Most current medical image segmentation models are primarily built upon the U-shaped network (U-Net) architecture, which has certain limitations in capturing both global contextual information and fine-grained details. To address this issue, this paper proposes a novel U-shaped network model, termed the Multi-View U-Net (MUNet), which integrates self-attention and multi-view attention mechanisms. Specifically, a newly designed multi-view attention module is introduced to aggregate semantic features from different perspectives, thereby enhancing the representation of fine details in images. Additionally, the MUNet model leverages a self-attention encoding block to extract global image features, and by fusing global and local features, it improves segmentation performance. Experimental results demonstrate that the proposed model achieves superior segmentation performance in coronary artery image segmentation tasks, significantly outperforming existing models. By incorporating self-attention and multi-view attention mechanisms, this study provides a novel and efficient modeling approach for medical image segmentation, contributing to the advancement of intelligent medical image analysis.
Humans ; Image Processing, Computer-Assisted/methods* ; Neural Networks, Computer ; Algorithms ; Attention ; Coronary Vessels/diagnostic imaging* ; Diagnostic Imaging/methods*

OBJECTIVES: To construct a Z-score regression model for coronary artery diameter based on echocardiographic data from children in Sichuan Province and to establish a Z-score calculation formula. METHODS: A total of 744 healthy children who underwent physical examinations at Sichuan Provincial People's Hospital from January 2020 to December 2022 were selected as the modeling group, while 251 children diagnosed with Kawasaki disease at the same hospital from January 2018 to December 2022 were selected as the validation group. Pearson correlation analysis was conducted to analyze the relationships between coronary artery diameter values and age, height, weight, and body surface area. A regression model was constructed using function transformation to identify the optimal regression model and establish the Z-score calculation formula, which was then validated. RESULTS: The Pearson correlation analysis showed that the correlation coefficients for the diameters of the left main coronary artery, left anterior descending artery, left circumflex artery, and right coronary artery with body surface area were 0.815, 0.793, 0.704, and 0.802, respectively (P<0.05). Among the constructed regression models, the power function regression model demonstrated the best performance and was therefore chosen as the optimal model for establishing the Z-score calculation formula. Based on this Z-score calculation formula, the detection rate of coronary artery lesions was found to be 21.5% (54/251), which was higher than the detection rate based on absolute values of coronary artery diameter. Notably, in the left anterior descending and left circumflex arteries, the detection rate of coronary artery lesions using this Z-score calculation formula was higher than that of previous classic Z-score calculation formulas. CONCLUSIONS The Z-score calculation formula established based on the power function regression model has a higher detection rate for coronary artery lesions, providing a strong reference for clinicians, particularly in assessing coronary artery lesions in children with Kawasaki disease.
Humans ; Male ; Female ; Child, Preschool ; Child ; Coronary Artery Disease/diagnostic imaging* ; Infant ; Mucocutaneous Lymph Node Syndrome ; Regression Analysis ; Coronary Vessels/diagnostic imaging* ; Echocardiography ; Adolescent

Objective To develop a diagnostic model combining the CT angiography(CCTA)-derived myocardial radiomics signatures with the CT-derived fractional flow reserve(CT-FFR)based on coronary CCTA and investigate the diagnostic accuracy of the hybrid model for hemodynamically significant coronary artery disease(CAD).Methods The patients presenting stable angina pectoris,diagnosed with CAD,and clinically referred for CCTA examination and invasive coronary angiography were prospectively recruited.Radiomics features of the left ventricular myocardium were extracted from the three main perfusion territories demarcated according to the coronary blood supply.The extracted features were first selected by the minimum redundancy maximum relevance feature ranking method.A least absolute shrinkage and selection operator Logistic regression algorithm with leave-one-out cross-validation was then employed to construct a radiomics model.The CT-FFR value was generated for each blood vessel.The area under the receiver operating characteristics curve(AUC_ROC),sensitivity,and specificity were adopted to evaluate the performance of each model against the reference standard invasive coronary angiography/FFR.Results A total of 70 patients[42 men and 28 women;(61±10) years old] were included in this study and complemented CCTA examination,with 175 vessels and the corresponding myocardial territories undergoing invasive coronary angiography/FFR.A total of 1 656 specific radiomics parameters were extracted,from which 14 features were selected to establish the radiomics model.The AUC_ROC,sensitivity,and specificity were 0.797(95%CI=0.732-0.861),77.1%,and 73.7%for the radiomics model,0.892(95%CI=0.841-0.943),81.4%,and 88.8%for the CT-FFR model,and 0.928(95%CI=0.890-0.965),83.3%,and 88.4%for the hybrid model,respectively.The hybrid model outperformed the radiomics model and CT-FFR alone(P=0.040).Conclusions The radiomics signatures of the vessel-related myocardium from CCTA could provide incremental value to the diagnostic performance of CT-FFR and improve vessel-specific ischemia detection.The hybrid model combining CT-FFR with radiomics signatures is potentially feasible for improving the diagnostic accuracy for hemodynamically significant CAD.
Coronary Angiography/methods* ; Tomography, X-Ray Computed ; Humans ; Hemodynamics ; Coronary Artery Disease/diagnostic imaging* ; Male ; Female ; Middle Aged ; Aged ; Radiomics ; Angina Pectoris/diagnostic imaging* ; China ; Image Processing, Computer-Assisted ; Coronary Vessels/diagnostic imaging*

Manual segmentation of coronary arteries in computed tomography angiography (CTA) images is inefficient, and existing deep learning segmentation models often exhibit low accuracy on coronary artery images. Inspired by the Transformer architecture, this paper proposes a novel segmentation model, the double parallel encoder u-net with transformers (DUNETR). This network employed a dual-encoder design integrating Transformers and convolutional neural networks (CNNs). The Transformer encoder transformed three-dimensional (3D) coronary artery data into a one-dimensional (1D) sequential problem, effectively capturing global multi-scale feature information. Meanwhile, the CNN encoder extracted local features of the 3D coronary arteries. The complementary features extracted by the two encoders were fused through the noise reduction feature fusion (NRFF) module and passed to the decoder. Experimental results on a public dataset demonstrated that the proposed DUNETR model achieved a Dice similarity coefficient of 81.19% and a recall rate of 80.18%, representing improvements of 0.49% and 0.46%, respectively, over the next best model in comparative experiments. These results surpassed those of other conventional deep learning methods. The integration of Transformers and CNNs as dual encoders enables the extraction of rich feature information, significantly enhancing the effectiveness of 3D coronary artery segmentation. Additionally, this model provides a novel approach for segmenting other vascular structures.
Neural Networks, Computer ; Humans ; Coronary Vessels/diagnostic imaging* ; Computed Tomography Angiography/methods* ; Deep Learning ; Coronary Angiography/methods* ; Imaging, Three-Dimensional ; Image Processing, Computer-Assisted/methods* ; Algorithms ; Convolutional Neural Networks

Humans ; Coronary Artery Disease/therapy* ; Consensus ; Tomography, Optical Coherence/methods* ; East Asian People ; Coronary Angiography ; Coronary Vessels/diagnostic imaging* ; Ultrasonography, Interventional/methods*

Coronary artery fractional flow reserve (FFR) is a critical physiological indicator for assessment of impaired blood flow caused by coronary artery stenosis. The wire-based invasive measurement of blood flow pressure gradient across stenosis is the gold standard for clinical measurement of FFR. However, it has the risk of vascular injury and requires the use of vasodilators, increasing the time and overall cost of interventional examination. Coronary imaging is playing an important role in clinical diagnosis of stenotic lesions, evaluation of severity of lesions, and planning of therapies. In recent years, the computation of FFR based on the physiological information of blood flow obtained from routinely collected coronary image data has become a research focus in this field. This technique reduces the cost of physiological assessment of coronary lesions and the use of pressure wires. It is beneficial to strengthen the physiological guidance in interventional therapy. In order to better understand this emerging technique, this paper highlights its implementation principle and diagnostic performance, analyzes practical problems and current challenges in clinical applications, and discusses possible future development.
Humans ; Coronary Vessels/diagnostic imaging* ; Fractional Flow Reserve, Myocardial ; Heart ; Constriction, Pathologic ; Coronary Stenosis/diagnostic imaging*

OBJECTIVE: To analyse the correlation between the characteristics of coronary plaque in coronary heart disease (CHD) patients with phlegm-blood stasis syndrome (PBS) and blood stasis syndrome (BSS). METHODS: Patients were divided into different groups based on Chinese medicine (CM) syndrome differentiation. The baseline demographics and clinical variables were collected from the medical records. Additionally, the characteristics of plaque and pathological manifestations in coronary artery were evaluated using intravascular ultrasound (IVUS). RESULTS: A total of 213 CHD patients were enrolled in two groups: 184 were diagnosed with PBS and the remaining 29 were diagnosed with BSS. There were no significant differences in age, body mass index, proportions of patients with high blood pressure, diabetes mellitus, smoking, hyperlipidemia, history of coronary artery bypass graft and percutaneous coronary intervention, medications, index from cardiac ultrasound image, blood lipids and C-reactive protein between the two groups (P>0.05), except gender, weight and proportions of IVUS observed target vessels (P<0.05 or P<0.01). More adverse events such as acute myocardial infarction (P=0.003) and unstable angina (P=0.048) were observed in BSS. Additionally, dissection, thrombus and coronary artery ectasia were significantly increased in BSS (P<0.05 or P<0.01). In contrast, PBS had more patients with stable angina and chronic total occlusion with significantly higher SYNTAX (synergy between percutaneous coronary intervention with Taxus and coronary artery bypass surgery) scores (P<0.05 or P<0.01). Moreover, dense-calcium was significantly elevated in PBS (P<0.01). CONCLUSIONS Coronary plaque characteristics were correlated with different CM syndromes. Patients with PBS were associated with a higher degree of calcified plaque and severe coronary artery stenosis, indicating poor clinical prognosis but with a low probability of acute coronary events. In contrast, the degree of calcified plaque in patients with BSS remained relatively low, and plaque was more vulnerable, resulting in the possibility of the occurrence of acute coronary events remaining high.
Coronary Angiography ; Coronary Artery Disease/diagnostic imaging* ; Coronary Vessels/pathology* ; Cross-Sectional Studies ; Humans ; Medicine, Chinese Traditional ; Percutaneous Coronary Intervention ; Plaque, Atherosclerotic/diagnostic imaging* ; Syndrome ; Ultrasonography, Interventional/methods*

Coronary Angiography ; Coronary Vessels/diagnostic imaging* ; Technology

Child ; Coronary Angiography/methods* ; Coronary Artery Disease/etiology* ; Coronary Vessels/pathology* ; Humans ; Mucocutaneous Lymph Node Syndrome/diagnostic imaging* ; Tomography, Optical Coherence/methods*

Objective To investigate the role of dual-layer detector energy spectral CT in resting myocardial perfusion imaging for patients with normal coronary artery. Methods One hundred and fifty-six patients with suspected coronary heart disease underwent dual-layer detector energy spectral CT coronary angiography,and resting myocardial perfusion imaging was performed for 28 patients with normal coronary artery.According to American Heart Association's 17-segmentmodel,the iodine density and effective atomic number(Z
Computed Tomography Angiography ; Coronary Angiography ; Coronary Vessels/diagnostic imaging* ; Humans ; Myocardial Perfusion Imaging ; Tomography, X-Ray Computed