Method and system for terabyte-level brain nerve fiber data reduction based on deep learning

A neural fiber and deep learning technology, applied in the field of image processing, to achieve the effect of fast segmentation, wide application range, and alleviating the imbalance of positive and negative samples

Active Publication Date: 2022-05-20
HUAZHONG UNIV OF SCI & TECH
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The generation of massive data and the hysteresis of data processing tools pose new challenges to the reconstruction of neuron morphology

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method and system for terabyte-level brain nerve fiber data reduction based on deep learning
  • Method and system for terabyte-level brain nerve fiber data reduction based on deep learning
  • Method and system for terabyte-level brain nerve fiber data reduction based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] In the present embodiment, the method for reducing the whole brain data of mice with TB level sparsity comprises the following steps:

[0046] S1: Obtain the image to be tested and construct a whole brain test data set.

[0047] For example, the original image is selected from a mouse brain slice image obtained by a fluorescence microsection imaging system or a functional two-photon confocal imaging microscope. The test image data set is from the coronal slice data of the whole brain, and every 200 layers of coronal slices are used for maximum projection (the selection of the number of layers directly determines the size of the data volume of the data set to be tested; of course, in addition to 200 layers, there are also The specific number of layers can be adjusted according to the actual situation; when adjusting the number of layers, the quality of the projection data should be considered to avoid: i. the number of layers is too small, and the nerve fiber information...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention belongs to the field of image processing, and discloses a TB-level 3D cranial nerve data reduction method and system based on deep learning, wherein the method includes the following steps: S1: establish a test data set; S2: establish and train a segmentation model; S3: Use the segmentation model to process each test image in the test data set to obtain the nerve fiber distribution information corresponding to each test image; S4: Use morphological operations to optimize the nerve fiber distribution information to make the three-dimensional space The maximum connected domain corresponding to the region where the nerve fibers are located in the nerve fiber contour map below is optimized, and finally the data reduction results of TB-level sparse whole-brain nerve fibers are obtained. The present invention can quickly, accurately and effectively reduce cranial nerve data sets of TB level and above, greatly reduce the amount of data for subsequent neuron reconstruction, and improve reconstruction efficiency.

Description

technical field [0001] The present invention belongs to the field of image processing, and more specifically relates to a method and system for reducing TB-level brain nerve fiber data based on deep learning. The method and system for reducing TB-level sparse brain nerve fiber data based on deep learning can be used for the reduction of whole-brain nerve fiber data in biomedical images. Background technique [0002] In recent years, a series of breakthroughs in molecular labeling and imaging technologies have made whole-brain-scale neural community imaging with single-cell resolution a reality. The generation of massive data and the lag of data processing tools pose new challenges to the reconstruction of neuron morphology. Neurons are widely distributed in the whole brain, and the distribution of each brain region is different, and there is a characteristic of sparseness on the scale of the whole brain, which makes it possible to reduce the nerve fibers in the whole brain....

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/00G06T7/10G06T7/13G06T5/30G06N3/04
CPCG06T7/0012G06T7/10G06T7/13G06T5/30G06T2207/20081G06T2207/30016G06T2207/10012G06N3/045
Inventor 全廷伟黄青刘世杰骆清铭曾绍群
Owner HUAZHONG UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products