Cardiovascular vulnerable plaque recognition method and system based on attention model and multi-task neural network

Abstract

The invention discloses a cardiovascular vulnerable plaque recognition method and system based on an attention model and a multi-task neural network. The method comprises the steps of (1) eliminatingnoise in an original polar coordinate image based on a top-down attention model, (2) classifying and segmenting a vulnerable plaque image in a preprocessed image by using a multi-task neural network,and (3) performing regional refinement on a classified and segmented vulnerable plaque image. The system includes a subsystem which eliminates the noise in the original polar coordinate image to obtain the preprocessed image based on the top-down attention model, a subsystem which classifies and segments a vulnerable plaque in the preprocessed image by using the multi-task neural network and a subsystem which carries out regional refinement on the classified and segmented vulnerable plaque image, and the subsystems are connected in order. The noise interference of a blood vessel to subsequentvulnerable plaque recognition is eliminated, and thus the positioning of the vulnerable plaque is more accurate.

Description

technical field [0001] The invention belongs to the field of medical image processing, and relates to a cardiovascular vulnerable plaque recognition method and system based on an attention model and a multi-task neural network. Background technique [0002] Vulnerable plaque is the most dangerous plaque in coronary atherosclerotic lesions. Vulnerable plaque is the main cause of thrombosis, acute coronary syndrome, and even sudden death. Therefore, detection and identification of various plaques Vulnerable plaque has a very high value. Cardiovascular optical coherence tomography is an intravascular imaging technology using near-infrared light reflection imaging, which can clearly observe vulnerable plaques. Therefore, the identification of vulnerable plaques based on optical coherence tomography (OCT) has become a important research trends. [0003] Commonly used performance evaluation criteria for OCT vulnerable plaques include: the recall rate R of vulnerable plaque detec...

AI Technical Summary

Problems solved by technology

[0005] definition Set the initial value of nTP, nFP, nFN to 0; sequentially judge the detection area from 1 to M, if any B i , B j All are judged as errors and do not participate in the following calculations; if B i with any A k If there is an intersection, and the DSC value is greater than 0.5, it is considered that the target i is detected correctly, Ntp++, and the DSC value is less than or equal to 0.5, it is considered that the target i is detected incorrectly, nFP++; sequentially judge the real detection target area from 1 to N; if A k with any B i If there is no intersection, it is considered that the target is judged as missed detection, nFN++; recall rate R: R=nTP / (nTP+nFN); accuracy rate P: P=nTP / (nTP+nFP); coincidence degree D is all detected correct The mean value of the DSC value of the area and its corresponding real area, The recall rate, accuracy rate and coincidence degree of the existing OCT image recognition method are not high, and the precision is low, which cannot meet the actual needs

Images