Check patentability & draft patents in minutes with Patsnap Eureka AI!

Method and device for automatically identifying liver cancer ultrasound image based on convolutional neural network

A convolutional neural network and automatic recognition technology, applied in the field of artificial intelligence, achieves fast training speed, small memory occupation, accurate and rich recognition

Pending Publication Date: 2021-05-28
北京小白世纪网络科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a method and device for automatic recognition of liver cancer ultrasound images based on convolutional neural network, aiming at solving the problem of automatic recognition of liver cancer ultrasound images, reducing the workload of doctors, and improving accuracy.

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
  • Method and device for automatically identifying liver cancer ultrasound image based on convolutional neural network
  • Method and device for automatically identifying liver cancer ultrasound image based on convolutional neural network
  • Method and device for automatically identifying liver cancer ultrasound image based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0061]According to an embodiment of the present invention, an apparatus for automatically identifying an ultrasonic image based on a convolutional neural network is provided.image 3 It is a schematic structural diagram of the apparatus of the embodiment of the present invention, such asimage 3 As shown, including,

[0062]Generating module 30 for generating a multi-scale liver ultrasound image.

[0063]Data enhancement module 32, for data enhancement for generated multi-scale liver ultrasound images, characterized in that different ways of data enhancement modules include: increasing Gaussian noise, random shear, flip, rotation, and / or color jitter.

[0064]The extraction module 34, the liver ultrasound image after data is enhanced, by convolutional neural network extraction, specifically, extracting the module using the RESNET network, the RESNET network removes the last pool in the four pool of the resnet The spatial structure of the sequence image multi-scale image is retained;

[0065]Fus...

Embodiment 2

[0068]Embodiments of the present invention provide a multi-modal automatic identification device based on breast cancer molecular softer ultrasound image, such asFigure 4As shown, including: memory 40, processor 42, and computer programs stored on said memory 40 and can operate on said processor 42, the computer program is performed by said processor 42 to perform as follows:

[0069]S1, generate multi-scale liver ultrasound images;

[0070]S2, data enhancement of the generated multi-scale liver ultrasound image;

[0071]S3, the liver ultrasound image after data is enhanced by convolutional neural network is extracted by multi-scale image characteristics;

[0072]S4, the resulting multi-scale image feature is fused to obtain an automatic identification result of the ultrasound image of liver cancer.

[0073]S1 specifically includes,

[0074]S11, generate liver ultrasound original image;

[0075]S12, scales the generated liver ultrasound to zoom different scales and generate multi-scale liver ultrasound ...

Embodiment 3

[0085]The embodiment of the present invention provides a computer readable storage medium that stores an implementation program for information transmission on the computer readable storage medium, which is implemented when executed by processor 42. Not described herein.

[0086]The computer readable storage medium of this embodiment includes, but is not limited to: ROM, RAM, a disk, or an optical disk or the like.

[0087]Obviously, those skilled in the art will appreciate that the modules or each step of the present invention can be implemented with a general-purpose computing device, which can be concentrated on a single computing device or distributed in a network composed of multiple computing devices. On, optionally, they can be implemented with program code executable by the computing device, thereby being stored in the storage device by a computing device, and in some cases, in order of different from this The steps shown or described are performed, or they are fabricated into ind...

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 method and a device for automatically recognizing a liver cancer ultrasound image based on a convolutional neural network, and the method comprises the steps: generating a multi-scale liver ultrasound image, carrying out data enhancement of the generated multi-scale liver ultrasound image, carrying out extraction of multi-scale image features of the data-enhanced liver ultrasound image, and carrying out convolution fusion on the obtained multi-scale image features. The invention has the advantages of being accurate and rich in recognition, high in training speed and small in memory occupation.

Description

Technical field[0001]The present invention relates to the field of artificial intelligence, and in particular, there is an automatic identification method and apparatus for automatic identification of liver cancer based on convolutional neural network.Background technique[0002]Liver cancer is a harmful disease, and the 5-year survival rate is less than 30%. The treatment strategy of liver cancer is very limited, and the method of research related treatment predicts is also very difficult. In order to understand the heterogeneity of hepatoma between patients, a large amount of work has been carried out to determine the liver cancer molecular subtype. A variety of subtypes have been identified, ranging from 2 to 6, based on various histological data types, drive assumptions, and calculation methods. In addition to the most commonly used mRNA gene expression data, a recent study combines copy number variation (CNV), DNA methylation, mRNA and miRNA expression to identify 5 HCC molecules...

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): G06K9/46G06K9/54G06N3/04G06N3/08
CPCG06N3/04G06N3/08G06V10/464G06V10/20
Inventor 杜强黄丹郭雨晨聂方兴唐超张兴
Owner 北京小白世纪网络科技有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com