Focus recognition method for ischemic stroke magnetic resonance images

Abstract

The invention relates to the technical field of medical auxiliary recognition and relates to a focus recognition method for ischemic stroke magnetic resonance images. The method comprises an image input step, a DWI image processing step, an ASL image processing step, an infusion calculation step, a low perfusion calculation step, a DWI three-dimensional reconstruction step, an ASL three-dimensional reconstruction step, and an ischemia semi-dark zone identification step and the like. In the DWI image processing step and the ASL image processing step, a morphological method is adopted to enhance the characteristics of the image. Focus segmentation and direct volume calculation are realized based on a segmentation method of an adaptive threshold value. Ischemia semi-dark band recognition is realized through an image registration algorithm, and then a Mismatch value is calculated. The cerebral arterial thrombosis lesion position can be accurately recognized, a specific lesion volume value is provided, three-dimensional visual data display is provided, an accurate reference basis is provided for diagnosis and treatment of doctors, and clinical decision making of the doctors is assisted.

Description

technical field [0001] The invention relates to the technical field of medical aided identification, in particular to a lesion identification method for magnetic resonance images of ischemic stroke. Background technique [0002] Stroke is a common cerebrovascular disease characterized by high morbidity, mortality and disability. Acute ischemic stroke (acute ischemic stroke, AIS) accounts for 60% to 80% of strokes, and it is a disorder of blood supply to brain tissue caused by various reasons. Brain parenchyma imaging is commonly used clinically for disease diagnosis, curative effect evaluation, and prognosis judgment. Among them, DWI technology has extremely high sensitivity for infarction, and ASL can observe the range of ischemic penumbra very well, so as to evaluate the treatment. If the ratio of the volume of the ischemic penumbra to the volume of the infarct (Mismatch) is greater than or equal to 1.8, more brain tissue can be saved, and thrombolysis and other operatio...

AI Technical Summary

Problems solved by technology

[0005] In the technical method disclosed in Chinese patent CN109509186, the region growing process is adopted to enhance the image features of the lesion area, but the region growing method is an iterative method, and the space and time overhead are relatively large, and noise and uneven gray scale may cause Causes holes and over-segmentation, and is often not very good at handling shadow effects in images

The difference in image features based on brain symmetry is used to determine the lesion area. Due to the influence of differences in brain lateralization caused by differences in cognitive functions, the bilateral cerebral hemispheres themselves have structural and morphological differences, which will bring certain errors to the segmentation.

And the obtained results are only displayed on a single image, which provides limited help for doctors

Images