Automatic analysis system and method of contrast-enhanced echocardiography ventricular wall thickness based on deep learning

Abstract

The invention discloses an automatic analysis system and method of contrast-enhanced echocardiography ventricular wall thickness based on deep learning. The system comprises a data acquisition and uploading module, a data identification and quality control module and a data measurement and presentation module; the data acquisition and uploading module acquires enhanced echocardiography examination image videos and electrocardiogram examination images, and uploads the images to the data identification and quality control module; the data identification and quality control module preprocesses the uploaded images and videos through a deep learning algorithm module, marks different tissue structures, and performs image quality analysis and feasibility evaluation; and the data measurement and presentation module is used for measuring ventricular wall thickness data of the marked images, and automatically outputting and presenting a measured result to an ultrasonic image workstation. The automatic analysis system combines the advantage of the deep learning algorithm, automation and standardization of data analysis are achieved, differences in individuals and among individuals of ventricular wall thickness measurement are reduced, and repeatability and consistency of ventricular wall thickness measurement are remarkably improved.

Description

technical field [0001] The invention relates to the technical field of ultrasonic medicine, in particular to a system and method for automatic analysis of wall thickness of a contrast-enhanced echocardiogram based on deep learning. Background technique [0002] Accurate measurement of ventricular wall thickness is of great significance in differentiating normal echocardiographic findings from cardiovascular diseases and clarifying the disease process and prognosis. However, due to the low resolution of the epicardial and endocardial boundaries in the current measurement of two-dimensional ultrasound wall thickness, there are obvious intra-individual and inter-individual differences, and the location of hypertrophy is also subject to individual subjectivity. [0003] Therefore, it is necessary to design a system and method for automatic measurement and analysis of cardiac echocardiography, so as to realize the automation and standardization of data analysis, and significantly...

AI Technical Summary

Problems solved by technology

However, due to the low resolution of the epicardial and endocardial boundaries in the current measurement of two-dimensional ultrasound wall thickness, there are obvious intra-individual and inter-individual differences, and the location of hypertrophy is also subject to personal subjectivity.

Images