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

An FPGA-based method for cell classification in real-time hyperspectral microscopy images

A hyperspectral image and microscopic image technology, applied in the field of biomedical images, can solve problems such as error, misdiagnosis, missed diagnosis, and lack of quantitative standards

Active Publication Date: 2020-11-20
BEIJING UNIV OF CHEM TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditional blood cell examination mainly relies on medical personnel to observe blood samples through a microscope to predict blood diseases. However, this method of relying on manual observation relies entirely on each person's clinical experience, lacks quantitative standards, and has certain errors. misdiagnosis, misdiagnosis

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
  • An FPGA-based method for cell classification in real-time hyperspectral microscopy images
  • An FPGA-based method for cell classification in real-time hyperspectral microscopy images
  • An FPGA-based method for cell classification in real-time hyperspectral microscopy images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] The basic flow of this method is as follows figure 1 As shown, a state machine is used on the FPGA, and the specific implementation will be introduced according to each state of the state machine.

[0061] 1) First convert the hyperspectral cell image data into a 16-bit binary unsigned number, input the first set of data in the hyperspectral cell image after this preprocessing into the FPGA chip, and convert all variables in the top-level file to Set to zero, this is the initial ready state.

[0062] 2) Enter state=00 state, read data y and Through the multiplier IP core will as well as The part that needs to be multiplied in the operation is completed, because y and All are sixteen-bit data, after multiplication, with have become 32-bit data, and is thirty-two bits of data, so It is data of sixty-four bits.

[0063] 3) Enter state=01 state, will with Add up the multiplied components according to the formula, then complete with calculation, and ...

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 an FPGA-based real-time hyperspectral microscopic image cell classification method, which belongs to the field of biomedical images. The specific innovation point of the present invention is to realize hyperspectral image classification based on FPGA. The hyperspectral image classification method adopted is a collaborative representation-based classification method, referred to as CRC. Through a series of processing on the cell images collected by the imaging spectrometer, the image data is input to the FPGA, the cells are classified, and the data results are obtained to determine whether there are diseased cells. The use of hyperspectral imaging technology has made some progress in biomedical research, but it is still rare to apply this technology to FPGA. After this technology is implemented on FPGA, cell images can be processed and classified quickly and in real time, which greatly improves the efficiency of cell image processing and classification. Reducing manual identification can reduce the rate of misdiagnosis, so that doctors can get a certain amount of liberation in this regard, and it can also make patients feel more at ease about the diagnosis results.

Description

technical field [0001] The invention relates to an FPGA-based real-time hyperspectral microscopic image cell classification method, which belongs to the field of biomedical images. Background technique [0002] In recent years, as China has entered into an industrialized society, water pollution and air pollution have become more and more serious, and the number of patients with leukemia and other blood diseases is increasing day by day. In terms of domestic malignant tumor mortality, leukemia ranks in the top six, and adolescents under the age of 18 rank No. one. Passing blood tests early has important application value in the prevention of leukemia and other blood diseases. Traditional blood cell examination mainly relies on medical personnel to observe blood samples through a microscope to predict blood diseases. However, this method of relying on manual observation relies entirely on each person's clinical experience, lacks quantitative standards, and has certain errors...

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): G06K9/00G06K9/62
CPCG06V20/698G06F18/214
Inventor 李伟吴晶晶
Owner BEIJING UNIV OF CHEM TECH
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