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

Mesoscopic fluorescence molecular tomography method and system based on bottleneck residual GAN

A fluorescence molecular tomography and bottleneck technology, applied in the field of mesoscopic fluorescence molecular tomography imaging methods and systems, can solve the problem of mesoscopic fluorescence molecular tomography inverse reconstruction time and computational load, ill-posed and ill-conditioned , It is difficult to meet the problems of high precision and real-time reconstruction at the same time, so as to avoid the disappearance and explosion of gradients, reduce the computational cost, and improve the robustness and generalization.

Inactive Publication Date: 2020-10-09
SHANDONG INST OF BUSINESS & TECH
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Due to the strong scattering and low absorption characteristics of biological samples and the high spatial resolution of this imaging modality, the number of independent measurement data is far less than the number of parameters to be solved, making the MFMT reconstruction problem highly ill-posed and ill-conditioned
At the same time, since the number and intensity of fluorescent photons decay exponentially with the increase of the thickness of the biological sample, it becomes more difficult to solve the already fragile inverse reconstruction
In addition, high-density sampling and fine discretization make the inverse reconstruction time and computational load of mesoscopic fluorescence molecular tomography huge, and iterative reconstruction algorithms usually used are difficult to meet the needs of high-precision and real-time reconstruction at the same time

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
  • Mesoscopic fluorescence molecular tomography method and system based on bottleneck residual GAN
  • Mesoscopic fluorescence molecular tomography method and system based on bottleneck residual GAN
  • Mesoscopic fluorescence molecular tomography method and system based on bottleneck residual GAN

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029] This embodiment provides a mesoscopic fluorescence molecular tomography method based on bottleneck residual GAN;

[0030] Such as figure 1 As shown, the mesoscopic fluorescence molecular tomography method based on the bottleneck residual GAN ​​includes:

[0031] Input the acquired fluorescence intensity data on the surface of the biological sample to be imaged into the pre-trained bottleneck residual GAN; the bottleneck residual GAN ​​first performs noise reduction, sparseness and mapping processing on the input data; then, after the mapping processing The data were reconstructed to obtain data reflecting the concentration and distribution of fluorescent protein probes; based on the data reflecting the concentration and distribution of fluorescent protein probes, the results of mesoscopic fluorescence molecular tomography were obtained.

[0032] As one or more embodiments, the acquisition of the fluorescence light intensity data on the surface of the biological sample ...

Embodiment 2

[0108] This embodiment provides a mesoscopic fluorescence molecular tomography system based on bottleneck residual GAN;

[0109] Mesoscopic fluorescence molecular tomography system based on bottleneck residual GAN, including:

[0110] The imaging module is configured to: input the acquired fluorescence intensity data on the surface of the biological sample to be imaged into the pre-trained bottleneck residual GAN; the bottleneck residual GAN ​​first performs noise reduction, sparseness and mapping on the input data in sequence processing; and then, reconstructing the data after mapping processing to obtain data reflecting the concentration and distribution of fluorescent protein probes; based on the data reflecting the concentration and distribution of fluorescent protein probes, obtaining mesoscopic fluorescence molecular tomography results.

[0111] It should be noted here that the above-mentioned imaging module corresponds to the steps in the first embodiment, and the examp...

Embodiment 3

[0115] This embodiment also provides an electronic device, including: one or more processors, one or more memories, and one or more computer programs; wherein, the processor is connected to the memory, and the one or more computer programs are programmed Stored in the memory, when the electronic device is running, the processor executes one or more computer programs stored in the memory, so that the electronic device executes the method described in Embodiment 1 above.

[0116] It should be understood that in this embodiment, the processor can be a central processing unit CPU, and the processor can also be other general-purpose processors, digital signal processors DSP, application specific integrated circuits ASIC, off-the-shelf programmable gate array FPGA or other programmable logic devices , discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor, or the processor may be any conventional processor, o...

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 mesoscopic fluorescence molecular tomography method and system based on a bottleneck residual GAN. The method comprises the steps of: inputting the obtained fluorescence intensity data of the surface of a to-be-imaged biological sample into a pre-trained bottleneck residual GAN; firstly carryings out noise reduction, sparseness and mapping processing on the input data insequence by the bottleneck residual GAN; then, reconstructing the mapped data to obtain data reflecting the fluorescent protein probe concentration and distribution; and acquiring a mesoscopic fluorescence molecular tomography result based on the data reflecting the fluorescent protein probe concentration and distribution.

Description

technical field [0001] The present disclosure relates to the technical field of molecular imaging, in particular to a mesoscopic fluorescence molecular tomography method and system based on bottleneck residual GAN ​​(Generative Adversarial Networks, GAN for short). Background technique [0002] The statements in this section merely mention background art related to the present disclosure and do not necessarily constitute prior art. [0003] With the increasing maturity of molecular imaging diagnosis and treatment technology, medical diagnosis is gradually progressing from pathological characterization, routine biochemical detection to early detection, screening and diagnosis of diseases with the help of microscopic features such as molecular probes. Most optical microscopy imaging has disadvantages such as penetration limit (0.5-1mm) and diffusion limit (>1cm), which cannot meet the needs of mesoscopic high-resolution imaging. Medical imaging modalities such as X-ray, CT...

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): G01N21/64G06T3/40G06N3/04G06N3/08
CPCG01N21/6486G01N21/6456G06T3/4053G06N3/08G06N3/045
Inventor 杨福刚陈洋王玉玲杜慧弓雪张艳丽
Owner SHANDONG INST OF BUSINESS & 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