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

Head and neck tumor distal metastasis prediction method based on machine learning

A head and neck tumor and metastasis prediction technology, applied in the field of deep learning, can solve the problem of insufficient imaging data of head and neck cancer, and achieve the effect of avoiding pain

Inactive Publication Date: 2021-07-16
NANFANG HOSPITAL OF SOUTHERN MEDICAL UNIV
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Deep learning has achieved remarkable results in natural image classification. There are also studies on applying deep learning to medical image processing and diagnosis, but there are few imaging data of head and neck cancer.

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
  • Head and neck tumor distal metastasis prediction method based on machine learning
  • Head and neck tumor distal metastasis prediction method based on machine learning
  • Head and neck tumor distal metastasis prediction method based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] In order to have a clearer understanding of the technical features, purposes and effects of the present invention, the specific implementation manners of the present invention will now be described in detail with reference to the accompanying drawings.

[0031] Such as figure 1 As shown, the present invention provides a method for predicting distant metastasis of head and neck tumors based on machine learning, including:

[0032] Obtain head and neck CT image data of head and neck tumor patients with distant metastasis, perform image preprocessing, and divide training set and test set;

[0033] Add the LRN layer after resampling the third layer of the convolutional neural network, use the Dropout layer after the sixth layer of the fully connected layer, construct an improved convolutional neural network model, and use the head and neck tumors with distant metastasis as the training set The patient's head and neck CT image data is input into the improved convolutional n...

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 relates to a head and neck tumor distal metastasis prediction method based on machine learning, and the method comprises the steps: building an improved convolutional neural network, training a built network model through the head and neck CT image data of a head and neck tumor patient with distal metastasis, and predicting the distal metastasis of the head and neck tumor after the training; and inputting a head and neck CT image of a head and neck tumor patient, which is shot in real time, into the network model, and outputting a result as far-end metastasis prediction of the head and neck CT image of the head and neck tumor patient. A radiomics method is adopted to replace a biopsy method to predict far-end metastasis of head and neck cancers, the pain that a head and neck patient suffers from multiple times of biopsy is avoided, a deep learning method is adopted to supplement a feature extraction algorithm of original radiomics, and the problem that the number of head and neck medical images is small is solved.

Description

technical field [0001] The present invention relates to the technical field of deep learning, and more specifically, relates to a machine learning-based method for predicting distal metastasis of head and neck tumors, computer equipment and storage media. Background technique [0002] Malignant tumors of the head and neck account for about 5% of malignant tumors in the whole body. Due to the complex anatomical structure and other reasons, although surgery is the main method of treatment, the rate of radical resection is low, and the early clinical symptoms are hidden. In the middle and advanced stages, it has always been a difficult point in tumor treatment. The diagnosis of malignant tumors of the head and neck usually requires a combination of medical history, signs, endoscopic biopsy and related imaging examinations. Imaging examinations are helpful for tumor detection, staging, and evaluation of treatment prognosis. Predicting whether the tumor has metastasized has impo...

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): G06K9/62G06K9/54G06N3/04G06N3/08G06T7/00
CPCG06T7/0012G06N3/08G06T2207/10081G06T2207/20081G06T2207/20084G06T2207/30096G06V10/20G06V2201/032G06N3/045G06F18/241
Inventor 文戈黄伟康张海捷夏琼段刚刘民英涂茜
Owner NANFANG HOSPITAL OF SOUTHERN MEDICAL 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