Coronary artery segmentation method, electronic device, and computer-readable storage medium

An electronic device, comprising:

• a processor;
• and
• a memory, wherein the memory stores computer program instructions, and when the computer program instructions are run by the processor, the processor is configured to implement a coronary artery segmentation method, the coronary artery segmentation method comprising:
• iteratively performing a detection step for a to-be-detected image, wherein the detection step comprises the following steps:
• obtaining a to-be-detected region and regional coronary artery inspiration data corresponding to the to-be-detected region, wherein the to-be-detected region is a part of the to-be-detected image, and the regional coronary artery inspiration data is used to provide an inspiration during segmentation of the to-be-detected region;
• inputting the to-be-detected region with the regional coronary artery inspiration data into a pre-trained coronary artery segmentation model to obtain regional coronary artery segmentation data;
• obtaining a comparison result of the regional coronary artery segmentation data and the regional coronary artery inspiration data;
• replacing the to-be-detected region in the to-be-detected image with the comparison result to obtain a replaced to-be-detected image so as to complete the detection step;
• for a plurality of the detection steps corresponding to the to-be-detected image, selecting the to-be-detected region in a current detection step from the replaced to-be-detected image in a previous detection step, and using a part of the comparison result in the previous detection step as the regional coronary artery inspiration data in the current detection step;
• outputting a finally replaced to-be-detected image as coronary artery segmentation data after the to-be-detected image is fully traversed and replaced by the comparison result, wherein the to-be-detected region is a coronary artery origin region, and
• the obtaining a to-be-detected region and regional coronary artery inspiration data corresponding to the to-be-detected region comprises:
• obtaining newly added coronary artery segmentation data from the comparison result in the previous detection step;
• extracting a second framework from the newly added coronary artery segmentation data;
• selecting a second seed point on the second framework according to a second preset step length;
• pushing the second seed point into a seed point stack to obtain a second stack top seed point;
• selecting, on the replaced to-be-detected image in the previous detection step by using the center of the second stack top seed point as the center, a second region with a second preset size as the to-be-detected region, wherein the second region covers a part of the comparison result in the previous detection step;
• and
• using the comparison result in the previous detection step in the second region as the regional coronary artery inspiration data.

A non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores a computer program, and when the computer program is run by a processor, the processor is configured to implement a coronary artery segmentation method, the coronary artery segmentation method comprising:

• iteratively performing a detection step for a to-be-detected image, wherein the detection step comprises the following steps:
• obtaining a to-be-detected region and regional coronary artery inspiration data corresponding to the to-be-detected region, wherein the to-be-detected region is a part of the to-be-detected image, and the regional coronary artery inspiration data is used to provide an inspiration during segmentation of the to-be-detected region;
• inputting the to-be-detected region with the regional coronary artery inspiration data into a pre-trained coronary artery segmentation model to obtain regional coronary artery segmentation data;
• obtaining a comparison result of the regional coronary artery segmentation data and the regional coronary artery inspiration data;
• replacing the to-be-detected region in the to-be-detected image with the comparison result to obtain a replaced to-be-detected image so as to complete the detection step;
• for a plurality of the detection steps corresponding to the to-be-detected image, selecting the to-be-detected region in a current detection step from the replaced to-be-detected image in a previous detection step, and using a part of the comparison result in the previous detection step as the regional coronary artery inspiration data in the current detection step;
• outputting a finally replaced to-be-detected image as coronary artery segmentation data after the to-be-detected image is fully traversed and replaced by the comparison result, and
• the obtaining a to-be-detected region and regional coronary artery inspiration data corresponding to the to-be-detected region comprises:
• obtaining newly added coronary artery segmentation data from the comparison result in the previous detection step;
• extracting a second framework from the newly added coronary artery segmentation data;
• selecting a second seed point on the second framework according to a second preset step length;
• pushing the second seed point into a seed point stack to obtain a second stack top seed point;
• selecting, on the replaced to-be-detected image in the previous detection step by using the center of the second stack top seed point as the center, a second region with a second preset size as the to-be-detected region, wherein the second region covers a part of the comparison result in the previous detection step;
• and
• using the comparison result in the previous detection step in the second region as the regional coronary artery inspiration data.