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.

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.

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).