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

A medical image enhancement method based on deep learning

A medical image and deep learning technology, which is applied in the field of medical image processing, can solve the problems that the reconstruction effect of detailed information such as edge contours of medical images is not ideal, there is no super-resolution reconstruction model, and it is unfavorable for doctors to diagnose, so that the detailed information can be clearly seen. , improve the possibility of diagnosis and cure, improve the possible effect of diagnosis and cure

Pending Publication Date: 2019-06-18
CENT SOUTH UNIV
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] (1) The existing super-resolution reconstruction model is not ideal for reconstructing detailed information such as edge contours of medical images, which is not conducive to doctor diagnosis
[0006] (2) There is a lack of medical images in the training data set of the existing model, and there is no doctor-specific super-resolution reconstruction model

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
  • A medical image enhancement method based on deep learning
  • A medical image enhancement method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] Residual network (ResNet) can solve the problem of convergence and accuracy decline while deepening the network. The super-resolution model based on the residual network can have a deeper level, which is very useful for learning from low-resolution to super-resolution. Non-linear mapping, expanding the reconstruction receptive field, and improving the quality of SR images are of great significance. Therefore, the super-resolution method based on the deep residual network can reconstruct medical images with clear details such as edges and contours. The technical scheme of the present invention is implemented in three steps: the first step is to construct a super-resolution model based on a deep residual network; the second step is to add medical image data to the super-resolution reconstruction common data set DIV2K, expand the training scale, and train the model; Three-step encapsulation of super-resolution models, combined with the needs of doctors to design a simple 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

The invention discloses a medical image enhancement method based on deep learning, and the method comprises the steps: adding medical image data to an original training data set, and constructing a simple and easy-to-use operation interface in combination with the requirements of doctors. To solve the problem that Detailed information such as an edge contour after super-resolution reconstruction of a medical image is not clear, the diagnosis of a doctor is possibly influenced, the invention provides a medical image super-resolution method based on a deep residual network. By stacking more levels under the same computing resources and using the deep residual network to learn nonlinear mapping from low-resolution images to high-resolution images, super-resolution images with clear edge contours are reconstructed, doctors are assisted to accurately diagnose illness conditions through medical images, and therefore the possibility of disease diagnosis and cure is improved.

Description

technical field [0001] The invention relates to the field of medical image processing, in particular to a medical image enhancement method based on deep learning. Background technique [0002] Medical imaging (X-ray imaging, CT imaging, magnetic resonance imaging, ultrasound imaging, and nuclear medicine imaging, etc.) allows doctors to understand the changes in the internal shape, function, and metabolism of the patient's body in addition to contact and anatomy, which is helpful for diagnosing the cause and condition of patients. important role. Medical imaging plays an extremely important role in medical clinical diagnosis, and modern medicine cannot do without medical imaging technology. At present, medical imaging data mostly rely on manual analysis. The medical imaging auxiliary diagnosis system developed by HKUST Xunfei, Tencent Miying, and Ali Health relies on high-quality and high-resolution images, which can be used in specific medical fields (pulmonary CT imaging ...

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): G06T3/40
Inventor 任盛郭克华郭海富
Owner CENT SOUTH 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