An automatic segmentation method of cranial nerves driven by large sample data

Abstract

An automatic segmentation method of cranial nerve fibers driven by large sample data, using the FreeSurfer tool for brain region segmentation, applying a deterministic tracking method based on spherical deconvolution (SD_STREAM) to track the fibers of the brainstem and cerebellum on the original DTI data , on the basis of the cranial nerve fiber atlas obtained by the multi-sample registration and clustering method, the target cranial nerve fiber bundle is obtained by mapping and registering the sample data. Compared with the commonly used methods of manually drawing ROIs and removing wrong fibers, the present invention eliminates the subjectivity introduced by human operations, while ensuring the certainty of fiber tract imaging, reducing data errors, and providing efficient, accurate and stable methods for cranial nerve fiber segmentation. , repeatable method.

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