We leverage some of the advanced ConvNet architectures as a backbone-model of the proposed attention mapping network to build Cardio-XAttentionNet. The proposed model is trained on ChestX-Ray14, which is a publicly accessible chest X-ray dataset. The best single model achieves an overall ...
Introduction: the cardio-thoracic ratio (CTR) and the transverse cardiac diameter (TCD) on Plain chest radiography are the two parameters commonly used to diagnose cardiomegaly and heart disease. A CTR of greater than 50% on a PA film is abnormal and normally indicates cardiac or pericardial ef...
These hearts exhibited worsened functional reserve as compared to age-matched controls and activity of AC was also markedly lower. A considerable reduction in Mn2+-stimulated AC activity together with similar decrease in AC activity determined under other stimulation conditions suggests that it is a ...
Deep learning-based methods are being used to identify the chest anatomy segmentation, but most of them only consider the lung segmentation, requiring a great deal of training. This work is based on a multiclass concatenation-based automatic semantic segmentation network, CardioNet, that was ...
Figure 1. Chest anatomy segmentation to calculate cardiomegaly: (a) original CXR PA image, (b) segmented image by CardioNet, (c) maximum width of heart and thorax to calculate the CTR. In medical imaging, segmentation is extracted with similar properties from the images. The areas of inter...