Three-dimensional nonlinear registration method and system for massive brain image datasets

A technology of nonlinear registration and image data set, which is applied in the field of image processing to achieve the effect of fast nonlinear registration

Active Publication Date: 2021-09-28
HUST SUZHOU INST FOR BRAINMATICS
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, with the advent of the era of big data, massive 3D image data sets continue to increase, and there is no nonlinear registration method that can handle TB-level 3D image data.

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
  • Three-dimensional nonlinear registration method and system for massive brain image datasets
  • Three-dimensional nonlinear registration method and system for massive brain image datasets
  • Three-dimensional nonlinear registration method and system for massive brain image datasets

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The present invention will be described in further detail below in conjunction with the accompanying drawings. figure 1 It shows a schematic flowchart of the three-dimensional non-linear registration method for massive brain image data sets provided by the preferred embodiment of the present invention.

[0045] A three-dimensional non-linear registration method for massive brain image data sets, comprising the following steps:

[0046] S0. A down-sampling step, down-sampling the preset high-resolution reference image data and high-resolution image data to be registered to obtain low-resolution reference image data and low-resolution image data to be registered.

[0047] Wherein, the high-resolution reference image data D1 and the high-resolution image data D2 to be registered. The two high-resolution image data are down-sampled to obtain low-resolution reference image data D3 and low-resolution image data D4 to be registered. The down-sampling process must ensure two ...

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 present invention relates to a three-dimensional non-linear registration method and system for massive brain image datasets, the three-dimensional nonlinear registration method for massive brain image datasets comprises the following steps: S0. down-sampling step; S1. low-resolution image Registration steps, including: S11. Linear registration steps; S12. Non-linear registration steps; S2. High-resolution image fast transformation steps, including: S21. Transformation matrix calculation steps for high-resolution registration; S22. High-resolution Step of calculating spatial range after registration; S23. Blocking step; S24. High-resolution nonlinear transformation step. The invention utilizes registration information of low-resolution image data to transform massive high-resolution three-dimensional image data sets to realize nonlinear registration of massive high-resolution three-dimensional image data sets. The invention is applicable to all linear registration based on transformation matrix and all nonlinear registration based on displacement field, and can rapidly perform nonlinear registration on TB level data sets.

Description

technical field [0001] The invention relates to image processing technology, in particular to a three-dimensional non-linear registration method for massive brain image data sets. Background technique [0002] As an important research direction in the field of image processing, image registration technology is widely used in remote sensing, automatic navigation, pattern recognition, computer vision, biomedicine and other fields. With the advent of the era of big data, massive 3D image data sets continue to increase, often reaching TB level. How to perform nonlinear registration on these massive 3D datasets is a very big challenge. [0003] In the Chinese invention patent specification CN104361590, a high-resolution remote sensing image registration method with adaptive distribution of control points is proposed. The control points are extracted, and then the normalized mutual information measure NMI is used to match the control points at multiple scales. However, the data...

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 & AuthorityPatents(China)
IPC IPC(8): G06T3/00
CPCG06T3/147
Inventor李安安谭朝镇骆清铭龚辉丰钊
OwnerHUST SUZHOU INST FOR BRAINMATICS