Ischemic region segmentation method, device and equipment and storage medium

Abstract

The invention relates to the technical field of image processing, in particular to an ischemic region segmentation method and device, equipment and a storage medium, and the method comprises the steps: obtaining an apparent diffusion coefficient image of the brain of a target object; acquiring a cerebral blood flow image, a cerebral blood volume image and an artery passing time image of the brain of the target object; and processing the apparent diffusion coefficient image, the cerebral blood flow image, the cerebral blood volume image and the artery passing time image by using a pre-trained classification model to obtain an ischemic region segmentation image of the brain of the target object. According to the ischemic region segmentation method, the ischemic region is segmented by combining the diffusion weighted image information and the delayed artery spin marking perfusion image information after marking, mutual information among various images is fully utilized, and the accuracy and robustness of ischemic region segmentation are improved.

Description

technical field [0001] The present invention relates to the technical field of image processing, and in particular, to a method, device, equipment and storage medium for ischemic region segmentation. Background technique [0002] Ischemic stroke is a common cerebrovascular disease, which has been seriously endangering human health, and its morbidity, disability and mortality rates are very high. How to quickly and effectively diagnose ischemic stroke is an important research topic in current clinical work. The early detection of ischemic stroke is very important, especially the correct detection in the hyperacute phase, which can guide timely measures to reduce the necrosis of brain cells in the ischemic penumbra area around the infarct. diagnosis and treatment are of great importance. [0003] In the prior art, brain parenchyma imaging is commonly used for disease diagnosis, curative effect evaluation and prognosis judgment, among which Arterial Spin Labeling (ASL) perfus...

AI Technical Summary

Problems solved by technology

[0004] However, the CBF image calculated by the existing ASL technique is sensitive to the selection of PLD, when the arterial transit time in a certain region is greater than the PLD, the CBF value will be severely underestimated, and the segmentation method by comparing with the contralateral value will miss The possibility of bilateral ischemia, and because the normal white matter CBF value is lower than the normal gray matter CBF value, the segmentation method by comparing with the contralateral value may include too much white matter signal, affecting the accuracy of the segmentation results

Moreover, the existing ASL technology and DWI technology use the absolute threshold segmentation method without considering the inconsistency of different individuals, which will lead to unstable segmentation results

Images