Migration learning lung lesion tissue detection system based on MaskScoring R-CNN network

A technology of transfer learning and detection system, applied in the field of lung lesion detection system, to achieve the effect of high precision and good generalization

Active Publication Date: 2019-12-20
ZHEJIANG UNIV OF TECH
View PDF2 Cites 28 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the present invention, the MaskScoring R-CNN neural network used for semantic segmentation of natural imag

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
  • Migration learning lung lesion tissue detection system based on MaskScoring R-CNN network
  • Migration learning lung lesion tissue detection system based on MaskScoring R-CNN network
  • Migration learning lung lesion tissue detection system based on MaskScoring R-CNN network

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0040] The invention will be specifically explained below in conjunction with the drawings

[0041] The migration learning lung lesion tissue detection system based on the MaskScoring R-CNN network of the present invention includes a storage module for storing four types of lung diseases: lung cancer, pneumonia, tuberculosis, and emphysema, and also includes a diagnosis module, a diagnosis module and a storage module Communication connection, the diagnostic module specifically includes:

[0042] Step 1) Medical image preprocessing;

[0043] The CT images of 4 different lung diseases: lung cancer, pneumonia, tuberculosis, and emphysema were selected, and the data were annotated by NLP method, and these data were used as positive samples. Choose normal CT images of lungs as negative samples.

[0044] Perform data enhancement processing on the collected lung medical images. Use 80% of the processed data as the training set of the network, 10% as the validation set, and finally 10% as 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

A migration learning lung lesion tissue detection system based on an MaskScoring R-CNN network comprises a storage module for storing four lung diseases including lung cancer, pneumonia, pulmonary tuberculosis and emphysema and further comprises a diagnosis module, and the diagnosis module is in communication connection with the storage module and comprises the following steps of 1) preprocessinga medical image; 2) constructing the MaskScoring R-CNN network model, wherein the step 2) specially comprises 1, constructing a shared convolutional neural network backbone (for feature extraction); 2, carrying out transfer learning on a shared convolutional neural network; 3, constructing an FPN network; 4, constructing an RPN network; 5, constructing an ROIAlign layer; 6, adding the MaskIoU head; and 3) identifying the lung medical image lesion tissue, inputting a to-be-detected lung CT image into the constructed MaskScoring R-CNN network, outputting and obtaining an identified image by thenetwork, framing out and masking the identified lesion tissues, and marking the lesion categories. According to the method, the requirement for high precision of medical image segmentation is met, andthe network can have the good generalization.

Description

technical field [0001] The invention relates to a detection system for lung lesions. [0002] technical background [0003] For nearly half a century, the incidence and mortality of lung cancer have been rising continuously, doubling in 15 years. The incidence of lung cancer in industrially developed areas is high, and the more you smoke, the higher the incidence. There is an obvious dose relationship. Both mortality and mortality rank first in malignant tumors. In order to be able to detect early and give timely treatment in the early stage of lung lesions, accurate lesion detection methods are extremely critical. [0004] Common lung diseases include lung abscess, emphysema, tuberculosis, pulmonary nodules, etc. In medicine, chest X-ray examination is one of the necessary basic examination items for lung diseases, which is helpful for the diagnosis of lung inflammation, atelectasis, emphysema, pneumothorax, pleural effusion and other diseases. Chest CT examination is hel...

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): G06T7/00G06T7/10
CPCG06T7/0012G06T7/10G06T2207/10081G06T2207/20081G06T2207/20084G06T2207/30061G06T2207/20104
Inventor 张聚俞伦端周海林吴崇坚吕金城陈坚
Owner ZHEJIANG UNIV OF 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