Multispectral fluorescence segmentation method and apparatus

A multi-spectral and fluorescence technology, applied in image analysis, image data processing, image enhancement, etc., can solve the problem of low accuracy of excitation fluorescence spot segmentation results, and achieve the effect of strengthening correlation and improving accuracy.

Active Publication Date: 2018-06-29
BEIJING DIGITAL PRECISION MEDICAL TECH CO LTD
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] An embodiment of the present invention provides a multi-spectral fluorescence segmentation method to solve the technical problem of low accuracy in the segmentation results of excited fluorescence spots in the prior art

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
  • Multispectral fluorescence segmentation method and apparatus
  • Multispectral fluorescence segmentation method and apparatus
  • Multispectral fluorescence segmentation method and apparatus

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0013] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be described in further detail below in conjunction with the embodiments and accompanying drawings. Here, the exemplary embodiments and descriptions of the present invention are used to explain the present invention, but not to limit the present invention.

[0014] In an embodiment of the present invention, a multispectral fluorescence segmentation method is provided, such as figure 1 As shown, the method includes:

[0015] Step 101: Obtain a multi-spectral fluorescence segmentation neural network, which is obtained by training a three-dimensional convolutional neural network, using multiple groups of surface-excited fluorescence images of different wavelengths obtained under laser excitation as a training center The required input data, using multiple sets of surface fluorescence images of different wavelengths obtained without laser excitation a...

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

Embodiments of the invention provide a multispectral fluorescence segmentation method and apparatus. The method comprises the steps of obtaining a multispectral fluorescence segmentation neural network, wherein the multispectral fluorescence segmentation network is obtained by training a three-dimensional convolutional neural network; taking multiple groups of surface excitation fluorescence images of different wavelengths obtained under a laser excitation condition as input data required for training, and taking multiple groups of surface fluorescence images of different wavelengths obtainedunder no laser excitation condition as a fluorescence spot distribution result of training; and obtaining to-be-processed multispectral excitation fluorescence images, and inputting the to-be-processed multispectral excitation fluorescence images to the multispectral fluorescence segmentation neural network, thereby obtaining a segmentation result of excitation fluorescence spots. According to thescheme, the situation that the fluorescence images of the different fluorescence wavelengths have optical correlation, so that an effective fluorescence region can be accurately divided and the accuracy of the segmentation result of the excitation fluorescence spots can be improved.

Description

technical field [0001] The invention relates to the technical field of optical imaging, in particular to a multispectral fluorescence segmentation method and device. Background technique [0002] Optical imaging technology is an emerging molecular imaging technology in recent years. It has the advantages of high sensitivity, non-ionizing radiation, and simple operation. It is a technology that can realize biophysical process imaging inside biological tissues at the molecular level. In addition, optical imaging technology is being gradually applied to clinical surgical navigation and other fields by mounting fluorescence cameras and laser light sources on endoscopes. By injecting the corresponding targeted probe drug into the imaging object, and irradiating the observation site with the laser mounted on the endoscope, the fluorescence information of the observation site under the laser irradiation is captured. However, due to the influence of the excitation light source and ...

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 Applications(China)
IPC IPC(8): G06T7/11G06N3/04
CPCG06T7/11G06T2207/10036G06T2207/10064G06T2207/20081G06T2207/20084G06T2207/30096G06N3/045
Inventor 迟崇巍王丽
Owner BEIJING DIGITAL PRECISION MEDICAL TECH CO LTD
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