DBCU-Net: Deep Learning Approach for Segmentation of Coronary Angiography Images

Abstract

Coronary angiography (CAG) is the “gold standard” for diagnosing coronary artery disease (CAD). However, due to the limitation of current imaging methods, the CAG image has low resolution and poor contrast with a lot of artifacts and noise, which makes it difficult for blood vessels segmentation. In this paper, we propose a DBCU-Net for automatic segmentation of CAG images, which is an extension of U-Net, DenseNet with bidirectional convLSTM. The main contribution of our network is that instead of convolution in the feature extraction of U-Net, we incorporate dense connectivity and the bidirectional convLSTM to highlight salient features. We conduct our experiment on our private dataset, and achieve average Accuracy, Precision, Recall and F1-score for coronary artery segmentation of 0.985, 0.913, 0.847 and 0.879 respectively.

Blood Vessels Disease Detection of Coronary Angiography Images using Deep learning Model

“…Where the main contribution of this model was the feature extraction of U-Net instead of convolution network, where the dense network connectivity and the bi-directional ConvLSTM with salient features. The outcomes predict the average Accuracy, Precision, Recall and F1-score of coronary artery segmentation having the evaluated results is 0.985, 0.913, 0.847 and 0.879 respectively[23].The author was proposing a real time system for fatty cardiac substructure using yolo model (You Only Look Once) framework on US video. In YOLO model could be used end to end neural network model for predictions of cardiac substructure.…”