Method and device for carrying out object analysis on medical image and storage medium

Abstract

The invention relates to a method and device for carrying out object analysis on a medical image and a storage medium. The method may include the following steps. A 3D medical image containing a subject may be acquired. The 3D medical image may be segmented to obtain a segmentation result of the object. A set of image tiles may be acquired in the 3D medical image in an extending direction. Internal representative points of the segmented object in each of the set of image tiles may be obtained. A set of image tiles in the 3D medical image may be acquired based on a set of internal representative points of the object of the set of image slices. Object analysis may be performed based on the set of image blocks. According to the method and the device, image slice layers and internal representative points on a 3D medical image are acquired; the 3D medical image is segmented based on the internal representative points, and the method can maintain the central point of the image block to be located in an organ or tissue (such as a blood vessel) while improving the prediction efficiency.

Description

technical field [0001] The present disclosure relates to the field of medical images, and more particularly, to a method, device and storage medium for object analysis on medical images. Background technique [0002] Vascular diseases have always been an important issue threatening human health. A considerable proportion of vascular diseases are caused by the accumulation of plaque lesions on the vessel wall causing vascular stenosis and abnormal swelling on the vessel wall causing aneurysms. There are certain deficiencies in detection and identification. [0003] Take head and carotid artery plaque as an example, head and carotid artery disease usually refers to the narrowing or blockage of arteries due to the accumulation of atherosclerotic plaque on the artery wall. Patients with narrowed and blocked intracranial arteries have limited blood supply to the brain, which can easily lead to ischemic stroke. If the plaque ruptures, it is easy to block and damage blood vessels...

AI Technical Summary

Problems solved by technology

This scheme has the problem of too many image blocks and low prediction efficiency; the image blocks selected by this scheme will predict lesions in non-vascular areas, and the prediction results are prone to more false positive lesions

Existing schemes for obtaining blood vessel center points generally rely on blood vessel skeletonization or centerline extraction. However, the calculation of blood vessel skeletonization takes a long time, and the obtained center points are relatively redundant, which reduces the efficiency of model prediction. In addition, skeletonization is vulnerable to vessel segmentation. Influenced by the results, especially the distribution of skeletonized results at the bifurcation of blood vessels is extremely uneven, and the center point of the selected image block is generally not in the blood vessel, which will adversely affect the prediction results; the blood vessel centerline extraction scheme not only needs to determine the starting point of the blood vessel, but also It is easily affected by the results of blood vessel segmentation, resulting in the wrong growth of the center line and affecting the extraction of the center point of the blood vessel. For example, when the result of blood vessel segmentation is discontinuous, the extraction of the center line is very easy to fail

Images