Cranial nerve automatic segmentation method based on large sample data driving

Abstract

The invention discloses a cranial nerve fiber automatic segmentation method based on large sample data driving. A FreeSurfer tool is used for carrying out brain region segmentation. A deterministic tracking method based on spherical deconvolution (SD_STREAM) is applied to perform fiber tracking of brainstem and cerebellum parts on original DTI data, and on the basis of a cranial nerve fiber atlasobtained by a multi-sample registration and clustering method, sample data is mapped and registered to obtain a target cranial nerve fiber bundle. Compared with a common method for manually drawing ROI and removing wrong fibers, the method has the advantages that subjectivity introduced by manual operation is eliminated, meanwhile, the imaging determinacy of the fiber bundle is guaranteed, data errors are reduced, and an efficient, accurate, stable and repeatable method can be provided for cranial nerve fiber segmentation.

Description

technical field [0001] The invention relates to the fields of medical imaging and neuroanatomy under computer graphics, in particular to an automatic cranial nerve segmentation method based on fiber atlas. Background technique [0002] Cranial nerves are 12 pairs of left and right nerves that originate from the brain, and are in charge of important functions such as smell, vision, and eye movement. Among the 12 pairs of cranial nerves, except for the olfactory and hypoglossal nerves, the remaining 10 pairs of nerves are more likely to be damaged. Injury to the cranial nerves can cause loss of general sensation in the skin of the head and face and mucous membranes of the tongue, mouth, and nasal cavity, dyskinesia of the masticatory muscles on the affected side, and loss of corneal reflexes. During the treatment of cranial nerves, fiber imaging technology is used to make up for the deficiency of clinical examination in the diagnosis of pathological processes. Diffusion tens...

AI Technical Summary

Problems solved by technology

[0005] The existing imaging technology relies too much on the operation of medical workers, and has a strong subjectivity. At the same time, it cannot guarantee the accuracy of the ROI drawn each time, which may easily cause fiber tract imaging uncertainty and data errors.

Images