Optic nerve segmentation method and device in magnetic resonance image

Abstract

Embodiments of the present invention provide a method and device for optic nerve segmentation in a magnetic resonance image, including: performing image registration on a target magnetic resonance image to obtain spatial probability distribution information of the target magnetic resonance image, where the spatial probability distribution information includes visual shape information and position information of the pathway; based on the trained visual pathway segmentation model, predict the target magnetic resonance image and the spatial probability distribution information, and obtain the visual pathway segmentation image of the target magnetic resonance image; the The trained visual pathway segmentation model is obtained by training the sample magnetic resonance images and the sample spatial probability distribution information. In the embodiment of the present invention, by obtaining the spatial probability distribution information of the visual pathway in the magnetic resonance image, and according to the shape information and position information of the spatial probability distribution information, the visual pathway in the magnetic resonance image is segmented, which effectively overcomes the blurring of the boundary of the visual pathway. problem, to achieve accurate segmentation of the visual pathway.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method and device for segmenting an optic nerve in a magnetic resonance image. Background technique [0002] Magnetic Resonance (MR) imaging is an imaging technique that uses the signal generated by the resonance of atomic nuclei in a strong magnetic field to undergo image reconstruction. Today, image-guided surgical navigation based on magnetic resonance images has become an important part of sinus and skull base surgery. important aids. [0003] Due to the intricate anatomy of the sinuses, skull base, and adjacent orbital region, containing important neural and vascular structures, such as the visual pathway, its elongated anatomy, low contrast and blurred borders in MRI images, Target segmentation methods based on threshold or edge detection cannot achieve results at all, and because the visual pathway accounts for a small proportion of the entire head volume data,...

AI Technical Summary

Problems solved by technology

[0003] Due to the intricate anatomy of the sinuses, skull base, and adjacent orbital region, containing important neural and vascular structures, such as the visual pathway, its elongated anatomy, low contrast and blurred boundaries in MRI images, Target segmentation methods based on threshold or edge detection cannot achieve results at all, and because the visual pathway accounts for a small proportion of the entire head body data, the accuracy of the existing visual pathway segmentation methods is low

Images