A system for detecting total occlusion lesions in coronary angiography based on deep learning

Abstract

The invention discloses a system for detecting whether there is a complete occlusion lesion in coronary angiography based on deep learning. The deep learning cyclic neural network is used to analyze the overall video, and the detection result is obtained by accelerated calculation using a GPU (graphics processor). Shixiao solves the real-time problem of detection. The system in the present invention includes a video input module, a convolutional neural network module, a codec attention module and a classification module. In particular, the codec attention module and its supervision algorithm proposed by the present invention are used to generate appropriate attention weights to improve detection accuracy. The end-to-end system design automates the coronary artery total occlusion detection workflow without complex intermediate steps. Compared with other systems for detecting the presence or absence of completely occluded lesions, the present invention analyzes the overall video instead of a single image, reduces the misjudgment caused by a single image, and significantly improves the accuracy of judging the existence of completely occluded lesions.

Description

technical field [0001] The invention relates to the technical field of digital image processing, in particular to a system for detecting whether there is a total occlusion lesion in coronary angiography based on deep learning. Background technique [0002] Coronary angiography videos are commonly used medical data for diagnosing cardiovascular disease. Cardiovascular lesions such as calcification, thrombus, stenosis and complete occlusion can all be observed through coronary angiography video. Thanks to the development of artificial intelligence and machine learning, there are already many applications that use deep learning methods to analyze medical data and assist in diagnosis. [0003] Existing applications are generally based on medical images, and use convolutional neural networks to extract abstract features and process them for classification and detection. Due to the technology and equipment of medical data, the image taken has a lot of noise, and it is easy to ca...

AI Technical Summary

Problems solved by technology

However, in the coronary angiography video, we only need to focus on the key video frames in the filling stage, and the analysis of the entire video increases the amount of calculation.

In addition, for completely occluded lesions, the observed morphology of the lesion is reflected by the absence of contrast agent and incomplete vascular morphology, which is similar to the vascular morphology in the diffusion and dissipation stages, resulting in misjudgment, so it is flawed to analyze the entire video

Images