The invention provides a left heart
data analysis method and
system based on
image segmentation, and relates to the technical field of medical
image processing. Comprising the following steps: acquiring
cardiac ultrasound image data and preprocessing; performing
image segmentation on the preprocessed image data to obtain a segmentation result including a left
ventricle, a left
ventricular wall and a
left atrium; searching a
boundary line of the left
ventricle and the
left atrium, selecting two boundary points corresponding to the minimum and maximum abscissas in the
boundary line as left and right
mitral valve ring points respectively, and establishing a
long axis based on the
mitral valve ring midpoint and the
cardiac apex point; modeling the
ventricle into a structure formed by superposing a plurality of discs along the
long axis direction, and obtaining the
diameter of the corresponding disc; based on the obtained diameters of the corresponding discs, the left ventricular volumes in the diastolic period and the systolic period are calculated respectively, and the
left ventricular ejection fraction is calculated. According to the method,
image segmentation and
geometric modeling are fused to achieve accurate calculation of the cardiac
ejection fraction, meanwhile, the accuracy of
cardiac structure image segmentation is improved, and an interpretable
ejection fraction estimation process is achieved.