Predicting major adverse cardiovascular events within 3 years by optimization of radiomics model derived from pericoronary adipose tissue on coronary computed tomography angiography: a case-control study.

BACKGROUND: Coronary inflammation induces changes in pericoronary adipose tissue (PCAT) can be detected by coronary computed tomography angiography (CCTA). Our aim was to investigate whether different PCAT radiomics model based on CCTA could improve the prediction of major adverse cardiovascular events (MACE) within 3 years. METHODS: This retrospective study included 141 consecutive patients with MACE and matched to patients with non-MACE (n = 141). Patients were randomly assigned into training and test datasets at a ratio of 8:2. After the robust radiomics features were selected by using the Spearman correlation analysis and the least absolute shrinkage and selection operator, radiomics models were built based on different machine learning algorithms. The clinical model was then calculated according to independent clinical risk factors. Finally, an overall model was established using the radiomics features and the clinical factors. Performance of the models was evaluated for discrimination degree, calibration degree, and clinical usefulness. RESULTS: The diagnostic performance of the PCAT model was superior to that of the RCA-model, LAD-model, and LCX-model alone, with AUCs of 0.723, 0.675, 0.664, and 0.623, respectively. The overall model showed superior diagnostic performance than that of the PCAT-model and Cli-model, with AUCs of 0.797, 0.723, and 0.706, respectively. Calibration curve showed good fitness of the overall model, and decision curve analyze demonstrated that the model provides greater clinical benefit. CONCLUSION: The CCTA-based PCAT radiomics features of three major coronary arteries have the potential to be used as a predictor for MACE. The overall model incorporating the radiomics features and clinical factors offered significantly higher discrimination ability for MACE than using radiomics or clinical factors alone.

COACT: Coronary artery centerline tracker.

BACKGROUND: The curved planar reformation (CPR) technique is one of the most commonly used methods in clinical practice to locate coronary arteries in medical images. PURPOSE: The artery centerline is the cornerstone for the generation of the CPR image. Here, we describe the development of a new fully automatic artery centerline tracker with the aim of increasing the efficiency and accuracy of the process. METHODS: We propose a COronary artery Centerline Tracker (COACT) framework which consists of an ostium point finder (OPFinder) model, an intersection point detector (IPDetector) model and a set of centerline tracking strategies. The output of OPFinder is the ostium points. The function of the IPDetector is to predict the intersections of a sample sphere and the centerlines. The centerline tracking process starts from two ostium points detected by the OPFinder, and combines the results of the IPDetector with a series of strategies to gradually reconstruct the coronary artery centerline tree. RESULTS: Two coronary CT angiography (CCTA) datasets were used to validate the models. Dataset1 contains 160 cases (32 for test and 128 for training) and dataset2 contains 70 cases (20 for test and 50 for training). The results show that the average distance between the ostium points predicted by the OPFinder and the manually annotated ostium points was 0.88 mm, which is similar to the differences between the results obtained by two observers (0.85 mm). For the IPDetector, the average overlap of the predicted and ground truth intersection points was 97.82% and this is also close to the inter-observer agreement of 98.50%. For the entire coronary centerline tree, the overlap between the results obtained by COACT and the gold standard was 94.33%, which is slightly lower than the inter-observer agreement, 98.39%. CONCLUSIONS: We have developed a fully automatic centerline tracking method for CCTA scans and achieved a satisfactory result. The proposed algorithms are also incorporated in the medical image analysis platform TIMESlice (https://slice-doc.netlify.app) for further studies.

New insight in massive cerebral infarction predictions after anterior circulation occlusion.

To predict massive cerebral infarction (MCI) occurrence after anterior circulation occlusion (ACO) by cASPECTS-CTA-CS (combined ASPECTS and CTA-CS). Of 185 cerebral infarction patients with the ACO, their collateral circulation scores from CT angiography (CTA) images in two groups (MCI and non-MCI) were evaluated using Alberta Stroke Program Early CT Score (ASPECTS) and CT angiography collateral score (CTA-CS) approaches. The cASPECTS-CTA-CS was validated internally using the bootstrap sampling method with 1000 bootstrap repetitions and compared to CTA-CS. Receiver-operating characteristic curve (ROC), clinical impact curve (CIC), and decision curve analysis (DCA) strategies were used to assess the clinical practicality and predictability of both approaches (cASPECTS-CTA-CS and CTA-CS). Using net reclassification improvement (NRI) and integrated discrimination improvement (IDI) analyses, discrimination levels of the cASPECTS-CTA-CS were compared with CTA-CS. Classification and regression tree (CART) analyses was conducted to identify the best predictive values and identify subgroup of MCI. The discrimination ability of collateral circulation evaluation score using the cASPECTS-CTA-CS [AUC: 0.918, 95% confidence interval (CI): 0.869-0.967, P < 0.01; NRI: 0.200, 95% CI: -0.104 to 0.505, P = 0.197; and IDI: 0.107, 95% CI: 0.035-0.178, P = 0.004] was better than CTA-CS alone (AUC: 0.885, 95% CI: 0.833-0.937, P < 0.01). DCA indicated the net benefits of the cASPECTS-CTA-CS approach was higher than CTA-CS alone when the threshold probability range over 20%. CIC analyses showed that the number of high risks and true positives were in agreement when the threshold probability > 80%. Less than 23 of cASPECTS-CTA-CS by CART was important factor in determining MCI occurrence, and ASPECTS < 7 was followed factor. The cASPECTS-CTA-CS approach cumulatively predicted MCI after ACO.

Age-dependent sex differences in non-stenotic intracranial plaque of embolic stroke of undetermined source.

Age and sex have effect on atherosclerosis. This study aimed to investigate their effect on non-stenotic intracranial atherosclerotic plaque (NIAP) in embolic stroke of undetermined source (ESUS) using high-resolution magnetic resonance imaging (HR-MRI). We retrospectively recruited consecutive ESUS patients who underwent intracranial HR-MRI to assess the plaque characteristics (remodeling index [RI], plaque burden [PB], fibrous cap [FC], discontinuity of plaque surface [DPS], intraplaque hemorrhage [IPH] and complicated plaque [CP]). We divided patients into three groups (< 60 years, 60-74 years, ≥ 75 years). 155 patients with ipsilateral NIAP were found from 243 ESUS patients, with 106 men (68.39%) and 49 women (31.61%). In total population or age group under 60 years, there were no significant differences in plaque characteristics between men and women (all p > 0.05). In age group of 60-74 years, men were associated with higher PB (66.27 ± 9.17% vs 60.91 ± 8.86%, p = 0.017) and RI (1.174 vs 1.156, p = 0.019), higher prevalence of DPS (82.50% vs 60.00%, p = 0.036) and complicated plaque (85.00% vs 63.33%, p = 0.036). For subjects ≥ 75 years old, PB were significantly higher in twomen vs men (68.85 ± 6.14% vs 62.62 ± 7.36%, p = 0.040). In addition, the probability for PBupper (≥ median PB), RIupper (≥ median RI) and vulnerable plaque increased as age increased, and its predictive power for index ESUS was higher in men than women. This study identified age-dependent sex differences in NIAP characteristics of ESUS patients, which will help us clarify their etiology.

Coronary slow flow research: a bibliometric analysis.

BACKGROUND: Studies on coronary slow flow are receiving increasing attention, but objective evaluations are still lacking. The purpose of this study was to visualize the current status and research hotspots of coronary slow flow through bibliometric analysis. METHODS: All relevant publications on coronary slow flow from 2003 to 2022 were extracted from the Web of Science Core Collection database and analyzed by VOSviewer and CiteSpace visualization software. Year of publication, journal, country/region, institution, and first author of each paper, as well as research hotspots were identified. RESULTS: A total of 913 publications were retrieved. The journal with the most publications was Coronary Artery Disease. The country/region with the most publications was Turkey, followed by China and the United States. The institution with the largest publication volume was Turkey Specialized Higher Education Research Hospital. The author with the largest publication volume was Chun-Yan Ma from China. Keyword analysis indicated that "treatment and prognosis", "pathogenesis and risk factors" and "diagnosis" were the clustering centers of coronary slow flow, and the research hotspots gradually changed with time, from pathogenesis to treatment and prognosis. CONCLUSION: Future research will focus on the search for effective and non-invasive detection indicators and treatments of coronary slow flow. Collaboration needs to be enhanced between different institutions or countries/regions, which would improve clinical outcomes for patients with coronary slow flow.

The association of intracranial atherosclerosis with cerebral small vessel disease imaging markers: a high-resolution magnetic resonance imaging study.

To evaluate the association of intracranial non-stenotic atherosclerotic plaque with cerebral small vessel disease (CSVD) imaging markers in a CSVD population using 3.0 T high-resolution magnetic resonance imaging (HRMRI), which was validated in embolic stroke of undetermined source (ESUS) cohort. We retrospectively recruited consecutive patients who were diagnosed with CSVD or ESUS from January 2015 to December 2019. All patients underwent intracranial HRMRI to assess intracranial non-stenotic atherosclerotic plaques. Baseline and imaging data were collected and were measured among all patients. Among 153 patients with CSVD, there were 59 with intracranial atherosclerotic plaque (IAP) and 94 with non-IAP, including 36 with intracranial atherosclerotic complicated plaque (IACP). Among 227 ESUS patients, there were 155 with IAP and 72 with non-IAP, including 127 with IACP. In the CSVD population, we found that: (1) CSVD burden was associated with IAP (p = 0.036) and IACP (p = 0.008); (2) IAP was associated with white matter hyperintensity (51% vs. 34%; P = 0.039), and IACP was associated with lacunes (69% vs. 35%; P = 0.009) and enlarge perivascular space (69% vs. 39%; P = 0.022). A similar association of CSVD imaging markers with IAP or IACP was found in the ESUS population. Furthermore, the association of unilateral IAP or IACP with CSVD imaging markers of ipsilateral hemisphere was identified in the two cohorts. This is the first report that intracranial non-stenotic atherosclerotic plaque, especially complicated plaque, is closely associated with CSVD imaging markers, which provide further evidence for the association of large artery atherosclerosis with CSVD.

The risk and outcome of malignant brain edema in post-mechanical thrombectomy: acute ischemic stroke by anterior circulation occlusion.

BACKGROUND AND PURPOSE: Malignant brain edema (MBE) occurring after mechanical thrombectomy (MT) in acute ischemic stroke (AIS) could lead to severe disability and mortality. We aimed to investigate the incidence, predictors, and clinical outcomes of MBE in patients with AIS after MT. METHODS: The clinical and imaging data of 155 patients with AIS of anterior circulation after MT were studied. Standard non-contrast CT was used to evaluate baseline imaging characteristics at admission. Clinical outcomes were measured using the 90-day modified Rankin Scale (mRS) score. Based on the follow-up CT scans performed within 72 h after MT, the patients were classified into MBE and non-MBE group. MBE was defined as a midline shift of ≥ 5 mm with signs of local brain swelling. Univariate and multivariate regression analyses were used to analyze the relationship between MBE and clinical outcomes and identify the predictors that correlate with MBE. RESULTS: MBE was observed in 19.4% of the patients who underwent MT and was associated with a lower rate of favorable 90-day clinical outcomes. Significant differences were observed in both MBE and non-MBE groups: baseline Alberta Stroke Program Early CT (ASPECT) score, hyperdense middle cerebral artery sign (HMCAS), baseline signs of early infarct, angiographic favorable collaterals, number of retrieval attempts, and revascularization rate. Multivariate analysis indicated that low baseline ASPECT score, absent HMCAS, angiographic poor collaterals, more retrieval attempt count, and poor revascularization independently influenced the occurrence of MBE in AIS patients with anterior circulation after MT. CONCLUSION: MBE was associated with a lower rate of favorable 90-day clinical outcomes. Low baseline ASPECT score, absent HMCAS, angiographic poor collaterals, more retrieval attempt count and poor revascularization were independently associated with MBE after MT.

Relationship between quantitative epicardial adipose tissue based on coronary computed tomography angiography and coronary slow flow.

BACKGROUND: The purpose of this study was to explore the relationship between quantitative epicardial adipose tissue (EAT) based on coronary computed tomography angiography (CCTA) and coronary slow flow (CSF). METHODS: A total of 85 patients with < 40% coronary stenosis on diagnostic coronary angiography were included in this retrospective study between January 2020 and December 2021. A semi-automatic method was developed for EAT quantification on CCTA images. According to the thrombolysis in myocardial infarction flow grade, the patients were divided into CSF group (n = 39) and normal coronary flow group (n = 46). Multivariate logistic regression was used to explore the relationship between EAT and CSF. Receiver operating characteristic (ROC) curve was plotted to evaluate the diagnostic value of EAT in CSF. RESULTS: EAT volume in the CSF group was significantly higher than that of the normal coronary flow group (128.83± 21.59 mL vs. 101.87± 18.56 mL, P < 0.001). There was no significant difference in epicardial fat attenuation index between the two groups (P > 0.05). Multivariate logistic regression analysis showed that EAT volume was independently related to CSF [odds ratio (OR) = 4.82, 95% confidence interval (CI): 3.06-7.27, P < 0.001]. The area under ROC curve for EAT volume in identifying CSF was 0.86 (95% CI: 0.77-0.95). The optimal cutoff value of 118.46 mL yielded a sensitivity of 0.80 and a specificity of 0.94. CONCLUSIONS: Increased EAT volume based on CCTA is strongly associated with CSF. This preliminary finding paves the way for future and larger studies aimed to definitively recognize the diagnostic value of EAT in CSF.

Automatic coronary artery segmentation of CCTA images using UNet with a local contextual transformer.

Coronary artery segmentation is an essential procedure in the computer-aided diagnosis of coronary artery disease. It aims to identify and segment the regions of interest in the coronary circulation for further processing and diagnosis. Currently, automatic segmentation of coronary arteries is often unreliable because of their small size and poor distribution of contrast medium, as well as the problems that lead to over-segmentation or omission. To improve the performance of convolutional-neural-network (CNN) based coronary artery segmentation, we propose a novel automatic method, DR-LCT-UNet, with two innovative components: the Dense Residual (DR) module and the Local Contextual Transformer (LCT) module. The DR module aims to preserve unobtrusive features through dense residual connections, while the LCT module is an improved Transformer that focuses on local contextual information, so that coronary artery-related information can be better exploited. The LCT and DR modules are effectively integrated into the skip connections and encoder-decoder of the 3D segmentation network, respectively. Experiments on our CorArtTS2020 dataset show that the dice similarity coefficient (DSC), Recall, and Precision of the proposed method reached 85.8%, 86.3% and 85.8%, respectively, outperforming 3D-UNet (taken as the reference among the 6 other chosen comparison methods), by 2.1%, 1.9%, and 2.1%.

Multi-constraint point set registration with redundant point removal for the registration of coronary arteries.

BACKGROUND: Coronary artery disease (CAD) is the leading cause of death worldwide. The registration of the coronary artery at different phases can help radiologists explore the motion patterns of the coronary artery and assist in the diagnosis of CAD. However, there is no automatic and easy-to-execute method to solve the missing data problem that occurs at the endpoints of the coronary artery tree. This paper proposed a non-rigid multi-constraint point set registration with redundant point removal (MPSR-RPR) algorithm to tackle this challenge. METHODS: Firstly, the MPSR-RPR algorithm roughly registered two coronary artery point sets with the pre-set smoothness regularization parameter and Gaussian filter width value. The moving coherent, local feature, and the corresponding relationship between bifurcation point pairs were exploited as the constraints. Next, the spatial geometry information of the coronary artery was utilized to automatically recognize the vessel endpoints and to delete the redundant points of the coronary artery. Finally, the algorithm continued carrying out the multi-constraint registration with another group of the pre-set parameters to improve the alignment performance. RESULTS: The experimental results demonstrated that the MPSR-RPR algorithm achieved a significantly lower mean value of the modified Hausdorff distance (MHD) compared to the other state-of-the-art methods for addressing the serious missing data in the left and right coronary arteries. CONCLUSION: This study demonstrated the effectiveness of the proposed algorithm in aligning coronary arteries, providing significant value in assisting in the diagnosis of coronary artery and myocardial lesions.

Low (0-5) Alberta Stroke Program Early Computed Tomography Score on admission predictive of worse functional outcome after mechanical thrombectomy for anterior circulation large vessel occlusion.

BACKGROUND AND PURPOSE: We examined functional outcomes of mechanical thrombectomy (MT) procedures following anterior circulation large vessel occlusion (ACLVO)-related acute ischemic strokes (AIS). Results were based on admission non-contrast computed tomography (NCCT) studies, using the Alberta Stroke Program Early Computed Tomography Score (ASPECTS) as standard metric. METHODS: Qualifying subjects were consecutive patients (N = 343) at a single center undergoing MT for ACLVO-related AIS. Each was grouped according to ASPECTS status on admission, determined from NCCT images by two physicians. Primary clinical endpoint was functional independence, assessed via modified Rankin Scale (mRS) at 90 days. Secondary endpoints were vessel recanalization (i.e., modified Thrombolysis in Cerebral Infarction [mTICI] score), symptomatic intracranial hemorrhage (sICH), and mortality. RESULTS: In this study population (mean age, 63.6 ± 12.6 years; women, 30.3%; median baseline National Institute of Health Stroke Scale [NIHSS] score, 15.2 ± 4.5), patients were stratified by ASPECTS tier at presentation, either 0-5 (n = 50) or 6-10 (n = 293). Multivariate logistic regression showed a relation between ASPECTS values ≤ 5 and lesser chance of 90-day functional improvement (OR = 2.309, 95% confidence interval [CI] 1.012-5.271; p = 0.047), once adjusted for age, baseline NIHSS score, diabetes mellitus, HbA1c concentration, D-dimer level, occlusive location, numbers of device passes, and successful recanalization. CONCLUSIONS: ASPECTS values ≤ 5 correspond with worse long-term functional improvement (mRS scores > 2) in patients undergoing MT for ACLVO-related AIS. Other independent determinants of functional outcomes after MT are age, baseline NIHSS score, HbA1c concentration, and successful recanalization.

Noncontrast cardiac computed tomography-derived mitral annular calcification scores in mitral valve disease.

BACKGROUND AND AIMS: Mitral annular calcification (MAC) by computed tomography (CT) is reported as an independent predictor of poor outcomes. However, it currently remains unclear if quantitative MAC parameters provide more value for mitral valve disease (MVD) management, therefore, we examined the prognostic value of MAC scores using noncontrast cardiac-CT in MVD patients. METHODS: Between January 2020 and December 2021, we prospectively enrolled 300 consecutive patients with MVD (MAC-present = 80 and MAC-absent = 220) undergoing preoperative cardiac-CT and mitral valve (MV) surgery. Noncontrast cardiac-CT images were used to qualitatively detect MAC (present or absent) and evaluate MAC scores. For analyses, we also collected baseline clinical data, intraoperative conversion (from MV repair to MV replacement), and follow-up arrhythmia data. RESULTS: Compared with the MAC-absent group, MAC-present patients were older (62 ± 7 vs. 58 ± 9 years, p < .001), mostly women (55% vs. 39.5%, p = .017), and also had aortic valve calcification (57.5% vs. 23.2%, p < .001), mitral stenosis (82.5% vs. 61.8%, p < .001), atrial fibrillation (30% vs. 11.8%, p < .001), and larger left atrial end-diastolic dimension (LADD, 49 [44-56] versus 46 [41-50], p = .001]. Furthermore, MAC-present patients underwent more MV replacements (61.8% vs. 82.5%, p = .001) and experienced a higher intraoperative conversion prevalence (11.8% vs. 61.3%, p < .001). Multiple logistic regression analyses showed that the female gender (odds ratio [OR]/95% confidence interval [CI]/p = 2.001/1.042-3.841/0.037) and MAC scores (OR/95% CI/p = 10.153/4.434-23.253/p < .001) were independent predictors of intraoperative conversion. During a follow-up of 263 ± 134 days, MAC-present patients had more arrhythmias (42.5% vs. 9.5%, p < .001). Also, MAC-scores (hazard ratio [HR]/95% CI/p = 6.841/3.322-14.089/p < .001) and LADD (HR/95% CI/p = 1.039/1.018-1.060/p < .001) were independently associated with arrhythmias by Cox regression analyses. CONCLUSIONS: Noncontrast cardiac CT-derived MAC-scores showed a high risk for intraoperative conversion and follow-up arrhythmias in MVD-patients.

A Comparative Study of Clinical and Aortic Morphological Characteristics between Bovine Aortic Arch and Normal Aortic Arch in Patients with Acute Type B Aortic Dissection.

INTRODUCTION: The purpose of this study was to analyze the difference in clinical and aortic morphological features between the bovine aortic arch and normal aortic arch in patients with acute type B aortic dissection (aTBAD). METHODS: A total of 133 patients diagnosed with aTBAD were retrospectively collected. Based on aortic arch morphology, they were divided into the bovine aortic arch group (n = 20) and the normal aortic arch group (n = 113). Aortic morphological features were assessed on computed tomographic angiography. Clinical and aortic morphological features were then compared between the bovine aortic arch and normal aortic arch groups. RESULTS: Patients in the bovine aortic arch group were significantly younger and with higher weight and BMI than the normal aortic arch group (p < 0.001, p = 0.045, and p = 0.016, respectively). The total aortic length in the bovine aortic arch group was significantly shorter than that in the normal aortic arch group (p = 0.039). The tortuosity of descending thoracic aorta, the tortuosity of descending aorta, and the angulation of aortic arch were significantly lower in the bovine aortic arch group (p = 0.004, p = 0.015, and p = 0.023, respectively). The width of descending aorta, the height of aorta arch, and the angle of ascending aorta were significantly smaller in the bovine aortic arch group (p = 0.045, p = 0.044, and p = 0.042, respectively). CONCLUSION: When the aTBAD occurred, patients with bovine aortic arch were prone to be younger and with higher BMI than those with normal aortic arch. The aortic curvature and the total aortic length were lower in patients with bovine aortic arch.

The role of epicardial and pericoronary adipose tissue radiomics in identifying patients with non-ST-segment elevation myocardial infarction from unstable angina.

Objectives: This study aimed to ascertain if the radiomics features of epicardial adipose tissue (EAT) and pericoronary adipose tissue (PCAT) based on coronary computed tomography angiography (CCTA) could identify non-ST-segment elevation myocardial infarction (NSTEMI) from unstable angina (UA). Materials and methods: This retrospective case-control study included 108 patients with NSTEMI and 108 controls with UA. All patients were separated into training cohort (n = 116), internal validation cohort 1 (n = 50), and internal validation cohort 2 (n = 50) based on the time order of admission. The internal validation cohort 1 used the same scanner and scan parameters as the training cohort, while the internal validation cohort 2 used different canners and scan parameters than the training cohort. The EAT and PCAT radiomics features selected by maximum relevance minimum redundancy (mRMR) and least absolute shrinkage and selection operator (LASSO) were adopted to build logistic regression models. Finally, we developed an EAT radiomics model, three vessel-based (right coronary artery [RCA], left anterior descending artery [LAD], and left circumflex artery [LCX]) PCAT radiomics models, and a combined model by combining the three PCAT radiomics models. Discrimination, calibration, and clinical application were employed to assess the performance of all models. Results: Eight radiomics features of EAT, sixteen of RCA-PCAT, fifteen of LAD-PCAT, and eighteen of LCX-PCAT were selected and used to construct radiomics models. The area under the curves (AUCs) of the EAT, RCA-PCAT, LAD-PCAT, LCX-PCAT and the combined models were 0.708 (95% CI: 0.614-0.802), 0.833 (95% CI:0.759-0.906), 0.720 (95% CI:0.628-0.813), 0.713 (95% CI:0.619-0.807), 0.889 (95% CI:0.832-0.946) in the training cohort, 0.693 (95% CI:0.546-0.840), 0.837 (95% CI: 0.729-0.945), 0.766 (95% CI: 0.625-0.907), 0.675 (95% CI: 0.521-0.829), 0.898 (95% CI: 0.802-0.993) in the internal validation cohort 1, and 0.691 (0.535-0.847), 0.822 (0.701-0.944), 0.760 (0.621-0.899), 0.674 (0.517-0.830), 0.866 (0.769-0.963) in the internal validation cohort 2, respectively. Conclusion: Compared with the RCA-PCAT radiomics model, the EAT radiomics model had a limited ability to discriminate between NSTEMI and UA. The combination of the three vessel-based PCAT radiomics may have the potential to distinguish between NSTEMI and UA.

Radiomics Signatures of Carotid Plaque on Computed Tomography Angiography : An Approach to Identify Symptomatic Plaques.

PURPOSE: To develop and validate a combined model incorporating conventional clinical and imaging characteristics and radiomics signatures based on head and neck computed tomography angiography (CTA) to assess plaque vulnerability. METHODS: We retrospectively analyzed 167 patients with carotid atherosclerosis who underwent head and neck CTA and brain magnetic resonance imaging (MRI) within 1 month. Clinical risk factors and conventional plaque characteristics were evaluated, and radiomic features were extracted from the carotid plaques. The conventional, radiomics and combined models were developed using fivefold cross-validation. Model performance was evaluated using receiver operating characteristic (ROC), calibration, and decision curve analyses. RESULTS: Patients were divided into symptomatic (n = 70) and asymptomatic (n = 97) groups based on MRI results. Homocysteine (odds ratio, OR 1.057; 95% confidence interval, CI 1.001-1.116), plaque ulceration (OR 6.106; 95% CI 1.933-19.287), and carotid rim sign (OR 3.285; 95% CI 1.203-8.969) were independently associated with symptomatic status and were used to construct the conventional model and s radiomic features were retained to establish the radiomics model. Radiomics scores incorporated with conventional characteristics were used to establish the combined model. The area under the ROC curve (AUC) of the combined model was 0.832, which outperformed the conventional (AUC = 0.767) and radiomics (AUC = 0.797) models. Calibration and decision curves analysis showed that the combined model was clinically useful. CONCLUSION: Radiomics signatures of carotid plaque on CTA can well predict plaque vulnerability, which may provide additional value to identify high-risk patients and improve outcomes.

Characteristics of intracranial plaque in patients with non-cardioembolic stroke and intracranial large vessel occlusion.

OBJECTIVE: To determine the characteristics of intracranial plaque proximal to large vessel occlusion (LVO) in stroke patients without major-risk cardioembolic source using 3.0 T high-resolution MRI (HR-MRI). METHODS: We retrospectively enrolled eligible patients from January 2015 to July 2021. The multidimensional parameters of plaque such as remodelling index (RI), plaque burden (PB), percentage lipid-rich necrotic core (%LRNC), presence of discontinuity of plaque surface (DPS), fibrous cap rupture, intraplaque haemorrhage and complicated plaque were evaluated by HR-MRI. RESULTS: Among 279 stroke patients, intracranial plaque proximal to LVO was more prevalent in the ipsilateral versus contralateral side to stroke (75.6% vs 58.8%, p<0.001). The larger PB (p<0.001), RI (p<0.001) and %LRNC (p=0.001), the higher prevalence of DPS (61.1% vs 50.6%, p=0.041) and complicated plaque (63.0% vs 50.6%, p=0.016) were observed in the plaque ipsilateral versus contralateral to stroke. Logistic analysis showed that RI and PB were positively associated with an ischaemic stroke (RI: crude OR: 1.303, 95% CI 1.072 to 1.584, p=0.008; PB: crude OR: 1.677, 95% CI 1.381 to 2.037, p<0.001). In subgroup with <50% stenotic plaque, the greater PB, RI, %LRNC and the presence of complicated plaque were more closely related to stroke, which was not evident in subgroup with ≥50% stenotic plaque. CONCLUSION: This is the first study to report the characteristics of intracranial plaque proximal to LVO in non-cardioembolic stroke. It provides potential evidence to support different aetiological roles of <50% stenotic vs ≥50% stenotic intracranial plaque in this population.

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

PURPOSE: 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. METHODS: 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. RESULTS: 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 . CONCLUSION: 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.

Pulmonary arteries segmentation from CT images using PA-Net with attention module and contour loss.

BACKGROUND: Pulmonary embolism is a kind of cardiovascular disease that threatens human life and health. Since pulmonary embolism exists in the pulmonary artery, improving the segmentation accuracy of pulmonary artery is the key to the diagnosis of pulmonary embolism. Traditional medical image segmentation methods have limited effectiveness in pulmonary artery segmentation. In recent years, deep learning methods have been gradually adopted to solve complex problems in the field of medical image segmentation. PURPOSE: Due to the irregular shape of the pulmonary artery and the adjacent-complex tissues, the accuracy of the existing pulmonary artery segmentation methods based on deep learning needs to be improved. Therefore, the purpose of this paper is to develop a segmentation network, which can obtain higher segmentation accuracy and further improve the diagnosis effect. METHODS: In this study, the pulmonary artery segmentation performance from the network model and loss function is improved, proposing a pulmonary artery segmentation network (PA-Net) to segment the pulmonary artery region from 2D CT images. Reverse Attention and edge attention are used to enhance the expression ability of the boundary. In addition, to better use feature information, the channel attention module is introduced in the decoder to highlight the important channel features and suppress the unimportant channels. Due to blurred boundaries, pixels near the boundaries of the pulmonary artery may be difficult to segment. Therefore, a new contour loss function based on the active contour model is proposed in this study to segment the target region by assigning dynamic weights to false positive and false negative regions and accurately predict the boundary structure. RESULTS: The experimental results show that the segmentation accuracy of this proposed method is significantly improved in comparison with state-of-the-art segmentation methods, and the Dice coefficient is 0.938 ± 0.035, which is also confirmed from the 3D reconstruction results. CONCLUSIONS: Our proposed method can accurately segment pulmonary artery structure. This new development will provide the possibility for further rapid diagnosis of pulmonary artery diseases such as pulmonary embolism. Code is available at https://github.com/Yuanyan19/PA-Net.

Intracranial plaque with large lipid core is associated with embolic stroke of undetermined source.

OBJECTIVE: To investigate an association between percentage lipid-rich necrotic core (LRNC) and an index ischemic stroke in an embolic stroke of undetermined source (ESUS) cohort. METHODS: A total of 167 ESUS patients with 259 non-stenotic intracranial plaques including 155 ipsilateral and 104 contralateral to stroke were finally enrolled in the current analysis. The multi-dimensional parameters involving remodeling index (RI), plaque burden (PB), LRNC, discontinuity of plaque surface (DPS), intraplaque hemorrhage (IPH), and vulnerable plaque defined as presence of complicated plaque were evaluated by high-resolution magnetic resonance imaging. RESULTS: We found that %LRNC was an independent predictor for ESUS in model 1 (OR: 2.574, 95% CI: 1.854-3.573, P < 0.001), and model 2 (OR: 2.550, 95% CI: 1.835-3.545, P < 0.001), but the association was not seen in PB. In receiver operating characteristic curve analysis, the discrimination of LRNC for ESUS was significantly superior to that of PB (absolute difference: 0.121, 95% CI: 0.056-0.205, P < 0.001). Importantly, a significantly positive synergy between the remodeling pattern and LRNC in response to plaque vulnerability was found by Sankey diagram (P for interaction = 0.001). CONCLUSION: This is the first report that LRNC, beyond PB, may be correlated with an index ESUS, and a synergistic effect between positive remodeling and larger LRNC could promote plaque vulnerability. The findings suggest that a potential target subgroup may benefit from stroke prevention with intensive statin, although this must be confirmed in future.

Performance of Radiomics Models Based on Coronary Computed Tomography Angiography in Predicting The Risk of Major Adverse Cardiovascular Events Within 3 Years: A Comparison Between the Pericoronary Adipose Tissue Model and the Epicardial Adipose Tissue Model.

RATIONALE AND OBJECTIVES: To compare the prediction performance of the epicardial adipose tissue (EAT) and pericoronary adipose tissue (PCAT) radiomics models based on coronary computed tomography angiography for major adverse cardiovascular events (MACE) within 3 years. MATERIALS AND METHODS: Our study included 288 patients (144 with MACE and 144 without MACE within 3 years) by matching age, gender, body mass index, and medication intake. Patients were randomly assigned either to the training (n = 201) or validation cohort (n = 87). A total of 184 radiomics features were extracted from EAT and PCAT images. Spearman's rank correlation coefficient and the gradient boosting decision tree algorithm were performed for feature selection. Five models were established based on PCAT or EAT radiomics features and clinical factors, including PCAT, EAT, clinical, PCAT-clinical, and EAT-clinical model (MPCAT, MEAT, Mclinical, MPCAT-clinical, and MEAT-clinical). Receiver operating characteristic curves, calibration curves, and the decision curve analysis were plotted to evaluate the model performance. RESULTS: The MPCAT achieved an area under the curve (AUC) of 0.703 in the validation cohort, which was better than MEAT with AUC of 0.538. The MPCAT-clinical showed better performance (AUC = 0.781) in predicting MACE than the Mclinical (AUC = 0.748) or MEAT-clinical (AUC = 0.745). CONCLUSION: Our results showed that the PCAT was better than the EAT in both single modality and combined models, and the MPCAT-clinical had the most significant clinical value in predicting the occurrence of MACE within 3 years.