Pneumothorax auxiliary diagnosis method based on deep learning

An auxiliary diagnosis and deep learning technology, applied in the field of artificial intelligence, can solve problems such as insufficient use, achieve good classification effect, good classification performance, and improve network performance

Inactive Publication Date: 2019-05-10
HANGZHOU DIANZI UNIV
View PDF7 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The latest research results show that the AUC in pneumothorax is 0.8887, which is not enough for clinical use

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
  • Pneumothorax auxiliary diagnosis method based on deep learning
  • Pneumothorax auxiliary diagnosis method based on deep learning
  • Pneumothorax auxiliary diagnosis method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The present invention will be further described below in conjunction with the drawings and specific embodiments.

[0041] The hardware environment used for implementation is: Intel i7 CPU computer, GPU is K80, running environment is python2.7 and Ubuntu 14.04.

[0042] Such as figure 1 As shown, the specific steps are as follows:

[0043] a) Data set acquisition. The original data was collected from the Second Affiliated Hospital of Zhejiang University School of Medicine. It is mainly exported from the hospital database through keyword search, the data format is the original dicom, a total of more than 36,000. Data is obtained through keyword search, and data without pneumothorax in negative sample data can be derived. However, pneumothorax may be mixed with non-pneumothorax data. For example, the search keyword "pneumothorax" may search for other fields. For example, the following words may appear in the pathology report: pneumothorax, non-pneumothorax, suspected pneumotho...

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 pneumothorax X-ray chest radiography auxiliary diagnosis method based on deep learning, and the method comprises the steps: firstly converting an image format, then trainingtwo small networks to complete a data set cleaning task, and carrying out the real-time amplification of a data set of an X-ray chest radiography through random histogram equalization; carrying out up-sampling on the amplified data set, and then training by using the up-sampled data; and finally, visualizing the network trained by adopting the method, and analyzing a visualization result. According to the method, deep learning and X-ray chest radiography recognition are combined, the pneumothorax diagnosis accuracy is improved, and the workload of doctors is reduced.

Description

Technical field [0001] The invention relates to the field of artificial intelligence, and relates to a pneumothorax auxiliary diagnosis method based on deep learning. Background technique [0002] Pneumothorax refers to the pathophysiological condition caused by the rupture of the visceral pleura without trauma or human factors, and the gas enters the pleural cavity to cause pneumothorax. Those with no obvious lung disease and the formation of subpleural emphysema bubble rupture are called idiopathic pneumothorax; Patients secondary to chronic obstructive pulmonary emphysema, tuberculosis, pleura and lung diseases are called secondary pneumothorax. According to pathophysiological changes, they are divided into closed (simple), open (communication) and tension (hypertension) Three categories. According to whether there is a primary disease, spontaneous pneumothorax can be divided into two types: primary and secondary pneumothorax. [0003] X-ray findings are the first choice for t...

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 Applications(China)
IPC IPC(8): G16H50/20G06K9/62G06N3/08
Inventor 王亚奇杨龙召孙玲玲
Owner HANGZHOU DIANZI 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