Specifically, we trained three different 2D convolutional neural network (CNN) architectures using correct (subject-level) and incorrect (slice-level) data split on public and private datasets ...

Since inter-slice and intra-slice resource constraints are mutually coupled, it is difficult to solve the problem via traditional Deep Reinforcement Learning (DRL) methods. Therefore, we decompose the ...

Objectives To explore clinical diagnostic value of 128-slice spiral CT coronary angiography (128-SCTCA) in the patients with coronary heart disease, and check the population adapt to 128-SCTCA.