Unlock instant, AI-driven research and patent intelligence for your innovation.

System, method and equipment for quantitative lung disease segmentation

A disease and lung technology, applied in the field of quantitative lung disease segmentation and detection based on technology, can solve problems such as low computational efficiency and segmentation accuracy, blind spots in medical image segmentation technology, and inability to achieve clinical applications.

Inactive Publication Date: 2019-05-07
SHANGHAI UNITED IMAGING INTELLIGENT MEDICAL TECH CO LTD
View PDF7 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

On this basis, some traditional machine learning methods based on Active Shape Model (ASM) can also play a certain role in this type of medical image segmentation, but due to the low computational efficiency and segmentation accuracy, clinical applications cannot be realized.
[0005] In recent years, image segmentation models based on machine learning have been continuously proposed, but there are still blind spots in the medical image segmentation technology for diseases such as common lung diseases on X-ray chest films

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
  • System, method and equipment for quantitative lung disease segmentation
  • System, method and equipment for quantitative lung disease segmentation
  • System, method and equipment for quantitative lung disease segmentation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] Neural networks are one of the latest trends in machine learning and artificial intelligence research. Neural network methods have revolutionized computer vision and machine learning. As a branch of machine learning, neural network is an algorithm for high-level abstraction of data by using multiple processing layers consisting of complex structures or multiple nonlinear transformations.

[0017] figure 1 A block diagram of a system 100 for quantitative lung disease segmentation and detection based on neural network technology is shown according to an exemplary aspect of the present disclosure. System 100 may include processor 102 and memory 104 . The system 100 may also include an input unit 110 , a segmentation model 112 , and an output unit 114 . The system 100 may also include a preprocessing component 116 , a training module 118 , a pulmonary condition calculation module 120 . The various components described above may be coupled by, for example, bus 106 and co...

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 present disclosure relates to a system for quantifying lung condition segmentation, comprising: a lung condition segmentation model configured to perform lung condition segmentation on the chest radiography image based on a neural network; The pulmonary lobe segmentation model configured to perform pulmonary lobe segmentation on the chest radiography image based on a neural network; And a calculation component configured to calculate a pneumothorax volume based on a result of the lung condition segmentation and the lung lobe segmentation. The present disclosure also relates to corresponding methods, devices, and computer-readable media for quantifying lung condition segmentation.

Description

technical field [0001] The present disclosure relates generally to medical image processing, and more particularly to techniques based on quantitative pulmonary disease segmentation and detection. Background technique [0002] Common lung diseases include pneumothorax, pulmonary edema, etc., which can seriously endanger human health. A pneumothorax is a condition in which air enters the pleural cavity, causing air to accumulate in the lungs. Pneumothorax can generally be divided into traumatic pneumothorax, spontaneous pneumothorax and artificial pneumothorax and so on. Traumatic pneumothorax is generally caused by trauma to the chest wall or lungs, spontaneous pneumothorax is caused by lung disease causing spontaneous rupture of lung tissue, and artificial pneumothorax is the active injection of air into the pleural cavity during treatment and diagnosis. Spontaneous pneumothorax is more common in young males or those suffering from chronic bronchitis, emphysema, and tuber...

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): G06T7/10G06T7/62G06T7/00A61B6/00
Inventor 伍吉兵郑介志
Owner SHANGHAI UNITED IMAGING INTELLIGENT MEDICAL TECH CO LTD