Non-small cell lung cancer subtype classification system based on multi-view deep learning

A non-small cell lung cancer and deep learning technology, applied in the field of non-small cell lung cancer subtype classification system, can solve problems such as difficulty in describing the whole picture of tumors, patient treatment delays, accuracy doubts, etc., to improve model learning efficiency and classification accuracy The effect of improving the rate, improving generalization ability, and high model classification accuracy

Pending Publication Date: 2021-12-28
北京志沅医疗科技有限公司
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Pathological diagnosis is currently the gold standard for subtype classification of non-small cell lung cancer clinically, however, it requires invasive biopsy or pathological tissue section, which often brings severe pain to patients
In the actual sampling operation, due to the spatiotemporal heterogeneity of lung canc

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
  • Non-small cell lung cancer subtype classification system based on multi-view deep learning
  • Non-small cell lung cancer subtype classification system based on multi-view deep learning
  • Non-small cell lung cancer subtype classification system based on multi-view deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0061] First, for each CT image, the data containing only the lung field is obtained through preprocessing methods such as rough segmentation and edge cleaning, in preparation for saving multi-view data later.

[0062] The data used comes from the Cancer Imaging Archives (NCI-TCIA) under the National Cancer Institute of the United States. For each lung CT image, the data containing only the lung field is obtained. The specific method is: based on the scanning slice thickness of different CT machines, approximate Interpolation is performed using a point sampling method, which interpolates a matrix by copying adjacent pixels. Through this method, each voxel is normalized to 1mm×1mm×1mm, which ensures that the original size of the lesion is restored and facilitates the training of the multi-view model.

[0063] Based on the pixel value of CT data, normalize each piece of data with a window width of 2000 and a window level of 0 (unit: Hu), and use -400 as the threshold to perform ...

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 non-small cell lung cancer subtype classification system based on multi-view deep learning, which realizes classification of lung adenocarcinoma and lung squamous carcinoma based on a CT image, generates and displays image data of an examined part based on volume data generated by performing lung CT on an examined body, and obtains non-small cell lung cancer subtype classification result of the examined body. The non-small cell lung cancer pathological subtype classification system comprises an information acquisition module, a network module and a training module. According to the system, automatic lung field segmentation can be realized, interlayer information and three-dimensional information carried by a CT image are fully utilized by a multi-view model, an obtained classification model can be used as a tool for assisting a doctor through automatic feature extraction and classification training, and the system has the characteristics of high automation and high practicability.

Description

technical field [0001] The invention belongs to the field of artificial intelligence deep learning and biological information technology, and in particular relates to a non-small cell lung cancer subtype classification system based on multi-view deep learning. Background technique [0002] Worldwide, the incidence of lung cancer accounts for 11.6% of new tumors, and its mortality rate accounts for 18.4% of all malignant tumor deaths. a great threat. Among lung cancers, non-small cell lung cancer accounts for 85-90%. [0003] According to the World Health Organization's 2015 standards, non-small cell lung cancer can be further divided into adenocarcinoma (ADC), squamous cell carcinoma (Squamous Cell Carcinoma, SCC), large cell carcinoma (LargeCell Carcinoma, LCC), and unspecified (Not Otherwise Specified, NOS). Among them, the incidence of lung adenocarcinoma is increasing year by year, which is the most common subtype of NSCLC, accounting for almost 60% of NSCLC, and the ...

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): G06K9/62G06N3/04G06N3/08G06T7/10
CPCG06T7/10G06N3/08G06T2207/10081G06T2207/30096G06T2207/30061G06N3/045G06F18/241
Inventor 张光磊宋凡田哲源范广达
Owner 北京志沅医疗科技有限公司
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