Correlated Regression Feature Learning for Automated Right Ventricle Segmentation

Abstract

Accurate segmentation of right ventricle (RV) from cardiac magnetic resonance (MR) images can help a doctor to robustly quantify the clinical indices including ejection fraction. In this paper, we develop one regression convolutional neural network (RegressionCNN) which combines a holistic regression model and a convolutional neural network (CNN) together to determine boundary points’ coordinates of RV directly and simultaneously. In our approach, we take the fully connected layers of CNN as the holistic regression model to perform RV segmentation, and the feature maps extracted by convolutional layers of CNN are converted into 1-D vector to connect holistic regression model. Such connection allows us to make full use of the optimization algorithm to constantly optimize the convolutional layers to directly learn the holistic regression model in the training process rather than separate feature extraction and regression model learning. Therefore, RegressionCNN can achieve optimally convolutional feature learning for accurately catching the regression features that are more correlated to RV regression segmentation task in training process, and this can reduce the latent mismatch influence between the feature extraction and the following regression model learning. We evaluate the performance of RegressionCNN on cardiac MR images acquired of 145 human subjects from two clinical centers. The results have shown that RegressionCNN’s results are highly correlated (average boundary correlation coefficient equals 0.9827) and consistent with the manual delineation (average dice metric equals 0.8351). Hence, RegressionCNN could be an effective way to segment RV from cardiac MR images accurately and automatically.

Vitamin D and bisphosphonates therapies for osteoporosis are associated with different risks of atrial fibrillation in women

“…Co-morbidities are important risk factors for the pathogenesis of AF. [ 29 – 32 ] Similarly, this study also found that the incidences of co-morbidities in osteoporosis patients with AF were higher than those among osteoporosis patients without AF. The incidence of comorbidities was higher in the vitamin D group than in the neither group, which suggests that the beneficial effects of vitamin D on reducing AF may be rather underestimated.…”

Tpeak-Tend/QT interval predicts ST-segment resolution and major adverse cardiac events in acute ST-segment elevation myocardial infarction patients undergoing percutaneous coronary intervention

“…The optimal cutoff value was defined as the value yielding the maximal Youden index (Youden index = Max ([sensitivity] + [specificity] − 1)), or the best combined sensitivity and specificity. [ 12 , 13 ] Kaplan–Meier plots with log-rank test were performed to analyze correlation of STR and ECG parameters with combined MACE. Statistical analysis was performed using SPSS 20.0.0 (IBM Inc, Armonk, NY).…”

Prognostic value role of radiofrequency lesion size by cardiac magnetic resonance imaging on outcomes of ablation in patients with ischemic scar-related ventricular tachycardia

“…CMR can be used with different techniques in cardiovascular imaging. [24–27] Feasibility of CMR imaging after ventricular ablation was only studied in paediatric cohort. [18] Ten pediatric patients who underwent VT ablation were immediately evaluated by CMR after ablation to assess immediate and mid-term arrhythmia recurrences.…”