Method and device for detecting vascular stenosis in coronary artery X-ray sequential radiography

Abstract

The invention discloses a method and a device for detecting vascular stenosis in coronary artery X-ray sequential radiography, which can be used for effectively detecting a suspected stenosis area ona blood vessel in a sequential image to obtain an accurate coronary artery stenosis detection result, and can be used for really helping doctors to carry out effective and quick disease diagnosis. Themethod comprises the following steps: (1) acquiring sequence image information of an XRA image; (2) coronary artery stenosis detection: combining front and back frame information in the sequence image to realize coronary artery stenosis section detection on the single-frame image, performing depth sequence feature fusion on continuous multi-frame image detection results to obtain more accurate stenosis detection results on each frame of the continuous multi-frame image, and taking the detection results as initial sequence stenosis detection results; and (3) processing the initial sequence narrow detection result, and obtaining an accurate detection result by removing repeated detection boxes in the frame and reserving the detection box with high similarity in the sequence.

Description

technical field [0001] The invention relates to the technical field of medical image processing, in particular to a method for detecting vascular stenosis in coronary X-ray sequence angiography, and also to a device for detecting vascular stenosis in coronary X-ray sequence radiography. Background technique [0002] Considering that most existing detection methods for coronary artery stenosis are aimed at three-dimensional CT angiography (Computed Tomography Angiography, CTA), or single-frame two-dimensional angiography images, these methods cannot well realize two-dimensional coronary artery X-ray sequence angiography images ( Detection of coronary artery stenosis in X-Ray Angiography (XRA) images, so the present invention proposes a method that can automatically detect vascular stenosis and mark its position from coronary artery XRA sequence images. Accurate detection of coronary artery stenosis on serial XRA images can assist doctors to complete disease diagnosis efficien...

AI Technical Summary

Problems solved by technology

However, some of these methods have poor detection accuracy and slow detection speed, which cannot really help doctors to carry out effective and rapid disease diagnosis

Images