Image processing method and device, electronic equipment and storage medium

Abstract

The invention provides an image processing method and device, electronic equipment and a storage medium. The method comprises the steps: acquiring cardiac magnetic resonance film imaging of at least one view angle; for each view angle, marking off the range of a left ventricle myocardial region in each frame of cardiac magnetic resonance imaging in the cardiac magnetic resonance film imaging of the view angle so as to obtain a region segmentation image group of the view angle; for each view angle, performing binarization processing on each frame of region segmentation image in the region segmentation image group of the view angle to obtain a binary segmentation image group of the view angle; for each view angle, inputting the binary segmentation image group of the view angle into a spatial-temporal feature extraction network to obtain spatial-temporal features of the left ventricular myocardial region corresponding to the view angle; and acquiring a multi-classification result based on the spatio-temporal feature vector corresponding to the spatio-temporal feature. According to the method and the device, the probability of suffering from different left ventricular diseases can be judged according to the motion morphological characteristics of the left ventricular myocardial region in the multi-frame image of at least one view angle.

Description

technical field [0001] The present application relates to the field of data processing, in particular, to an image processing method, device, electronic equipment and storage medium. Background technique [0002] Left ventricular hypertrophy (left ventricular hypertrophy, LVH) is common in a variety of primary or secondary heart diseases, and is an important independent risk predictor of cardiovascular events and all-cause mortality. Hypertrophic cardiomyopathy (HCM), cardiac amyloidosis (cardiac amyloidosis, CA), and left ventricular hypertensive burden (hypertension, HTN) are the most common LVH diseases. Early and accurate disease diagnosis is crucial to determine the timing of surgical intervention The determinants of cardiac pacemaker implantation and treatment are also key issues that affect the health and quality of life of such patients. Although LVH patients all showed abnormal ventricular wall thickening and specific changes in myocardial tissue morphologically, t...

AI Technical Summary

Problems solved by technology

[0003] The LGE sequence of cardiac magnetic resonance (Cardiovascular magnetic resonance, CMR) can be used for the assessment of myocardial fibrosis and is an important tool for the diagnosis of LVH. However, CMR of the LGE sequence relies on contrast agents and takes a long time to scan; the rise of the T1mapping sequence provides an objective and quantitative assessment of myocardial fibrosis. The characteristics provide the possibility, but the scanning parameters of different machines in different centers are inconsistent, and the basic reference value of mapping depends on the accumulation of cases in each center. Even if the nativeT1 mapping without contrast agent is used as the diagnostic modeling object, it is difficult to be generalizable and clinical Adaptability; as the basic sequence of routine CMR examination, the cardiac film sequence has low scanning conditions. With the advancement of technology (such as ECG gating and respiratory gating), the requirement for patient cooperation is also decreasing. At the same time, the image With continuous improvement in quality, it is the gold standard for calculating traditional volumetric cardiac function evaluation indicators (including left ventricular volume, stroke volume, left ventricular ejection fraction (LVEF), etc.)

However, although these indicators can distinguish patients with HTN, HCM and CA to a certain extent, patients with severe HTN and patients with end-stage HCM also have decreased LVEF. limitation

Images