Left atrial function by cardiac computed tomography is a predictor of heart failure and cardiovascular death.

OBJECTIVES: We sought to evaluate cardiac CT angiography (CCTA)-based assessment of left atrial (LA) function as a predictor of hospitalizations for heart failure (HF) and cardiovascular (CV) mortality. METHODS: LA function was evaluated using automatic derivation of LA volumes to calculate LA total emptying fraction (LATEF) in 788 consecutive patients with normal sinus rhythm who had undergone spiral CT scans. The relationship between LATEF evaluated by CCTA and the composite endpoint of admission for HF or CV mortality was analyzed using Cox models. RESULTS: During a median follow-up of 4 years, there were 100 events, 62 HF hospitalizations, and 38 cardiovascular deaths. Mean LATEF was 30.7 ± 10.7% and 40.5 ± 11.2% in patients with and without events, respectively (p < 0.0001). A high LATEF (upper tertile > 46%) was associated with a very low event rate (3.5% at 6 years [95% CI 1.7-7.1%]). The adjusted HR for HF or CV mortality was 4.37 (95% CI 1.99-9.60) in the lowest LATEF tertile, and 2.29 (95% CI 1.03-5.14) in the middle tertile, relative to the highest tertile. For the endpoint of HF alone, adjusted HR for the lowest LATEF tertile was 5.93 (95% CI 2.23-15.82) and for the middle tertile 2.89 (95% CI 1.06-7.86). The association of LATEF with outcome was similar for patients with both reduced and preserved left ventricular (LV) ejection fraction (Pinteraction = 0.724). Reduced LATEF was associated with a high event rate, even when coupled with normal LA volume. CONCLUSION: CCTA-derived LA function is a predictor of HF hospitalization or CV death, independent of clinical risk factors, LA volume, and LV systolic function. KEY POINTS: • Left atrial function can be automatically derived from cardiac CTA scans. • Cardiac CTA-derived left atrial function is a predictor of hospitalization for heart failure and cardiovascular death. • Evaluation of left atrial function could be useful in identifying patients at risk of heart failure.

Surgical treatment for Behcet's disease with acute superior vena cava syndrome.

BACKGROUND AND AIM OF THE STUDY: Behcet's disease (BD) is a multisystem vasculitis with unknown etiology. The involvement of superior vena cava (SVC) is reported in less than 2% of patients with BD. METHODS: We report a patient with acute edema of neck and face associated with dyspnea as the primary manifestation. So a diagnosis of superior Vena Cava syndrome (SVCS) was made and the thickening wall of SVC was resected. An Operation was performed under cardiopulmonary bypass to remove the mass and thrombus for avoiding for pulmonary embolism. RESULTS: The diagnosis of Behcet's disease (BD) didn't not be made until the recurrent oral and genital ulceration occurred 2 weeks later. The patient taked aspirin and prednisolone orally as prescribed and no recurrence were observed during the 30 months follow-up. CONCLUSIONS: BD should be suspected in patients presenting with SVCS, when there is thickening of SVC, whether thrombosis or not. Early diagnosis and treatment are essential for management of BD.

Pediatric Cardiac CT and MRI: Considerations for the General Radiologist.

OBJECTIVE. This article reviews the use and current imaging techniques of cardiac CT angiography and cardiac MRI in the evaluation of commonly encountered pediatric cardiac processes that may present to the general radiologist. CONCLUSION. Imaging pediatric patients with acquired and congenital heart disease is an important skill for general radiologists. As survival rates increase and these patients enter adulthood, knowledge of pediatric acquired and congenital heart disease remains pertinent.

Diagnostic efficacy of model-based iterative reconstruction algorithm in an assessment of coronary artery in comparison with standard hybrid-Iterative reconstruction algorithm: dose reduction and image quality.

PURPOSE: To evaluate the image quality and radiation dose exposure of low-dose coronary CTA (cCTA) study, reconstructed with the new model-based iterative reconstruction algorithm (IMR), compared with standard hybrid-iterative reconstruction (iDose4) cCTA in patients with suspected coronary artery disease. MATERIALS AND METHODS: Ninety-eight patients with an indication for coronary CT study were prospectively enrolled. Fifty-two patients (study group) underwent 256-MDCT low-dose cCTA (80 kV; automated-mAs; 60 mL of CM, 350 mgL/mL) with prospective ECG-triggering acquisition and IMR. A control group of 46 patients underwent 256-MDCT standard prospective ECG-gated protocol (100 kV; automated-mAs; 70 mL of CM, 400 mgL/mL; iDose4). Subjective and objective image quality (attenuation value, SD, SNR and CNR) were evaluated by two radiologists subjectively. Radiation dose exposure was quantified as DLP, CTDIvol and ED. RESULTS: Mean values of mAs were significantly lower for IMR-cCTA (167 ± 62 mAs) compared to iDose-cCTA (278 ± 55 mAs), p < 0.001. With a significant reduction of 38% in radiation dose exposure (DLP: IMR-cCTA 91.7 ± 26 mGy cm vs. iDose-cCTA 148.6 ± 35 mGy cm; p value < 0.001), despite the use of different CM, we found higher mean attenuation values of the coronary arteries in IMR group compared to iDose4 (mean density in LAD: 491HU IMR-cCTA vs. 443HU iDose-cCTA; p = 0.03). We observed a significant higher value of SNR and CNR in study group due to a lower noise level. Qualitative analysis did not reveal any significant differences between the two groups (p = 0.23). CONCLUSIONS: Low-dose cCTA study combined with IMR reconstruction allows to correctly evaluate coronary arteries disease, offering high-quality images and significant radiation dose exposure reduction (38%), as compared to standard cCTA protocol.

Left atrial appendage morphology and risk of stroke following pulmonary vein isolation for drug-refractory atrial fibrillation in low CHA2DS2Vasc risk patients.

BACKGROUND: Cardiac CT angiography (CCTA) has become an important adjunct in the structural assessment of the pulmonary veins (PV) prior to pulmonary vein isolation (PVI). Published data is conflicting regarding a relationship between left atrial appendage (LAA) and the risk of ischemic stroke (CVA) following PVI. We investigated the associations of volumetric and morphologic left atrial (LA) and LAA measurements for CVA following PVI. METHODS: We retrospectively reviewed 332 consecutive patients with drug refractory atrial fibrillation who obtained cardiac CT angiogram (CCTA) prior to PVI. Baseline demographic data, procedural and lab details, and outcomes were obtained from abstraction of an electronic medical records system. LA, LAA, and PV volumes were measured using CCTA datasets utilizing a semi-automated 3D workstation application. LAA morphology was assigned utilizing volume rendered images as previously described. RESULTS: The study cohort was 55 ± 13 years-old, 83.7% male, low CVA risk (median CHA2DS2Vasc 1; IQR 1, 3), and 30.4% were treated with novel oral anticoagulants. Chicken wing (CW) was the most common morphology (52%), followed by windsock (WS), cauliflower (CF), and cactus (CS) at 18, 9, and 2%, respectively. CVAs occurred in 4 patients following PVI with median time to CVA of 170.5 days. All CVAs were observed in CW morphology patients. When comparing CW morphology with non-CW morphology, CVAs occurred more frequently with the CW morphology (2.1% vs 0%, p = 0.03). This difference was not significant, though, after adjusting for CHA2DS2Vasc risk factors (p = 0.14). CONCLUSION: The CW morphology was observed more commonly in patients who experienced post-PVI CVA. After adjusting for CHA2DS2Vasc risk factors, CW morphology was not an independent predictor of post-PVI CVA. These findings should be interpreted in the setting of a low CVA event rate amongst a low risk population that was highly compliant with indicated anticoagulation therapy.

Cardiac CT angiography in the emergency department.

OBJECTIVE. Nearly 8 million patients present annually to emergency departments (EDs) in the United States with acute chest pain. Identifying those with a sufficiently low risk of acute coronary syndrome (ACS) remains challenging. Early imaging is important for risk stratification of these individuals. The objective of this article is to discuss the role of cardiac CT angiography (CTA) as a safe, efficient, and cost-effective tool in this setting and review state-of-the-art technology, protocols, advantages, and limitations from the perspective of our institution's 10-year experience. CONCLUSION. Early utilization of cardiac CTA in patients presenting to the ED with chest pain and a low to intermediate risk of ACS quickly identifies a group of particularly low-risk patients (< 1% risk of adverse events within 30 days) and allows safe and expedited discharge. By preventing unnecessary admissions and prolonged lengths of stay, a strategy based on early cardiac CTA has been shown to be efficient, although potential overutilization and other issues require long-term study.

Cardiac CT angiography beyond the coronary arteries: what radiologists need to know and why they need to know it.

OBJECTIVE: With current state-of-the-art CT combining fast scanning times and high spatial resolution, anatomy beyond the coronary arteries is well visualized and may lead to discovery of abnormalities. The purpose of this article is to provide a strategy for radiologists to recognize important extracoronary cardiac CT angiography (CTA) findings. CONCLUSION: A systemic approach to cardiac CTA by anatomic location and attention to key CT features are critical to identify and properly characterize important extracoronary cardiac abnormalities.

Denoising Multiphase Functional Cardiac CT Angiography Using Deep Learning and Synthetic Data.

Coronary CT angiography is increasingly used for cardiac diagnosis. Dose modulation techniques can reduce radiation dose, but resulting functional images are noisy and challenging for functional analysis. This retrospective study describes and evaluates a deep learning method for denoising functional cardiac imaging, taking advantage of multiphase information in a three-dimensional convolutional neural network. Coronary CT angiograms (n = 566) were used to derive synthetic data for training. Deep learning-based image denoising was compared with unprocessed images and a standard noise reduction algorithm (block-matching and three-dimensional filtering [BM3D]). Noise and signal-to-noise ratio measurements, as well as expert evaluation of image quality, were performed. To validate the use of the denoised images for cardiac quantification, threshold-based segmentation was performed, and results were compared with manual measurements on unprocessed images. Deep learning-based denoised images showed significantly improved noise compared with standard denoising-based images (SD of left ventricular blood pool, 20.3 HU ± 42.5 [SD] vs 33.4 HU ± 39.8 for deep learning-based image denoising vs BM3D; P < .0001). Expert evaluations of image quality were significantly higher in deep learning-based denoised images compared with standard denoising. Semiautomatic left ventricular size measurements on deep learning-based denoised images showed excellent correlation with expert quantification on unprocessed images (intraclass correlation coefficient, 0.97). Deep learning-based denoising using a three-dimensional approach resulted in excellent denoising performance and facilitated valid automatic processing of cardiac functional imaging. Keywords: Cardiac CT Angiography, Deep Learning, Image Denoising Supplemental material is available for this article. © RSNA, 2024.

TTN: Topological Transformer Network for Automated Coronary Artery Branch Labeling in Cardiac CT Angiography.

OBJECTIVE: Existing methods for automated coronary artery branch labeling in cardiac CT angiography face two limitations: 1) inability to model overall correlation of branches, since differences between branches cannot be captured directly. 2) a serious class imbalance between main and side branches. METHODS AND PROCEDURES: Inspired by the application of Transformer in sequence data, we propose a topological Transformer network (TTN), which solves the vessel branch labeling from a novel perspective of sequence labeling learning. TTN detects differences between branches by establishing their overall correlation. A topological encoding that represents the positions of vessel segments in the artery tree, is proposed to assist the model in classifying branches. Also, a segment-depth loss is introduced to solve the class imbalance between main and side branches. RESULTS: On a dataset with 325 CCTA, our method obtains the best overall result on all branches, the best result on side branches, and a competitive result on main branches. CONCLUSION: TTN solves two limitations in existing methods perfectly, thus achieving the best result in coronary artery branch labeling task. It is the first Transformer based vessel branch labeling method and is notably different from previous methods. CLINICAL IMPACT: This Pre-Clinical Research can be integrated into a computer-aided diagnosis system to generate cardiovascular disease diagnosis report, assisting clinicians in locating the atherosclerotic plaques.

Cardiac Computed Tomography Angiography in Infants and Young Children Without Sedation.

Cardiac computed tomography (CT) imaging plays a pivotal role in the diagnosis and management of infants and young children with congenital heart disease (CHD). While the benefits of CT imaging are well-established, the challenge lies in adapting these procedures to the unique requirements of infants and young children. Traditionally, sedation has been a common practice to ensure cooperation and motion control during imaging. However, using sedation introduces its challenges including potential risks, limitations, and cost implications. In this study, authors explore the feasibility, safety, and diagnostic accuracy of unsedated cardiac CT examinations in infants and young children. This study proves cardiac CT can be performed in India without sedation using simple restraining techniques. This approach aligns with the cultural and familial dynamics prevalent in the country and holds the potential to address economic and infrastructure challenges.

Unicuspid aortic valve by cardiac computed tomography: the best view is from the mountaintop-a case report.

Background: Unicuspid aortic valve (UAV) is a rare valvular heart disease and a challenging diagnosis. Advanced imaging techniques, particularly cardiac computed tomography (CT), appear to be invaluable tools to correctly identify this disease pre-operatively, as this may have an impact on the optimal surgical treatment. Case summary: We describe the case of a young patient admitted with heart failure, due to a severely stenotic UAV. Cardiac CT allowed adjusting the imaging plane to the best view in two orthogonal planes to identify the top of the 'dome' and to accurately measure the smallest valve opening by planimetry. Surgical inspection confirmed a rare case of acommissural UAV. Discussion: Cardiac CT angiography is crucial to understand the complexity of UAV disease and to differentiate the acommissural from the unicommissural type. Accurate positioning of the imaging plane through the smallest valve opening in systole reduces the risk of missing the diagnosis of this rare disease.

Application of dual-energy CT with prospective ECG-gating in cardiac CT angiography for children: Radiation and contrast agent dose.

OBJECTIVE: This research aimed to investigate the feasibility of utilizing dual-energy CT virtual monoenergetic images (VMI1) with prospective electrocardiogram (ECG2) gating for reducing radiation and contrast agent doses in pediatric patients with congenital heart disease (CHD3). METHODS: There were 100 pediatric patients with CHD included in this study. Group A (n = 50) underwent dual-energy scanning with prospective ECG-gating, and group B (n = 50) underwent conventional scanning with retrospective ECG-gating. Comparative analysis of CT values of lumen, objective image quality assessment, subjective image quality evaluations, and diagnostic efficacy were performed. RESULTS: CT values, image noise, signal-to-noise ratio (SNR4), and contrast-to-noise ratio (CNR5) were significantly affected by the VMI energy level, and they all increased with decreasing energy levels (P > 0.05). Combining subjective evaluation, the 45 keV VMI was considered the optimum image in group A. The 45 keV VMI exhibited higher CT values of lumen compared to conventional scanning images (P < 0.003 âˆ¼ 0.836), but meanwhile, the image noise was also higher in the 45 keV VMI (P = 0.004). Differences between the two groups in SNR, CNR, and diagnostic accuracy were not statistically significant. Compared to group B, the 45 keV VMI showed fewer contrast-induced artifacts (P < 0.001) and higher image quality score (P = 0.037). Group A had a 64 % reduction in radiation dose and a 40 % decrease in iodine dose compared to group B. CONCLUSION: The combination of dual-energy CT with prospective ECG-gating reduces radiation and iodine doses in pediatric patients with CHD. The 45 keV VMI can provide clinically acceptable image quality while declining contrast agent artifacts.

Non-rigid registration based on hierarchical deformation of coronary arteries in CCTA images.

In this paper, we propose an accurate and rapid non-rigid registration method between blood vessels in temporal 3D cardiac computed tomography angiography images of the same patient. This method provides auxiliary information that can be utilized in the diagnosis and treatment of coronary artery diseases. The proposed method consists of the following four steps. First, global registration is conducted through rigid registration between the 3D vessel centerlines obtained from temporal 3D cardiac CT angiography images. Second, point matching between the 3D vessel centerlines in the rigid registration results is performed, and the corresponding points are defined. Third, the outliers in the matched corresponding points are removed by using various information such as thickness and gradient of the vessels. Finally, non-rigid registration is conducted for hierarchical local transformation using an energy function. The experiment results show that the average registration error of the proposed method is 0.987 mm, and the average execution time is 2.137 s, indicating that the registration is accurate and rapid. The proposed method that enables rapid and accurate registration by using the information on blood vessel characteristics in temporal CTA images of the same patient.

Contemporary cardiovascular computed tomography (CCT) training: Serial surveys of the international CCT community by the Fellow and Resident Leaders of the Society of Cardiovascular Computed Tomography (SCCT) Committee (FiRST) and SCCT Future Leaders Program (FLP).

BACKGROUND: As cardiovascular computed tomography (CCT) practice evolves, the demand for specialists continues to increase. However, CCT training remains variable globally with limited contemporaneous data to understand this heterogeneity. We sought to understand the role of CCT globally and the training available to underpin its use. METHODS: We performed two consecutive surveys of cardiology and radiology physicians, two years apart, utilizing the Society of Cardiovascular Computed Tomography (SCCT) website, weblinks, social media platforms, and meeting handouts to maximize our response rate. We compared United States (US)-based vs. international responses to understand global similarities and differences in practice and training in the surveys. RESULTS: 235 respondents (37% trainees and 63% educators/non-trainees) initiated the first survey with 174 (74%) completing the core survey, with 205 providing their work location (114 US and 91 international). Eighty-four percent (92/110) of educator respondents stated a need for increased training opportunities to meet growing demand. Dedicated training fellowships are heterogenous, with limited access to structural heart imaging training, despite structural scanning being performed within institutions. The lack of a standardized curriculum was identified as the main obstacle to effective CCT learning, particularly in the US, with web-based learning platforms being the most popular option for improving access to CCT training. 148 trainees initiated the second survey with 107 (72%) completing the core components (51% North America, 49% international). Only 68% said they would be able to meet their required CCT education needs via their training program. Obstacles in obtaining CCT training again included a lack of a developed curriculum (51%), a lack of dedicated training time (35%), and a lack of local faculty expertise (31%). There was regional variability in access to CCT training, and, in contrast to the first survey, most (89%) felt 1:1 live review of cases with trained/expert reader was most useful for improving CCT training alongside formal curriculum/live lectures (72%). CONCLUSIONS: There is a need to expand dedicated CCT training globally to meet the demand for complex CCT practice. Access to CCT education (didactic and 1:1 case-based teaching from expert faculty), implementation of recently published global training curricula, and increased teaching resources (web-based) as an adjunct to existing experiential learning opportunities, are all deemed necessary to address current educational shortfalls.

Added Prognostic Value of Plaque Burden to Computed Tomography Angiography and Myocardial Perfusion Imaging in Patients with Diabetes.

BACKGROUND: We aimed to compare the added prognostic value of plaque burden to cardiac computed tomographic angiography (CCTA) anatomic assessment and single-photon emission computed tomography (SPECT) physiologic assessment in patients with diabetes undergoing both tests. METHODS: Consecutive patients with diabetes who underwent clinically indicated CCTA and SPECT myocardial imaging for suspected coronary artery disease were included. Stenosis severity and segment involvement score (SIS) were determined from CCTA, and presence of ischemia was determined from SPECT. Patients were followed from date of imaging for major adverse cardiovascular events (MACE). RESULTS: A total of 778 patients were included (mean age 60.6 ± 14.4 years, 55% males). After a median follow-up of 31 months, 87 (11%) patients experienced a MACE. In multivariable Cox regression models, SIS significantly predicted outcomes in models including obstructive stenosis and ischemia (hazard ratio 1.17, 95% confidence interval 1.10-1.24, P < .001; hazard ratio 1.16, 95% confidence interval 1.10-1.23, P < .001, respectively), and improved discrimination (Harrel's C 0.75, P = .006; 0.76, P = .006 in models with CCTA obstructive stenosis and SPECT ischemia, respectively). Results were consistent using subgroups of summed scores by composition of plaque (calcified vs noncalcified) and alternate definitions of obstructive stenosis. CONCLUSION: Our results suggest that in high-risk patients with diabetes and suspected coronary disease, SIS has incremental prognostic value over ischemia by SPECT or stenosis by CCTA in predicting incident cardiovascular outcomes.

Predictors and neurological consequences of periprocedural cerebrovascular events following transcatheter aortic valve implantation with self-expanding valves.

Aims: To evaluate the patient- and procedure-related predictors of transcatheter aortic-valve implantation (TAVI)-associated ischemic brain lesions and to assess the effect of silent cerebral ischemic lesions (SCIL) on neurocognitive function. Methods and results: We investigated 113 consecutive patients with severe aortic stenosis who underwent brain magnetic resonance imaging (MRI) within a week following TAVI. To assess periprocedural cerebral ischemic lesions, diffusion-weighted MRI was utilized. We used multivariate linear regression to identify the independent predictors of TAVI-related ischemic lesion volume (ILV) and periprocedural stroke. Neurocognitive evaluation was performed before and following TAVI at 6-month and one-year follow-up. Following TAVI, a total of 944 new cerebral ischemic lesions were detected in 104 patients (92%). The median ILV was 257 µl (interquartile range [IQR]:97.1-718.8µl) with a median lesion number of 6/patient [IQR:2-10]. The majority of ischemic lesions were clinically silent (95%), while 5% of the lesions induced a stroke, which was confirmed by MRI. Predilatation (ß = 1.13[95%CI:0.32-1.93], p = 0.01) and the number of valve positioning attempts during implantation (ß = 0.28[95%CI:0.06-0.50], p = 0.02) increased the log-transformed total ILV. Predilatation (OR = 12.04[95%CI:1.46-99.07], p = 0.02) and alternative access routes (OR = 7.84[95%CI:1.01-61.07], p = 0.02) were associated with stroke after adjustments for comorbidities and periprocedural factors. The presence of SCILs were not associated with a change in neurocognitive function that remained stable during the one-year follow-up. Conclusion: While periprocedural ischemic lesions are frequent, most of them are clinically silent and might not impact the patients' neurocognitive function. The number of valve positioning attempts, predilatation, and alternative access routes should be taken into consideration during TAVI to reduce the ILV and risk for stroke.

Dilated Cardiomyopathy Associated with Paraquat Herbicide Poisoning.

Dilated cardiomyopathy is a subset of cardiomyopathies defined by reduced ejection fraction of less than 45% and a dilated left ventricle. While dilated cardiomyopathy is common, its etiology is not always readily evident. Paraquat is used as an herbicide worldwide and is one of the main causes of fatal poisoning in underdeveloped countries in Asia, Central America, and the Pacific Islands. The most commonly affected organs are the lungs and kidneys. However, experimental research has shown that Paraquat can affect the heart indirectly through increased vascular permeability. In vivo animal studies have shown that paraquat poisoning causes myocardial contractile dysfunction by decreased fractional shortening and cardiac remodeling. We report the first case in published literature of a 52-year-old Hispanic man with dilated cardiomyopathy strongly associated with Paraquat exposure. It is important to obtain detailed medical history and proper diagnostic work-up including work, social, and family history, and echocardiography, baseline EKG, lab work, and ischemia cardiac testing as it can lead to improved diagnostic evaluation of possible etiologies of the commonly seen dilated cardiomyopathies and help identify less well-known etiologies as seen in our patient.

CT assessment of the left atrial appendage post-transcatheter occlusion - A systematic review and meta analysis.

BACKGROUND: Transesophageal echocardiography (TEE) is the standard imaging modality used to assess the left atrial appendage (LAA) after transcatheter device occlusion. Cardiac computed tomography angiography (CCTA) offers an alternative non-invasive modality in these patients. We aimed to conduct a comparison of the two modalities. METHODS: We performed a comprehensive systematic review of the current literature pertaining to CCTA to establish its usefulness during follow-up for patients undergoing LAA device closure. Studies that reported the prevalence of inadequate LAA closure on both CCTA and TEE were further evaluated in a meta-analysis. 19 studies were used in the systematic review, and six studies were used in the meta-analysis. RESULTS: The use of CCTA was associated with a higher likelihood of detecting LAA patency than the use of TEE (OR, 2.79, 95% CI 1.34-5.80, p â€‹= â€‹0.006, I2 â€‹= â€‹70.4%). There was no significant difference in the prevalence of peridevice gap ≥5 â€‹mm (OR, 3.04, 95% CI 0.70-13.17, p â€‹= â€‹0.13, I2 â€‹= â€‹0%) between the two modalities. Studies that reported LAA assessment in early and delayed phase techniques detected a 25%-50% higher prevalence of LAA patency on the delayed imaging. CONCLUSION: CCTA can be used as an alternative to TEE for LAA assessment post occlusion. Standardized CCTA acquisition and interpretation protocols should be developed for clinical practice.

An 8-layer residual U-Net with deep supervision for segmentation of the left ventricle in cardiac CT angiography.

BACKGROUND AND OBJECTIVES: Accurate segmentation of left ventricle (LV) is a fundamental step in evaluation of cardiac function. Cardiac CT angiography (CCTA) has become an important clinical diagnostic method for cardio-vascular disease (CVD) due to its non-invasive, short exam time, and low cost. To obtain the segmentation of the LV in CCTA scans, we present a deep learning method based on an 8-layer residual U-Net with deep supervision. METHODS: Based on the original 4-layer U-Net, our method deepened the network to eight layers, which increased the fitting capacity of the network, thus greatly improved its LV recognition capability. Residual blocks were incorporated to optimize the network from the increased depth. Auxiliary paths as deep supervision were introduced to supervise the intermediate information to improve the segmentation quality. In this study, we collected CCTA scans of 100 patients. Eighty patients with 1600 discrete slices were used to train the LV segmentation and the remaining 20 patients with 400 discrete slices were used for testing our method. An interactive graph cut algorithm was utilized reliably to annotate the LV reference standard that was further confirmed by cardiologists. Online data augmentation was performed in the training process to improve the generalization and robustness of our method. RESULTS: Compared with the segmentation results from the original U-Net and FC-DenseNet56 with Dice similarity coefficient (DSC) of 0.878±0.230 and 0.897±0.189, respectively, our method demonstrated higher segmentation accuracy and robustness for varying LV shape, size, and contrast, achieving DSC of 0.927±0.139. Without online data augmentation, our method resulted in inferior performance with DSC of 0.911±0.170. In addition, compared with the provided results from other existing studies in the LV segmentation of cardiac CT images, our method achieved a competitive performance for the LV segmentation. CONCLUSIONS: The proposed 8-layer residual U-Net with deep supervision accurately and efficiently segments the LV in CCTA scans. This method has potential advantages to be a reliable segmentation method and useful for the evaluation of cardiac function in the future study.

Quantification of hypo-attenuated leaflet thickening after transcatheter aortic valve implantation: clinical relevance of hypo-attenuated leaflet thickening volume.

AIMS: Our aim was to establish an objective, quantitative methodology for volumetric hypo-attenuated leaflet thickening (HALT) diagnosis and evaluate its clinical significance. METHODS AND RESULTS: We prospectively enrolled 144 patients who underwent transcatheter aortic valve implantation (TAVI) between 2011 and 2016. At inclusion, cardiac computed tomography angiography (CTA), transthoracic echocardiography, and brain magnetic resonance imaging (MRI) were performed. We quantified HALT on CTA datasets by segmenting the inner volume of TAVI frame at the level of leaflets and extracted voxels between a threshold of -200 to 200 HU based on prior recommendation. The median HALT volume was 72 [inter-quartile range (IQR): 1-154] mm3 (intra- and inter-reader agreement: intra-class correlation coefficient = 0.92 and 0.94, respectively) and 79% (n = 87/111) of the patients had HALT >0 mm3. In multivariate linear regression, oral anti-coagulation (ß: -0.32; 95% CI: -0.62 to -0.01; P = 0.004) and history of myocardial infarction (ß: 0.32; 95% CI: 0.01-0.63; P = 0.043) were associated with HALT quantity. Log-transformed HALT volume was associated with elevated (>13 mmHg) aortic mean gradient (AMG, OR: 12.85; 95% CI: 1.96-152.93; P = 0.021) and moderate-to-severe valvular degeneration (AMG ≥ 20 mmHg or ΔAMG ≥ 10 mmHg; OR: 10.56; 95% CI: 1.44-148.71; P = 0.046) but did not predict ischaemic brain lesions on MRI or all-cause death after a median follow-up of 29 (IQR: 11-29) months (all P > 0.05). CONCLUSION: Through systematic analysis of asymptomatic patients with TAVI, an objective and reproducible methodology was feasible for volumetric measurement of HALT. Anti-coagulation might have a protective effect against HALT. Ischaemic brain lesions and all-cause death were not associated with HALT; nevertheless, it might deteriorate prosthesis function due to its association with elevated AMG. CLINICAL TRIAL REGISTRATION: http//:www.ClinicalTrials.gov; NCT02826200.