Matching Image Retrieval Method and Retrieval System of Breast Image Based on Similarity

A technology of image retrieval and similarity, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve the problems of missing tumor areas and inaccurate tumor locations, reduce capacity storage, improve retrieval efficiency, and speed up speed effect

Inactive Publication Date: 2017-01-18
XIAN HWATECH MEDICAL INFORMATION TECH
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, since the current machine learning technology and target detection technology are not mature enough, especially the "semantic gap (Semantic Gap)" problem has not been fundamentally resolved, the existing methods of applying the above-mentioned technologies for automatic detection of breast tumor areas have missed the mass area. Problems such as drop or inaccurate tumor location

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
  • Matching Image Retrieval Method and Retrieval System of Breast Image Based on Similarity
  • Matching Image Retrieval Method and Retrieval System of Breast Image Based on Similarity
  • Matching Image Retrieval Method and Retrieval System of Breast Image Based on Similarity

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0083] The image database used in this embodiment is the breast image database of a hospital in Xi'an, which contains 2560 mammograms in total.

[0084] First, extract the SIFT feature blocks of each mammogram according to step 1, and extract the HOG features of each feature block. Follow step 2 to create a search database. In this embodiment, the number of child nodes generated by each node is K=3; the threshold depth=4 for the number of layers of the hierarchical clustering tree.

[0085] Secondly, for any input breast image to be retrieved, perform retrieval according to step 3 and step 4. Figure 8 A complete retrieval process is shown. in, Figure 8 (a) is an input image to be retrieved, Figure 8(b) is all the SIFT feature blocks extracted using the SIFT algorithm in step 3, a total of 631. In this embodiment, the SIFT feature block conforming to the specified scale refers to a SIFT feature block not smaller than 32×32 pixels. Therefore, the SIFT feature block that...

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 matching image retrieval method and a retrieval system for breast images based on similarity. The matching image retrieval method for breast images based on similarity includes the following steps: establishing an image feature library; establishing a hierarchical clustering tree; extracting Features of the image to be retrieved; find images similar to the retrieved image and output. The system of the present invention includes an image feature library building module, a hierarchical clustering tree building module, a feature extraction module of images to be retrieved and a similar image search module. The method and system of the present invention can input images of mammograms to be retrieved into the retrieval database in real time, then analyze the input images, and sort and output the images in the retrieval database according to the similarity with the input images. The retrieval speed of the invention is fast and the retrieval result is accurate.

Description

technical field [0001] The invention belongs to the technical field of digital image retrieval, and in particular relates to a matching image retrieval method and retrieval system of mammary gland images based on similarity. Background technique [0002] Breast disease is a disease that seriously endangers women's health. At present, breast cancer has accounted for about 30% of new malignant diseases in women, ranking first in the incidence of female malignant tumors. Mammography (Mammography) uses a special molybdenum-palladium X-ray machine to take pictures of the breast to form a mammogram. At present, using mammography as the basic data for breast disease research has become the most common method in developed countries. . There are four common forms of lesions in breast cancer X-ray films: regular or quasi-circular masses, irregular or fuzzy masses, burr masses, and lucent ring masses. The target detection technology in the field of computer vision and the machine lea...

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 Patents(China)
IPC IPC(8): G06F17/30G06K9/64
CPCG06F16/5838G06F18/231
Inventor 张浪辛良申田李云峰张孝林
Owner XIAN HWATECH MEDICAL INFORMATION TECH
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