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

Image enhancement method and device for diabetic renal lesion classification

A kidney lesion and image enhancement technology, applied in the field of medical image processing, can solve problems such as low quality of CT images and limit the classification accuracy of image classification models, and achieve the effects of improving image quality, feature extraction and fusion, and improving efficiency

Pending Publication Date: 2022-02-11
成都市第二人民医院
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the limitations of equipment performance and medical costs, the quality of the actual CT images obtained is generally low, which limits the accuracy of the image classification 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
  • Image enhancement method and device for diabetic renal lesion classification
  • Image enhancement method and device for diabetic renal lesion classification
  • Image enhancement method and device for diabetic renal lesion classification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] The super-resolution reconstruction network architecture and the structure of each module in the present invention are as follows Figure 1-Figure 6 As shown, the MDC feature extraction unit 2 is set to eight, the preliminary feature extraction unit 1 is a 3*3 convolutional layer, and the second image 6 input to the super-resolution network is a three-channel image. After the preliminary feature extraction unit 1, Obtain the first feature map with a channel number of 48. Inside the MDC feature extraction unit 2, the number of G1, G2, and G3 feature map channels extracted by the three branches is 48. After G1 and G2 undergo element summation, 1*1 convolution, and ReLU activation function, they are combined with G2, G2, and G3. G3 splicing to obtain the G4 feature map with 144 channels.

[0051] Inside the enhanced channel attention module 22, such as Figure 4 As shown, the four branches are in a parallel relationship, and the four branches all receive the G4 feature m...

Embodiment 2

[0057] As a comparative experiment, in the case that the relevant factors such as the control data set and the loss function are exactly the same, only the enhanced channel attention module 22, the modulation module 4 and its connection structure of the super-resolution reconstruction network provided by the present invention in Example 1 are used modified as Figure 7 Shown as Comparative Example I. In Comparative Example I, the four branches modulated the feature map G4 and spliced ​​at the same time. The enhanced channel attention module 22, modulation module 4 and its connection structure of the super-resolution reconstruction network provided by the present invention in embodiment 1 are modified as follows Figure 8 Shown as Comparative Example II. In Comparative Example II, the third branch 25 in the enhanced channel attention module 22 is removed.

[0058] Using exactly the same data set as in Example 1, after the training of Comparative Example I and Comparative Exa...

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 image enhancement method for diabetic renal lesion classification and electronic equipment, the enhancement method comprises the steps of contrast enhancement, denoising, super-resolution reconstruction and the like, and the accuracy of an image classification network on diabetic renal lesion classification is improved by improving the quality of a kidney CT image. The super-resolution reconstruction network comprises a preliminary feature extraction unit, an MDC feature extraction unit and an up-sampling unit; the MDC feature extraction unit is arranged at the downstream end of the preliminary feature extraction unit; the plurality of MDC feature extraction units are sequentially connected end to end; and the up-sampling unit is arranged at the downstream end of the MDC feature extraction unit and is used for carrying out super-resolution reconstruction on the second feature map. According to the invention, the super-division network is used for repeatedly utilizing the features, the situation that low-layer feature information gradually disappears in continuous nonlinear operation is effectively avoided, and the model obtains good balance between the feature extraction effect and the complexity.

Description

technical field [0001] The invention belongs to the technical field of medical image processing, and in particular relates to an image enhancement method and equipment for classifying diabetic nephropathy. Background technique [0002] Diabetic nephropathy is a common complication of diabetes and one of the leading causes of death due to diabetes. Patients typically present with anorexia, weight loss, weakness, proteinuria, and hypertension. The traditional diagnostic method relies on doctors to judge the stage of diabetic nephropathy by visually observing the pathological images of the kidneys, and then formulate targeted treatment plans. However, the diagnosis of the disease depends heavily on the actual clinical experience of the doctor, and the workload is heavy, especially for some key hospitals, where there are many patients and the medical burden is heavy. [0003] Using image classification network to classify kidney CT images to assist in the diagnosis of diabetic...

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): G06T5/00G06T3/40G06N3/08G06N3/04G06K9/62
CPCG06T3/4053G06T3/4046G06T3/4038G06N3/08G06T2207/20081G06T2207/20084G06T2207/30084G06T2200/32G06N3/048G06N3/045G06F18/253G06T5/90G06T5/70Y02A90/10
Inventor 黄昶荃李永红李江玥孙玉彬
Owner 成都市第二人民医院
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