OCT image quality evaluation method based on improved Resnet and SVR hybrid model

An image quality evaluation and hybrid model technology, applied in the field of medical image processing, can solve the problem of insufficient OCT image accuracy, and achieve the effect of avoiding information loss and small amount of data

Active Publication Date: 2019-02-05
NORTHWEST UNIV +1
View PDF8 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0019] In view of the deficiencies in the prior art, the purpose of the present invention is to provide an OCT image quality evaluation method based o

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
  • OCT image quality evaluation method based on improved Resnet and SVR hybrid model
  • OCT image quality evaluation method based on improved Resnet and SVR hybrid model
  • OCT image quality evaluation method based on improved Resnet and SVR hybrid model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0072] The present embodiment provides a kind of OCT image quality assessment method based on improved Resnet and SVR mixed model, comprises the following steps:

[0073] Step 1, preprocessing the original OCT image to obtain a preprocessed OCT image;

[0074] Since the original OCT image is different from the image finally displayed on the screen for the doctor to view, it needs to undergo gamma correction processing, and this embodiment evaluates the subjective perception quality of the OCT image, so it is necessary to perform gamma correction on the original OCT image ; On the other hand, due to the particularity of medical imaging, the data set used for training is small, which may lead to overfitting of the network. First, it is necessary to divide the corrected OCT image into blocks, so that the original OCT image The image becomes n OCT images, and n is the number of local OCT image blocks after block, which can make the effect of network training better. Therefore, th...

Embodiment 2

[0111] The difference between this embodiment and embodiment 1 is that in step 3, the deep-level features of the extracted preprocessed OCT image are used to train the OCT image quality evaluation model;

[0112] Given an OCT image to be evaluated, use the OCT image quality evaluation model to obtain the quality score of the OCT image to be evaluated;

[0113] Can also be:

[0114] Step 3.1, use the feature extraction network to extract the deep-level image features of each local OCT image block, and obtain the deep-level features of the OCT image through feature fusion;

[0115] In this embodiment, the last fully connected layer of the trained deep residual network is removed, and the remaining structure is used to extract deep image features of the input OCT image. The specific steps are as follows:

[0116] Step 3.1.1, remove the last fully connected layer of the deep residual network, at this time, the network input is the local OCT image block of m*m, and the output is t...

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 provides an OCT image quality evaluation method based on an improved Resnet and SVR mixed model, comprising the following steps: step 1, pre-processing the original OCT image to obtain the pre-processed OCT image; step 2, construct and training a depth residual network, and adopt that trained depth residual network to extract the deep-level features of the pre-processed OCT image; 3, train an OCT image quality evaluation model by utilizing that deep-level characteristic of the extracted preprocessed OCT image; Given an OCT image to be evaluated, the quality fraction of the OCT image to be evaluated is obtained by using the OCT image quality evaluation model. The invention combines the depth residual network with the quality evaluation task of the OCT image, and establishes anew objective prediction model of the subjective perceived quality of the OCT image.

Description

technical field [0001] The invention belongs to the field of medical image processing, and relates to a method for evaluating the quality of fundus OCT images, in particular to a method for evaluating the quality of OCT images based on an improved Resnet and SVR hybrid model. Background technique [0002] The fundus is the innermost tissue of the eyeball, and fundus disease refers to lesions that occur in the fundus. For fundus diseases, if not treated in time, the long-term delay will reduce the visual functions, and blindness may be caused when the eyeball tissues are irreversibly damaged. Image acquisition is the basis of clinical work in ophthalmology, especially in fundus diseases. Optical coherence tomography (OCT) technology, as an ophthalmic imaging method, has the characteristics of non-contact, high resolution and fast imaging, which determine the important position of this technology in the field of ophthalmology. On the one hand, OCT equipment will generate spe...

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): G06T7/00G06K9/62
CPCG06T7/0012G06T2207/30041G06T2207/30168G06T2207/20084G06T2207/20081G06T2207/10101G06F18/2135
Inventor 张敏王佳阳张蕾冯筠吕毅
Owner NORTHWEST UNIV
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap