Predictive performance of the perivascular fat attenuation index for interventional antegrade percutaneous coronary intervention for chronic total occlusion.

OBJECTIVES: This study aimed to investigate the association between the perivascular fat attenuation index (FAI) and the success of the antegrade percutaneous coronary intervention (PCI) for chronic total occlusion (CTO). METHODS: This study evaluated patients with only one CTO lesion observed on conventional coronary angiography (CAG) who underwent coronary computed tomography angiography (CCTA) < 1 month before CAG, from 2018 to 2019. The clinical data, CCTA-based CTO lesion morphologic characteristics, and perivascular FAI of CTO lesions were recorded and analysed. RESULTS: In total, 156 patients with CTOs were enrolled in this study. Successful antegrade PCI (A-PCI) was achieved in 105 CTO lesions (67.3%). The perivascular FAI of the failed A-PCI group was significantly lower than the successful A-PCI group (-84.76 ± 10.44 Hounsfield unit (HU) vs. -67.54 ± 9.94 HU; p < 0.001), and the cut-off value determined by the receiver operating characteristic (ROC) curve was -77.50 HU. Multivariable analysis revealed no statistical significance in the clinical data, FAI ≤ -77.50 HU (odds ratio (OR): 33.96), negative remodeling (OR: 4.36), severe calcification degree (OR: 4.43) and occlusion length ≥ 20.25 mm (OR: 3.89) were independent predictors of A-PCI failure. The prediction performance of combining the three morphologic characteristics (severe calcification, occlusion length ≥ 20.25 mm, and negative remodeling) with FAI ≤ -77.50 HU was better than that of the three morphologic characteristics alone (0.93 versus 0.77, p < 0.001). CONCLUSIONS: As a non-invasive index for detecting coronary inflammation, FAI complements indicators based on coronary CTA well and may be helpful for choosing appropriate interventional strategies. KEY POINTS: • Perivascular FAI of CTO was significantly higher in the failed A-PCI group. • The combination of FAI with other morphological predictors showed higher predictive performance of failed A-PCI for CTOs. • FAI is a good complement to indicators based on coronary CTA.

Predicting reintervention after thoracic endovascular aortic repair of Stanford type B aortic dissection using machine learning.

OBJECTIVES: To construct models for predicting reintervention after thoracic endovascular aortic repair (TEVAR) of Stanford type B aortic dissection (TBAD). METHODS: A total of 192 TBAD patients who underwent TEVAR were included; 68 (35.4%) had indications for reintervention. Clinical characteristics, aorta characteristics on pre- and postoperative computed tomography angiography, and aorta characteristics on immediate postoperative aortic digital subtraction angiography were collected. The least absolute shrinkage and selection operator (LASSO) regression was applied to identify the risk factors for reintervention. Eight classifiers were used for modeling. The models were trained on 100 train-validation random splits with a ratio of 2:1. The performance was evaluated by the receiver operating characteristic curve. RESULTS: Seven predictors of reintervention were identified, including maximum false lumen diameter, aortic diameter measured at the level of approximately 15 mm distal to the left subclavian artery, aortic diameter measured at the level of the diaphragm, false lumen diameter measured at the level of the celiac artery, number of bare-metal and covered stents, number of bare-metal stents, and residual perfusion of the false lumen. Logistic regression (LR) yielded the highest performance, with an area under the curve of 0.802. A nomogram built for clinical use showed good calibration. The cutoff value for dividing patients into low- and high-risk subgroups was 0.413. Kaplan-Meier curves showed that the overall survival of high-risk patients was significantly shorter than that of low-risk patients (both p < 0.05). CONCLUSION: Our nomogram could predict the reintervention after TEVAR in patients with TBAD, which may facilitate patient selection and surveillance strategies. KEY POINTS: • Seven risk factors of reintervention after TEVAR of TBAD were identified for modeling. • Logistic regression performed best in predicting reintervention with an AUC of 0.802. • Patients with a high risk of reintervention had shorter OS than those with a low risk.

Evaluating the severity of aortic coarctation in infants using anatomic features measured on CTA.

OBJECTIVES: A machine learning model was developed to evaluate the severity of aortic coarctation (CoA) in infants based on anatomical features measured on CTA. METHODS: In total, 239 infant patients undergoing both thorax CTA and echocardiography were retrospectively reviewed. The patients were assigned to either mild or severe CoA group based on their pressure gradient on echocardiography. They were further divided into patent ductus arteriosus (PDA) and non-PDA groups. The anatomical features were measured on double-oblique multiplanar reconstructed CTA images. Then, the optimal features were identified by using the Boruta algorithm. Subsequently, the coarctation severity was classified using linear discriminant analysis (LDA). We further investigated the relationship between the anatomical features and re-coarctation using Cox regression. RESULTS: Four anatomical features showed significant differences between the mild and severe CoA groups, including the smallest aortic cross-sectional area indexed to body surface area (p < 0.001), the narrowest aortic diameter (CoA diameter) indexed to height (p < 0.001), the diameter of the descending aorta at the diaphragmatic level (p < 0.001) and weight (p = 0.005). With these features, accuracy of 88.6% and 90.2%, sensitivity of 65.0% and 72.1%, and specificity of 92.9% and 100% were obtained for classifying the CoA severity in the non-PDA and PDA groups, respectively. Moreover, CoA diameter indexed to weight was associated with the risk of re-coarctation. CONCLUSIONS: CoA severity can be evaluated by using LDA with anatomical features. When quantifying the severity of CoA and risk of re-coarctation, both anatomical alternations at the CoA site and the growth of the patients need to be considered. KEY POINTS: • CTA is routinely ordered for infants with coarctation of the aorta; however, whether anatomical variations observed with CTA could be used to assess the severity of CoA remains unknown. • Using the diameter and area of the coarctation site adjusted to body growth as features, the LDA model achieved an accuracy of 88.6% and 90.2% in differentiating between the mild and severe CoA patients in the non-PDA group and PDA group, respectively. • The narrowest aortic diameter (CoA diameter) indexed to weight has a hazard ratio of 10.29 for re-coarctation.

Myocardial Mechanics Parameters That Predict Left Ventricular Outflow Tract Obstruction in Patients With Hypertrophic Cardiomyopathy: A Cardiovascular Magnetic Resonance Feature Tracking Analysis.

OBJECTIVE: To identify left ventricular (LV) myocardial mechanics predictors of LV outflow tract obstruction (LVOTO) in patients with hypertrophic cardiomyopathy (HCM). METHODS: Thirty-nine adults with HCM and 21 controls underwent cardiovascular magnetic resonance. The feature tracking (FT) analysis results of HCM patients with and without LVOTO and controls were compared. RESULTS: Global radial strain measured on the short-axis slice (GRS-SAX) (odds ratio [OR], 1.09; 95% confidence interval [CI], 1.02-1.15; P < 0.01), global longitudinal strain measured on the long-axis slice (GLS-LAX) (OR, 1.81; 95% CI, 1.21-2.73; P < 0.01) and GRS measured on the long-axis slice (GRS-LAX) (OR, 1.07; 95% CI, 1.01-1.13; P = 0.02) were independent predictors of LVOTO. The combination of GRS-SAX plus GLS-LAX and GRS-LAX showed great discriminatory power for identifying LVOTO with an area under the receiver operating characteristic curve value of 0.91 (95% CI: 0.81-1.00). CONCLUSIONS: In adult HCM patients, GRS-SAX, GLS-LAX, and GRS-LAX were independent predictors of LVOTO. The combination of GRS-SAX plus GLS-LAX and GRS-LAX showed great discriminatory power for identifying LVOTO.

Prediction of pulmonary pressure after Glenn shunts by computed tomography-based machine learning models.

OBJECTIVES: This study aimed to develop non-invasive machine learning classifiers for predicting post-Glenn shunt patients with low and high risks of a mean pulmonary arterial pressure (mPAP) > 15 mmHg based on preoperative cardiac computed tomography (CT). METHODS: This retrospective study included 96 patients with functional single ventricle who underwent a bidirectional Glenn procedure between November 1, 2009, and July, 31, 2017. All patients underwent post-procedure CT, followed by cardiac catheterization. Overall, 23 morphologic parameters were manually extracted from cardiac CT images for each patient. The Mann-Whitney U or chi-square test was applied to select the most significant predictors. Six machine learning algorithms including logistic regression, Naive Bayes, random forest (RF), linear discriminant analysis, support vector machine, and K-nearest neighbor were used for modeling. These algorithms were independently trained on 100 train-validation random splits with a 3:1 ratio. Their average performance was evaluated by area under the curve (AUC), accuracy, sensitivity, and specificity. RESULTS: Seven CT morphologic parameters were selected for modeling. RF obtained the best performance, with mean AUC of 0.840 (confidence interval [CI] 0.832-0.850) and 0.787 (95% CI 0.780-0.794); sensitivity of 0.815 (95% CI 0.797-0.833) and 0.778 (95% CI 0.767-0.788), specificity of 0.766 (95% CI 0.748-0.785) and 0.746 (95% CI 0.735-0.757); and accuracy of 0.782 (95% CI 0.771-0.793) and 0.756 (95% CI 0.748-0.764) in the training and validation cohorts, respectively. CONCLUSIONS: The CT-based RF model demonstrates a good performance in the prediction of mPAP, which may reduce the need for right heart catheterization in post-Glenn shunt patients with suspected mPAP > 15 mmHg. KEY POINTS: • Twenty-three candidate descriptors were manually extracted from cardiac computed tomography images, and seven of them were selected for subsequent modeling. • The random forest model presents the best predictive performance for pulmonary pressure among all methods. • The computed tomography-based machine learning model could predict post-Glenn shunt pulmonary pressure non-invasively.

Anatomy of the retro-oesophageal major aortopulmonary collateral arteries in patients with pulmonary atresia with ventricular septal defect: results from preoperative CTA.

OBJECTIVES: To assess the frequency and anatomy of retro-oesophageal aortopulmonary collateral arteries (REMs) in patients with pulmonary atresia with ventricular septal defect and major aortopulmonary collateral arteries (PA-VSD-MAPCAs). METHODS: A total of 130 consecutive PA-VSD-MAPCA patients with preoperative CT angiography (CTA) data who underwent cardiac surgery were included. A detailed analysis of MAPCA anatomy was performed using CTA. RESULTS: A REM was identified in 82/130 included patients (63 %). A total of 277 MAPCAs were observed in these 82 patients and were divided into groups based on REM status: REM (n=94) and non-REM (n=183). Compared with non-REMs, REMs originated at a lower level and tended to originate from the lateral side of the aorta (all p<0.01). REMs had a higher probability of suffering stenosis (χ2=9.79, p<0.01), particularly midsegment stenosis (χ2=6.27, p=0.01). REMs were more posterior to the bronchus at the pulmonary hilum than non-REMs (91 % vs. 51 %) (χ2=50.81, p<0.01). CONCLUSIONS: REMs are associated with a lower level, more lateral origin, stenosis and more posterior location with respect to the bronchus at the pulmonary hilum. The unique CTA data obtained in this study showing the anatomy of REMs will be highly useful for surgeons in identifying REMs. KEY POINTS: • Unifocalization is a very important surgical approach for PA-VSD-MAPCA patients. • The anatomical variability of REMs becomes clinically relevant in unifocalization. • CTA provides a non-invasive way to observe the anatomy of REMs. • REMs are associated with lower level, more lateral origin, more midsegment stenosis. • REMs tend to be posterior to the bronchus at the pulmonary hilum.

Correction to: Anatomy of the retro-oesophageal major aortopulmonary collateral arteries in patients with pulmonary atresia with ventricular septal defect: results from preoperative CTA.

The original version of this article, originally published online ahead of printing on January 05, 2018, unfortunately contained mistakes.

Intravoxel incoherent motion MRI: emerging applications for nasopharyngeal carcinoma at the primary site.

OBJECTIVES: We compared pure molecular diffusion (D), perfusion-related diffusion (D*), perfusion fraction (f) and apparent diffusion coefficient (ADC) based on intravoxel incoherent motion (IVIM) theory in patients with nasopharyngeal carcinoma (NPC). METHODS: Sixty-five consecutive patients (48 men) with suspected NPC were examined using a 3.0-T MR system. Diffusion-weighted imaging (DWI) was performed with 13 b values (range, 0-800 s/mm(2)). We regarded the result of endoscopy and biopsy as the gold standard for detection. D, D* and f were compared between patients with primary NPC and enlarged adenoids. RESULTS: IVIM DWI was successful in 37 of 40 NPC and 23 of 25 enlarged adenoids cases. D (P = 0.001) and f (P < 0.0001) were significantly lower in patients with NPC than in patients with enlarged adenoids, whereas D* was significantly higher (P < 0.0001). However, the ADC was not significantly different between the two groups (P > 0.05). The area under the ROC curve (AUC) for D was 0.849 and was significantly larger than that for ADC (P < 0.05). CONCLUSIONS: IVIM DWI is a feasible technique for investigating primary NPC. D was significantly decreased in primary NPC, and increased D* reflected increased blood vessel generation and parenchymal perfusion in primary NPC. KEY POINTS: • Intravoxel incoherent motion (IVIM) analysis permits separate quantification of diffusion and perfusion. • IVIM DWI is a feasible technique for investigating primary NPC. • IVIM suggests that primary NPC tissue voxels exhibit both perfusion and diffusion.

Initial experience of correlating parameters of intravoxel incoherent motion and dynamic contrast-enhanced magnetic resonance imaging at 3.0 T in nasopharyngeal carcinoma.

PURPOSE: To determine the correlation between intravoxel incoherent motion (IVIM) and dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) parameters. METHODS: Thirty-eight newly diagnosed NPC patients were prospectively enrolled. Diffusion-weighted images (DWI) at 13 b-values were acquired using a 3.0-T MRI system. IVIM parameters including the pure molecular diffusion (D), perfusion-related diffusion (D*), perfusion fraction (f), DCE-MRI parameters including maximum slope of increase (MSI), enhancement amplitude (EA) and enhancement ratio (ER) were calculated by two investigators independently. Intra- and interobserver agreement were evaluated using the intraclass correlation coefficient (ICC) and Bland-Altman analysis. Relationships between IVIM and DCE-MRI parameters were evaluated by calculation of Spearman's correlation coefficient. RESULTS: Intra- and interobserver reproducibility were excellent to relatively good (ICC = 0.887-0.997; narrow width of 95 % limits of agreement). The highest correlation was observed between f and EA (r = 0.633, P < 0.001), with a strong correlation between f and MSI (r = 0.598, P = 0.001). No correlation was observed between f and ER (r = -0.162; P = 0.421) or D* and DCE parameters (r = 0.125-0.307; P > 0.119). CONCLUSION: This study suggests IVIM perfusion imaging using 3.0-T MRI is feasible in NPC, and f correlates significantly with EA and MSI. KEY POINTS: Assessment of tumour perfusion is important in nasopharyngeal carcinoma. DCE-MRI provided perfusion information with the use of intravenous contrast media. Perfusion information could be provided by non-invasive IVIM MRI. IVIM parameter f correlated with DCE-MRI parameters.

Prognostic value of optical flow ratio for cardiovascular outcomes in patients after percutaneous coronary stent implantation.

Background: The relationship between the optical flow ratio (OFR) and clinical outcomes in patients with coronary artery disease (CAD) after percutaneous coronary stent implantation (PCI) remains unknown. Objective: To examine the correlation between post-PCI OFR and clinical outcomes in patients with CAD following PCI. Methods: Patients who underwent optical coherence tomography (OCT) guided PCI at Guangdong Provincial People's Hospital were retrospectively and continuously enrolled. Clinical data, post-PCI OCT characteristics, and OFR measurements were collected and analyzed to identify predictors of target vessel failure (TVF) after PCI. Results: Among 354 enrolled patients, 26 suffered TVF during a median follow-up of 484 (IQR: 400-774) days. Post-PCI OFR was significantly lower in the TVF group than in the non-TVF group (0.89 vs. 0.93; P = 0.001). In multivariable Cox regression analysis, post-PCI OFR (HR per 0.1 increase: 0.60; 95% CI: 0.41-0.89; P = 0.011), large stent edge dissection (HR: 3.85; 95% CI: 1.51-9.84; P = 0.005) and thin-cap fibroatheroma (TCFA) (HR: 2.95; 95% CI: 1.19-7.35; P = 0.020) in the non-stented segment were independently associated with TVF. In addition, the inclusion of post-PCI OFR to baseline characteristics and post-PCI OCT findings improved the predictive power of the model to distinguish subsequent TVF after PCI (0.838 vs. 0.796; P = 0.028). Conclusion: The post-PCI OFR serves as an independent determinant of risk for TVF in individuals with CAD after PCI. The inclusion of post-PCI OFR assessments, alongside baseline characteristics and post-PCI OCT findings, substantially enhances the capacity to differentiate the subsequent manifestation of TVF in CAD patients following PCI.

The effects of cardiac structure, valvular regurgitation, and left ventricular diastolic dysfunction on the diagnostic accuracy of Murray law-based quantitative flow ratio.

Objective: The study aimed to investigate the diagnostic accuracy of Murray law-based quantitative flow ratio (µQFR) from a single angiographic view in patients with abnormal cardiac structure, left ventricular diastolic dysfunction, and valvular regurgitation. Background: µQFR is a novel fluid dynamics method for deriving fractional flow reserve (FFR). In addition, current studies of µQFR mainly analyzed patients with normal cardiac structure and function. The accuracy of µQFR when patients had abnormal cardiac structure, left ventricular diastolic dysfunction, and valvular regurgitation has not been clear. Methods: This study retrospectively analyzed 261 patients with 286 vessels that underwent both FFR and µQFR prior to intervention. The cardiac structure and function were measured using echocardiography. Pressure wire-derived FFR ≤0.80 was defined as hemodynamically significant coronary stenosis. Results: µQFR had a moderate correlation with FFR (r = 0.73, p < 0.001), and the Bland-Altman plot presented no difference between the µQFR and FFR (0.006 ± 0.075, p = 0.192). With FFR as the standard, the diagnostic accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of µQFR were 94.06% (90.65-96.50), 82.56% (72.87-89.90), 99.00% (96.44-99.88), 97.26 (89.91-99.30), and 92.96% (89.29-95.44), respectively. The concordance of µQFR/FFR was not associated with abnormal cardiac structure, valvular regurgitation (aortic valve, mitral valve, and tricuspid valve), and left ventricular diastolic function. Coronary hemodynamics showed no difference between normality and abnormality of cardiac structure and left ventricular diastolic function. Coronary hemodynamics demonstrated no difference among valvular regurgitation (none, mild, moderate, or severe). Conclusion: µQFR showed an excellent agreement with FFR. The effect of abnormal cardiac structure, valvular regurgitation, and left ventricular diastolic function did not correlate with the diagnostic accuracy of µQFR. Coronary hemodynamics showed no difference in patients with abnormal cardiac structure, valvular regurgitation, and left ventricular diastolic function.

A clinically applicable AI system for diagnosis of congenital heart diseases based on computed tomography images.

Congenital heart disease (CHD) is the most common type of birth defect. Without timely detection and treatment, approximately one-third of children with CHD would die in the infant period. However, due to the complicated heart structures, early diagnosis of CHD and its types is quite challenging, even for experienced radiologists. Here, we present an artificial intelligence (AI) system that achieves a comparable performance of human experts in the critical task of classifying 17 categories of CHD types. We collected the first-large CT dataset from three different CT machines, including more than 3750 CHD patients over 14 years. Experimental results demonstrate that it can achieve diagnosis accuracy (86.03%) comparable with junior cardiovascular radiologists (86.27%) in a World Health Organization appointed research and cooperation center in China on most types of CHD, and obtains a higher sensitivity (82.91%) than junior cardiovascular radiologists (76.18%). The accuracy of the combination of our AI system (97.20%) and senior radiologists achieves comparable results to that of junior radiologists and senior radiologists (97.16%) which is the current clinical routine. Our AI system can further provide 3D visualization of hearts to senior radiologists for interpretation and flexible review, surgeons for precise intuition of heart structures, and clinicians for more precise outcome prediction. We demonstrate the potential of our model to be integrated into current clinic practice to improve the diagnosis of CHD globally, especially in regions where experienced radiologists can be scarce.

Myocardial Segmentation of Cardiac MRI Sequences With Temporal Consistency for Coronary Artery Disease Diagnosis.

Coronary artery disease (CAD) is the most common cause of death globally, and its diagnosis is usually based on manual myocardial (MYO) segmentation of MRI sequences. As manual segmentation is tedious, time-consuming, and with low replicability, automatic MYO segmentation using machine learning techniques has been widely explored recently. However, almost all the existing methods treat the input MRI sequences independently, which fails to capture the temporal information between sequences, e.g., the shape and location information of the myocardium in sequences along time. In this article, we propose a MYO segmentation framework for sequence of cardiac MRI (CMR) scanning images of the left ventricular (LV) cavity, right ventricular (RV) cavity, and myocardium. Specifically, we propose to combine conventional neural networks and recurrent neural networks to incorporate temporal information between sequences to ensure temporal consistency. We evaluated our framework on the automated cardiac diagnosis challenge (ACDC) dataset. The experiment results demonstrate that our framework can improve the segmentation accuracy by up to 2% in the Dice coefficient.

The Hemodynamics of Patent Ductus Arteriosus in Patients after Central Shunt Operation.

A central shunt (CS) was an important surgery of systemic-to-pulmonary shunt (SPS) for the treatment of complex congenital heart diseases with decreased pulmonary blood flow (CCHDs-DPBF). There was no clear conclusion on how to deal with unclosed patent ductus arteriosus (PDA) during CS surgery. This study expanded the knowledge base on PDA by exploring the influence of the closing process of the PDA on the hemodynamic parameters for the CS model. The initial three-dimensional (3D) geometry was reconstructed based on the patient's computed tomography (CT) data. Then, a CS configuration with three typical pulmonary artery (PA) dysplasia structures and different sizes of PDA was established. The three-element windkessel (3WK) multiscale coupling model was used to define boundary conditions for transient simulation through computational fluid dynamics (CFD). The results showed that the larger size of PDA led to a greater systemic-to-pulmonary shunt ratio (Q S/A), and the flow ratio of the left pulmonary artery (LPA) to right pulmonary artery (RPA) (Q L/R) was more close to 1, while both the proportion of high wall shear stress (WSS) areas and power loss decreased. The case of PDA nonclosure demonstrates that the aortic oxygen saturation (Sao2) increased, while the systemic oxygen delivery (Do2) decreased. In general, for the CS model with three typical PA dysplasia, the changing trends of hemodynamic parameters during the spontaneous closing process of PDA were roughly identical, and nonclosure of PDA had a series of hemodynamic advantages, but a larger PDA may cause excessive PA perfusion and was not conducive to reducing cyanosis symptoms.

ImageTBAD: A 3D Computed Tomography Angiography Image Dataset for Automatic Segmentation of Type-B Aortic Dissection.

Type-B Aortic Dissection (TBAD) is one of the most serious cardiovascular events characterized by a growing yearly incidence, and the severity of disease prognosis. Currently, computed tomography angiography (CTA) has been widely adopted for the diagnosis and prognosis of TBAD. Accurate segmentation of true lumen (TL), false lumen (FL), and false lumen thrombus (FLT) in CTA are crucial for the precise quantification of anatomical features. However, existing works only focus on only TL and FL without considering FLT. In this paper, we propose ImageTBAD, the first 3D computed tomography angiography (CTA) image dataset of TBAD with annotation of TL, FL, and FLT. The proposed dataset contains 100 TBAD CTA images, which is of decent size compared with existing medical imaging datasets. As FLT can appear almost anywhere along the aorta with irregular shapes, segmentation of FLT presents a wide class of segmentation problems where targets exist in a variety of positions with irregular shapes. We further propose a baseline method for automatic segmentation of TBAD. Results show that the baseline method can achieve comparable results with existing works on aorta and TL segmentation. However, the segmentation accuracy of FLT is only 52%, which leaves large room for improvement and also shows the challenge of our dataset. To facilitate further research on this challenging problem, our dataset and codes are released to the public (Dataset, 2020).

Pyramid-Net: Intra-layer Pyramid-Scale Feature Aggregation Network for Retinal Vessel Segmentation.

Retinal vessel segmentation plays an important role in the diagnosis of eye-related diseases and biomarkers discovery. Existing works perform multi-scale feature aggregation in an inter-layer manner, namely inter-layer feature aggregation. However, such an approach only fuses features at either a lower scale or a higher scale, which may result in a limited segmentation performance, especially on thin vessels. This discovery motivates us to fuse multi-scale features in each layer, intra-layer feature aggregation, to mitigate the problem. Therefore, in this paper, we propose Pyramid-Net for accurate retinal vessel segmentation, which features intra-layer pyramid-scale aggregation blocks (IPABs). At each layer, IPABs generate two associated branches at a higher scale and a lower scale, respectively, and the two with the main branch at the current scale operate in a pyramid-scale manner. Three further enhancements including pyramid inputs enhancement, deep pyramid supervision, and pyramid skip connections are proposed to boost the performance. We have evaluated Pyramid-Net on three public retinal fundus photography datasets (DRIVE, STARE, and CHASE-DB1). The experimental results show that Pyramid-Net can effectively improve the segmentation performance especially on thin vessels, and outperforms the current state-of-the-art methods on all the adopted three datasets. In addition, our method is more efficient than existing methods with a large reduction in computational cost. We have released the source code at https://github.com/JerRuy/Pyramid-Net.

Image quality of ct angiography using model-based iterative reconstruction in infants with congenital heart disease: Comparison with filtered back projection and hybrid iterative reconstruction.

PURPOSE: To compare the image quality, rate of coronary artery visualization and diagnostic accuracy of 256-slice multi-detector computed tomography angiography (CTA) with prospective electrocardiographic (ECG) triggering at a tube voltage of 80kVp between 3 reconstruction algorithms (filtered back projection (FBP), hybrid iterative reconstruction (iDose4) and iterative model reconstruction (IMR)) in infants with congenital heart disease (CHD). METHODS: Fifty-one infants with CHD who underwent cardiac CTA in our institution between December 2014 and March 2015 were included. The effective radiation doses were calculated. Imaging data were reconstructed using the FBP, iDose4 and IMR algorithms. Parameters of objective image quality (noise, signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR)); subjective image quality (overall image quality, image noise and margin sharpness); coronary artery visibility; and diagnostic accuracy for the three algorithms were measured and compared. RESULTS: The mean effective radiation dose was 0.61±0.32 mSv. Compared to FBP and iDose4, IMR yielded significantly lower noise (P<0.01), higher SNR and CNR values (P<0.01), and a greater subjective image quality score (P<0.01). The total number of coronary segments visualized was significantly higher for both iDose4 and IMR than for FBP (P=0.002 and P=0.025, respectively), but there was no significant difference in this parameter between iDose4 and IMR (P=0.397). There was no significant difference in the diagnostic accuracy between the FBP, iDose4 and IMR algorithms (χ2=0.343, P=0.842). CONCLUSIONS: For infants with CHD undergoing cardiac CTA, the IMR reconstruction algorithm provided significantly increased objective and subjective image quality compared with the FBP and iDose4 algorithms. However, IMR did not improve the diagnostic accuracy or coronary artery visualization compared with iDose4.

Significant survival advantage of high pulmonary vein index and the presence of native pulmonary artery in pulmonary atresia with ventricular septal defect and major aortopulmonary collateral arteries: results from preoperative computed tomography angiography.

OBJECTIVES: The prognosis of pulmonary atresia with ventricular septal defect and major aortopulmonary collateral arteries (PA-VSD-MAPCAs) after surgery shows substantial clinical heterogeneity and predictors for outcomes are lacking. This study aimed to assess the predictive value of preoperative cardiac computed tomography angiography (CTA) for survival in patients with PA-VSD-MAPCAs. METHODS: We retrospectively analysed PA-VSD-MAPCA patients with preoperative CTA who underwent both right ventricular outflow tract reconstruction and MAPCA unifocalization ( n = 24) or pulmonary artery rehabilitation ( n = 28). The end-point was overall survival. Prognostic values of CTA were assessed using Cox univariate and multivariate analyses. The significant threshold of independent parameters was calculated using receiver-operating characteristic (ROC) curves. RESULTS: During a median follow-up of 1145 days, a total of 13 deaths were observed. Multivariate analysis identified a high pulmonary vein index (PVI) [hazard ratio (HR) = 0.03; 95% confidence interval (CI): 0.03, 0.28; P < 0.01] and the presence of native pulmonary artery (HR = 0.06; 95% CI: 0.10, 0.35; P < 0.01) as independent positive predictors of better survival. The area under the ROC curve for PVI was 0.79 ( P < 0.01), and a cut-off point of 438 mm 2 /m 2 was deemed the significant threshold for survival (sensitivity 92%, specificity 72%). CONCLUSIONS: Preoperational high PVI and native pulmonary artery presence were significant morphologic predictors of a positive survival advantage in PA-VSD-MAPCA patients. A PVI ≥438 mm 2 /m 2 may be a reliable positive prognosticator that could improve the decision-making strategy for PA-VSD-MAPCA patients.

Operator Radiation and the Efficacy of Ceiling-Suspended Lead Screen Shielding during Coronary Angiography: An Anthropomorphic Phantom Study Using Real-Time Dosimeters.

Operator radiation and the radiation protection efficacy of a ceiling-suspended lead screen were assessed during coronary angiography (CA) in a catheterization laboratory. An anthropomorphic phantom was placed under the X-ray beam to simulate patient attenuation in eight CA projections. Using real-time dosimeters, radiation dose rates were measured on models mimicking a primary operator (PO) and an assistant. Subsequently, a ceiling-suspended lead screen was placed in three commonly used positions to compare the radiation protection efficacy. The radiation exposure to the PO was 2.3 to 227.9 (mean: 67.2 ± 49.0) µSv/min, with the left anterior oblique (LAO) 45°/cranial 25° and cranial 25° projections causing the highest and the lowest dose rates, respectively. The assistant experienced significantly less radiation overall (mean: 20.1 ± 19.6 µSv/min, P < 0.003), with the right anterior oblique (RAO) 30° and cranial 25° projections resulting in the highest and lowest exposure levels, respectively. Combined with table-side shielding, the ceiling-suspended lead screen reduced the radiation to the PO by 76.8%, 81.9% and 93.5% when placed close to the patient phantom, at the left side and close to the PO, respectively, and reduced the radiation to the assistant by 70.3%, 76.7% and 90.0%, respectively. When placed close to the PO, a ceiling-suspended lead screen provides substantial radiation protection during CA.