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

Method for establishing medical image atlas based on image segmentation and convolutional neural network (CNN)

A convolutional neural network and medical imaging technology, applied in the field of image recognition and knowledge graphs, can solve problems such as difficult classification, insufficient granularity of image recognition, inability to mine and utilize image data, etc., and achieve high accuracy and recall Effect

Active Publication Date: 2018-08-10
XI AN JIAOTONG UNIV
View PDF6 Cites 43 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Most of the existing medical knowledge graphs are constructed based on text-based unstructured cases and documents, rather than based on medical images, and image data cannot be mined and utilized
[0004] In addition, the commonly used image segmentation technology usually has problems such as difficult classification, poor correlation and contrast, and insufficient granularity of image recognition, so it is not suitable for medical image processing.

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
  • Method for establishing medical image atlas based on image segmentation and convolutional neural network (CNN)
  • Method for establishing medical image atlas based on image segmentation and convolutional neural network (CNN)
  • Method for establishing medical image atlas based on image segmentation and convolutional neural network (CNN)

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0094] Construct image medical knowledge map to realize image-based in-depth search.

[0095] The understanding of images in existing search depends on the surrounding text, and neither extracts the knowledge contained in the images nor organizes similar knowledge, thus limiting the ability to provide information; at the same time, the search results contain more ambiguity, which cannot reflect Dependencies among knowledge. The present invention uses a convolutional neural network to process images, extracts image features, compares them with entities in the constructed knowledge map, and returns a network structure centered on this entity, including disease names, signs, complications, images, etc. Features and other content, understand the search intent semantically, avoid ambiguity, improve search accuracy and the ability to provide information.

Embodiment 2

[0097] Construct imaging medical knowledge map to realize auxiliary diagnosis and treatment based on image processing.

[0098] The medical atlas adopts a hierarchical and structured way to reflect the relationship between various medical entities, comprehensively reflects image and document information, and provides auxiliary basis for differential diagnosis. In medicine, the same sign corresponds to multiple typical diseases, and the same disease has multiple imaging manifestations. This diversity brings challenges to diagnosis. The invention extracts typical features of images corresponding to diseases through image segmentation and recognition, and ensures the accuracy of features on the basis of a large amount of training data. Through similarity comparison, the corresponding entity can be quickly determined, so as to give suggestions for disease diagnosis. At the same time, the knowledge map comprehensively reflects the relationship between diseases and symptoms, and di...

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 method for establishing a medical image atlas based on image segmentation and the CNN. A CNN method is used to segment medical images finely, image segmentation identification is carried out on the collected medical images, medical knowledge unit segmentation is carried out on medical diagnosis knowledge, and knowledge units of different medical images are formed; an image relation of image segmentation is analyzed to connect the different image knowledge units and communicate with an additional medical illness knowledge unit, a knowledge base association relation isestablished on the basis of connection between medical image identification and medical diagnosis knowledge; characteristic matching is carried out on the knowledge units after image segmentation, entities with the same type of attribute serves as entity nodes in the knowledge atlas, a knowledge base entity is established by fusion, and entities are aligned; and a knowledge atlas is established byusing the entities and the associations therebetween. Suspected diagnosis prompt and treatment suggestion are provided, and AI diagnosis is made possible.

Description

technical field [0001] The invention belongs to the technical field of image recognition and knowledge atlas, and in particular relates to a method for constructing a medical image atlas based on image segmentation and convolutional neural network. Background technique [0002] As a method of deep retrieval and mining, knowledge graph is widely used in the accurate acquisition of big data information. In recent years, the exploration of AI diagnosis and treatment based on knowledge maps in the medical field has achieved certain research results, such as a method for building Chinese medical knowledge maps based on deep learning. However, at present, there is no mature precedent for the construction of medical imaging knowledge maps in China, and the cross-comparison between medical images and corresponding medical text records is still in the blank stage. Therefore, there is a need for a knowledge map construction method that is suitable for the extraction of medical image ...

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): G16H30/40G16H50/20G16H50/70G06T7/11
CPCG06T2207/10116G06T2207/20081G06T2207/20084G06T7/11G16H30/40G16H50/20G16H50/70
Inventor 刘宏杰徐宏喆闫雨李文杨刚王婵
Owner XI AN JIAOTONG 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