Abstract
BackgroundCoronary artery angiography is an indispensable assistive technique for cardiac interventional surgery. Segmentation and extraction of blood vessels from coronary angiographic images or videos are very essential prerequisites for physicians to locate, assess and diagnose the plaques and stenosis in blood vessels.MethodsThis article proposes a novel coronary artery segmentation framework that combines a three–dimensional (3D) convolutional input layer and a two–dimensional (2D) convolutional network. Instead of a single input image in the previous medical image segmentation applications, our framework accepts a sequence of coronary angiographic images as input, and outputs the clearest mask of segmentation result. The 3D input layer leverages the temporal information in the image sequence, and fuses the multiple images into more comprehensive 2D feature maps. The 2D convolutional network implements down–sampling encoders, up–sampling decoders, bottle–neck modules, and skip connections to accomplish the segmentation task.ResultsThe spatial–temporal model of this article obtains good segmentation results despite the poor quality of coronary angiographic video sequences, and outperforms the state–of–the–art techniques.ConclusionsThe results justify that making full use of the spatial and temporal information in the image sequences will promote the analysis and understanding of the images in videos.
Highlights
Coronary artery angiography is an indispensable assistive technique for cardiac interventional surgery
The acquisition equipments of these video clips are products of many different manufacturers, so the image resolution ranges from 512 × 512 to 769 × 718, the frame rate ranges from 10fps to 15fps, and the original video format is wmv, MP4, etc
We use ffmpeg software toolkit to extract each frame of the videos and save it as a losslessly encoded red– green–blue (RGB) image file with a color depth of 8 bits in each chromatic channel
Summary
Coronary artery angiography is an indispensable assistive technique for cardiac interventional surgery. Segmentation and extraction of blood vessels from coronary angiographic images or videos are very essential prerequisites for physicians to locate, assess and diagnose the plaques and stenosis in blood vessels. Physicians have been practicing interventional surgeries to diagnose and treat cardiovascular diseases for several decades They locate, assess and diagnose the blood vessel stenosis and plaques by directly watching the angiographic videos with naked eyes during the surgeries. Based on their experiences, the physicians quickly make a qualitative judgment on the patient’s coronary artery condition and plan the treatment. A dual encoding U–Net was proposed to replace the skip– connections with attention modules to further promote of retinal vessel segmentation [15]
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call