Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Medical-image-oriented multi-thread parallel computing method

A medical image and parallel computing technology, applied in the field of medical image processing, can solve problems such as the inability to significantly improve the overall performance of the system, and achieve the effects of improving program operation efficiency, reducing execution time, and optimizing medical image processing programs.

Inactive Publication Date: 2014-03-12
XIAMEN UNIV
View PDF5 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in 2005, when the main frequency was close to 4 GHz, Intel and Advanced Microelectronics discovered that the speed would also encounter its own limit: that is, simply increasing the main frequency could not significantly improve the overall performance of the system.

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
  • Medical-image-oriented multi-thread parallel computing method
  • Medical-image-oriented multi-thread parallel computing method
  • Medical-image-oriented multi-thread parallel computing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] Embodiments of the present invention include the following steps:

[0018] 1) Decompose the source image into multiple small image blocks that can be processed independently (for example, as shown in Table 1, first extend the boundary of the 64x64 image, and divide the source image into 4096 pieces with each pixel as the starting point for the expanded image 8x8 small image block), so as to divide the processing of the original image into a set of subtasks whose size is Q;

[0019] Table 1

[0020]

[0021] In Table 1, the numerical value represents the pixel number, the solid thick line frame area is the original image, the fine dotted line frame area is the image block 1 expanded with pixel 1 as the pivot, and the thick dotted line frame area is the pixel 2 as the pivot Extended image blocks.

[0022] 2) Use C language or multi-thread programming technology in Open Multi-Processing (OpenMP) language to create N threads, and then distribute the Q subtasks decompos...

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 discloses a medical-image-oriented multi-thread parallel computing method, and relates to a medical image processing method, in particular to an image processing and optimizing method for applying a multi-thread thought and a programming method to medical images. On a processor supporting hyper threading or a multi-core technology, multi-thread programming is performed by using hardware resources on the processor by means of software. The method comprises the following steps: partitioning a medical image needing to be processed into image blocks which can be processed independently and grouping the image blocks; simultaneously running a plurality of threads in different kernels of different processors at the same moment by using a multi-thread technology; enabling each thread to execute image block groups with relatively average workload from an original image respectively and to carry out parallel processing on an original image processing task set till all threads finish processing; and summarizing processing results, and outputting. Through the overall multi-thread parallel computation, the execution efficiency of image processing can be increased, and the aim of accelerating computation is fulfilled.

Description

technical field [0001] The invention relates to a medical image processing method, in particular to a medical image-oriented multi-thread parallel computing method. Background technique [0002] Medical image processing (including magnetic resonance images, computed tomography images, and ultrasound images, etc.) plays an important role in medical imaging science and clinical practice. With the development of image processing technology and people's increasing attention to medical health, it is expected that the running time of medical image processing will be reduced. The emergence of hyper-threading and multi-core technology provides the possibility to accelerate medical image processing. [0003] In 1971, Intel launched the world's first general-purpose microprocessor, the 4004, which consisted of 2,300 transistors. At that time, Gordon Moore proposed "Moore's Law", which was later regarded as a creed by the industry-every 18 months, the number of transistors that can b...

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
IPC IPC(8): G06F9/38
Inventor 屈小波沈前进李淇越郭迪陈忠
Owner XIAMEN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com