is a diagnostic modality used to diagnose the coronary artery disease or the extent of blockage of coronary arteries. The multi-slice computed tomography (MSCT) technology such as 64-slice, 128-slice, 256-slice, and now 320-slice MSCT has produced a high diagnostic accuracy of CT coronary angiography. This prospective-cross sectional study was done in Department of Cardiology in Medanta, the Medicity, from November 2017 to December 2018 with the aim to evaluate the diagnostic accuracy of 256 slice CT coronary angiogram in measuring the percentage diameter stenosis compared to invasive angiography and to determine the sensitivity and specicity of CT coronary angiography in detection of coronary artery stenosis among symptomatic patients. A total of 60 patients presented with acute or chronic chest pain with risk for CAD were included. The mean age of the participants was 57.35±10.16 years and 88.3% participants were male and 11.7% participants were females. 56.6% participants had BMI &gt;25, 11.7% were alcoholic, 40% were smoker, 16.7% had diabetes and 38.3% had hypertension. The study concluded that CCTA should be considered initial test of choice in patients presenting with chest pain with low to intermediate probability of CAD because the time required for diagnosis is signicantly shorter, high sensitivity, specicity, PPV and NPV on per vessel and per segment basis, determination of LVEF and has the ability to rule out causes of atypical chest pain including pulmonary embolism and aortic dissection.

New applications of cardiac computed tomography for evaluation of myocardial ischemia

MSCT is known for its extremely high diagnostic accuracy in coronary artery stenosis detection and quantification. However, there are still questions about physiological assessment of myocardial ischemia, since the degree of arterial stenosis and clinical outcomes do not always correlate. It is also noted that the exclusive use of functional non-invasive tests to assess the grade of stenosis can lead to false-negative results and worsen the long-term prognosis of cardiovascular events. Thus, the combined use of anatomical and functional tests can improve the prognosis in coronary heart disease patient. MSCT coronary angiography, combined with stress perfusion and/or CT derived fractional flow reserve, could be used as an all-in-one approach. This review describes new applications of cardiac MSCT.

New applications of cardiac computed tomography for evaluation of myocardial ischemia

MSCT is known for its extremely high diagnostic accuracy in coronary artery stenosis detection and quantification. However, there are still questions about physiological assessment of myocardial ischemia, since the degree of arterial stenosis and clinical outcomes do not always correlate. It is also noted that the exclusive use of functional non-invasive tests to assess the grade of stenosis can lead to false-negative results and worsen the long-term prognosis of cardiovascular events. Thus, the combined use of anatomical and functional tests can improve the prognosis in coronary heart disease patient. MSCT coronary angiography, combined with stress perfusion and/or CT derived fractional flow reserve, could be used as an all-in-one approach. This review describes new applications of cardiac MSCT.

Diagnostic Value of Multidetector Computer Tomography Coronary Angiography in Detection of Coronary Artery Stenosis

Diagnostic Value of Multidetector Computer Tomography Coronary Angiography in Detection of Coronary Artery Stenosis

Diagnostic Accuracy and Generalizability of a Deep Learning-Based Fully Automated Algorithm for Coronary Artery Stenosis Detection on CCTA: A Multi-Centre Registry Study.

Aims: In this retrospective, multi-center study, we aimed to estimate the diagnostic accuracy and generalizability of an established deep learning (DL)-based fully automated algorithm in detecting coronary stenosis on coronary computed tomography angiography (CCTA).Methods and results: A total of 527 patients (33.0% female, mean age: 62.2 ± 10.2 years) with suspected coronary artery disease (CAD) who underwent CCTA and invasive coronary angiography (ICA) were enrolled from 27 hospitals from January 2016 to August 2019. Using ICA as a standard reference, the diagnostic accuracy of the DL algorithm in the detection of ≥50% stenosis was compared to that of expert readers. In the vessel-based evaluation, the DL algorithm had a higher sensitivity (65.7%) and negative predictive value (NPV) (78.8%) and a significantly higher area under the curve (AUC) (0.83, p < 0.001). In the patient-based evaluation, the DL algorithm achieved a higher sensitivity (90.0%), NPV (52.2%) and AUC (0.81). Generalizability analysis of the DL algorithm was conducted by comparing its diagnostic performance in subgroups stratified by sex, age, geographic area and CT scanner type. The AUCs of the DL algorithm in the aforementioned subgroups ranged from 0.79 to 0.86 and from 0.75 to 0.93 in the vessel-based and patient-based evaluations, both without significant group differences (p > 0.05). The DL algorithm significantly reduced post-processing time (160 [IQR:139–192] seconds), in comparison to manual work (p < 0.001).Conclusions: The DL algorithm performed no inferior to expert readers in CAD diagnosis on CCTA and had good generalizability and time efficiency.

Analysis of Deep Neural Networks for Detection of Coronary Artery Stenosis

Analysis of Deep Neural Networks for Detection of Coronary Artery Stenosis

Real-time coronary artery stenosis detection based on modern neural networks

Invasive coronary angiography remains the gold standard for diagnosing coronary artery disease, which may be complicated by both, patient-specific anatomy and image quality. Deep learning techniques aimed at detecting coronary artery stenoses may facilitate the diagnosis. However, previous studies have failed to achieve superior accuracy and performance for real-time labeling. Our study is aimed at confirming the feasibility of real-time coronary artery stenosis detection using deep learning methods. To reach this goal we trained and tested eight promising detectors based on different neural network architectures (MobileNet, ResNet-50, ResNet-101, Inception ResNet, NASNet) using clinical angiography data of 100 patients. Three neural networks have demonstrated superior results. The network based on Faster-RCNN Inception ResNet V2 is the most accurate and it achieved the mean Average Precision of 0.95, F1-score 0.96 and the slowest prediction rate of 3 fps on the validation subset. The relatively lightweight SSD MobileNet V2 network proved itself as the fastest one with a low mAP of 0.83, F1-score of 0.80 and a mean prediction rate of 38 fps. The model based on RFCN ResNet-101 V2 has demonstrated an optimal accuracy-to-speed ratio. Its mAP makes up 0.94, F1-score 0.96 while the prediction speed is 10 fps. The resultant performance-accuracy balance of the modern neural networks has confirmed the feasibility of real-time coronary artery stenosis detection supporting the decision-making process of the Heart Team interpreting coronary angiography findings.

Stenosis-DetNet: Sequence consistency-based stenosis detection for X-ray coronary angiography.

The automatic detection of coronary artery stenosis on X-ray images is important in coronary heart disease diagnosis. Conventional methods cannot accurately detect all stenosis areas because of heartbeat, respiratory movements and weak vascular features in single-frame contrast images. This paper proposes the use of Stenosis-DetNet, which is a method based on object detection networks. A sequence feature fusion module and a sequence consistency alignment module are designed to maximize temporal information to achieve accurate detection results. The sequence feature fusion module fuses all candidate box features and uses the temporal information to enhance these features. The sequence consistency alignment module optimizes the initial results by using the coronary artery displacement information and image features of the adjacent images and leads to the final detection of coronary artery stenosis. In the experiment, 166 X-ray image sequences were used for training and testing. Compared with the three existing stenosis detection methods, the precision and sensitivity of Stensis-DetNet were 94.87 % and 82.22 %, respectively, which were better than those of the other three methods. Our proposed method effectively suppressed the false positive and false negative results of stenosis detection in sequence angiography images. It was superior to the state-of-art methods.

Deep Learning CT Image Reconstruction in Clinical Practice.

Computed tomography (CT) is a central modality in modern radiology contributing to diagnostic medicine in almost every medical subspecialty, but particularly in emergency services. To solve the inverse problem of reconstructing anatomical slice images from the raw output the scanner measures, several methods have been developed, with filtered back projection (FBP) and iterative reconstruction (IR) subsequently providing criterion standards. Currently there are new approaches to reconstruction in the field of artificial intelligence utilizing the upcoming possibilities of machine learning (ML), or more specifically, deep learning (DL). This review covers the principles of present CT image reconstruction as well as the basic concepts of DL and its implementation in reconstruction. Subsequently commercially available algorithms and current limitations are being discussed. DL is an ML method that utilizes a trained artificial neural network to solve specific problems. Currently two vendors are providing DL image reconstruction algorithms for the clinical routine. For these algorithms, a decrease in image noise and an increase in overall image quality that could potentially facilitate the diagnostic confidence in lesion conspicuity or may translate to dose reduction for given clinical tasks have been shown. One study showed equal diagnostic accuracy in the detection of coronary artery stenosis for DL reconstructed images compared to IR at higher image quality levels. Consequently, a lot more research is necessary and should aim at diagnostic superiority in the clinical context covering a broadness of pathologies to demonstrate the reliability of such DL approaches. · Following iterative reconstruction, there is a new approach to CT image reconstruction in the clinical routine using deep learning (DL) as a method of artificial intelligence.. · DL image reconstruction algorithms decrease image noise, improve image quality, and have potential to reduce radiation dose.. · Diagnostic superiority in the clinical context should be demonstrated in future trials.. · Arndt C, Güttler F, Heinrich A et al. Deep Learning CT Image Reconstruction in Clinical Practice. Fortschr Röntgenstr 2021; 193: 252 - 261.

Transfer Learning for Stenosis Detection in X-ray Coronary Angiography

Coronary artery disease is the most frequent type of heart disease caused by an abnormal narrowing of coronary arteries, also called stenosis or atherosclerosis. It is also the leading cause of death globally. Currently, X-ray Coronary Angiography (XCA) remains the gold-standard imaging technique for medical diagnosis of stenosis and other related conditions. This paper presents a new method for the automatic detection of coronary artery stenosis in XCA images, employing a pre-trained (VGG16, ResNet50, and Inception-v3) Convolutional Neural Network (CNN) via Transfer Learning. The method is based on a network-cut and fine-tuning approach. The optimal cut and fine-tuned layers were selected following 20 different configurations for each network. The three networks were fine-tuned using three strategies: only real data, only artificial data, and artificial with real data. The synthetic dataset consists of 10,000 images (80% for training, 20% for validation) produced by a generative model. These different configurations were analyzed and compared using a real dataset of 250 real XCA images (125 for testing and 125 for fine-tuning), regarding their randomly initiated CNNs and a fourth custom CNN, trained as well with artificial and real data. The results showed that pre-trained VGG16, ResNet50, and Inception-v3 cut on an early layer and fine-tuned, overcame the referencing CNNs performance. Specifically, Inception-v3 provided the best stenosis detection with an accuracy of 0.95, a precision of 0.93, sensitivity, specificity, and F1 score of 0.98, 0.92, and 0.95, respectively. Moreover, a class activation map is applied to identify the high attention regions for stenosis detection.

Evaluation of Left Atrial Strain Parameter in Coronary Artery Stenosis: A New Tool to Predict LCX Stenosis

Introduction: Speckle tracking echocardiography (STE) based on frame-to-frame tracking of acoustic speckles is a novel angle-independent method, used for evaluating myocardial deformation and recently to assess left atrium (LA) function.Aim: To the best of our knowledge, there is no investigation evaluating the predictor role of LA strain parameters in detection of coronary artery stenosis in ischemic heart disease. In this study, we assessed this parameter for predicting the culprit artery in patients underwent selective coronary angiography (SCA) in Mashhad, Iran. Patients and Methods: This was a case-control study, which was performed in Imam Reza and Quaem Hospitals in Mashhad, Iran between 2017 and 2018 in patients referred for SCA. Subjects with two or three- vessel diseases were excluded .Sixty-five cases were included in the study and divided into four groups according to the vessel involved : Group (1): normal coronary artery subjects (n=36); group (2): patients with left anterior descending (LAD) artery stenosis (n=12); group (3): patients with left circumflex artery (LCX) stenosis (n= 7) and group 4: patients with right coronary artery (RCA) stenosis (n=10). Patients underwent routine TTE and Speckle Tracking Imaging.Results: The mean age of participants was 56.72± 10.69 years old. The male/female ratio was 0.96. Mean absolute value of LA strain was 24.74% in normal subjects, while in groups with stenotic coronary artery disease, less values were defined as 18.63%, 16.03% and 19.05%, respectively (p value=0.05). The amounts of left ventricle end systolic volume (LVESV), LV global longitudinal strain (GLS) and Em of septal annulus were significantly different between normal group and those with LCX stenosis. Among different echocardiographic parameters, LA strain, LVESV and Em of septal annulus were defined as predictors of LCX occlusion with regression analysis. Conclusion: LA strain in subjects with coronary artery stenosis was lower than the strain in normal group and could predict isolated LCX occlusion.

Comparison of compressed sensing and conventional coronary magnetic resonance angiography for detection of coronary artery stenosis

PurposeThis study aimed to compare the efficacy of compressed sensing (CS) and conventional coronary magnetic resonance angiography (CMRA) in detecting coronary artery stenosis. MethodTwenty-eight patients underwent 3 T contrast-enhanced CS and conventional CMRA; for late gadolinium enhancement (LGE) imaging, 0.1 mmol/kg gadolinium medium was infused. CS CMRA was scanned within the LGE waiting time. After the LGE image acquisition, conventional CMRA was performed. The diagnostic performance of both CMRA for the detection of significant stenosis was evaluated using coronary angiography as a reference. The analysis was conducted to examine the three main coronary artery vessels: left anterior descending artery (LAD), left circumflex artery (LCX), and right coronary artery (RCA). These arteries were subdivided into 8 segments (LAD; main, proximal, and middle, LCX; proximal and distal, RCA; proximal, middle, and distal). Of these, hypoplastic segments and vessels after coronary stent implantation were excluded. The acquisition time of CS CMRA was compared with that of conventional CMRA. ResultsThe coronary arteries were evaluated in 197 segments. The sensitivity, specificity, and accuracy of CS CMRA in detecting significant stenosis were 85.2 %, 82.5 %, and 83.2 %, respectively, on a per-segment basis. Those of conventional CMRA were 85.2 %, 86.7 %, and 86.3 %, respectively. The acquisition time was 207 s (range, 144–258 s) for CS and 975 s (range, 787–1226s) for conventional CMRA (p < 0.001). ConclusionsSimilar to conventional CMRA, CS CMRA has shown potential for the detection of significant coronary artery stenosis.

Automatic detection of coronary artery stenosis by convolutional neural network with temporal constraint

Coronary artery disease (CAD) is a major threat to human health. In clinical practice, X-ray coronary angiography remains the gold standard for CAD diagnosis, where the detection of stenosis is a crucial step. However, detection is challenging due to the low contrast between vessels and surrounding tissues as well as the complex overlap of background structures with inhomogeneous intensities. To achieve automatic and accurate stenosis detection, we propose a convolutional neural network-based method with a novel temporal constraint across X-ray angiographic sequences. Specifically, we develop a deconvolutional single-shot multibox detector for candidate detection on contrast-filled X-ray frames selected by U-Net. Based on these static frames, the detector demonstrates high sensitivity for stenoses yet unacceptable false positives still exist. To solve this problem, we propose a customized seq-fps module that exploits the temporal consistency of consecutive frames to reduce the number of false positives. Experiments are conducted with 148 X-ray angiographic sequences. The results show that the proposed method outperforms existing stenosis detection methods, achieving the highest sensitivity of 87.2% and positive predictive value of 79.5%. Furthermore, this study provides a promising tool to improve CAD diagnosis in clinical practice.