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

Method for automatically detecting pectoralis major muscle area in molybdenum target image

An automatic detection, pectoralis major technology, applied in the field of image processing to achieve high accuracy and ease the need for training samples

Inactive Publication Date: 2018-09-21
PERCEPTION VISION MEDICAL TECH CO LTD
View PDF0 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The reason for the above shortcomings is that they have strong usage conditions for specific types of data or specific problems.

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 for automatically detecting pectoralis major muscle area in molybdenum target image
  • Method for automatically detecting pectoralis major muscle area in molybdenum target image
  • Method for automatically detecting pectoralis major muscle area in molybdenum target image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0044] With the advent of advanced machine learning methods such as convolutional neural networks and deep learning, many are using this approach for image segmentation and classification. This method has been successfully applied in natural images, with very accurate segmentation and classification results, even more accurate than artificial results. However, in mammography images, it is quite challenging to build a robust network model based on grayscale or texture. For example, when the appearance of the breast and pec regions is very similar, it is very difficult to rectify the boundary between the two categories, and a deep convolutional neural network needs a large amount of reliable data to train to build a reliable network. Obtaining reliable data from manual detection by radiologists is difficult and time-consuming.

[0045] The present invention combines traditional methods such as traditional grayscale, gradient, texture and other features, and uses a deep convolutio...

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 for automatically detecting a pectoralis major muscle area in a molybdenum target image. The method comprises the following steps: S1, using a conventional method based on grey scale, gradient and texture characteristics to acquire a coarse segmentation image of the pectoralis major muscle area; S2, carrying out segmentation on the coarse segmentation image acquired in the step S1 through deep convolutional neural network to acquire a fine segmentation image; and S3, automatically detecting a pectoralis major muscle image of a mammary molybdenum target image based on the acquired deep convolutional neural network model. According to the method disclosed by the invention, a classic algorithm is adopted, the pectoralis major muscle area in the molybdenum target image is primarily detected; because a conventional algorithm generally only adapts to some special conditions, the method is difficultly and generally used, and therefore, the pectoralis major muscle area is primarily segmented, and refined segmentation is carried out by using the deep convolutional neural network; meanwhile, through coarse segmentation processing, a demand of a large number of training samples required in deep learning can be greatly alleviated.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an automatic detection method for the pectoralis major region in a molybdenum target image. Background technique [0002] Breast cancer is one of the leading causes of cancer death in women. Currently, the most effective method for early detection of breast cancer is mammography screening. However, at present, radiologists analyze hundreds of mammography images every day, and the task is time-consuming and labor-intensive, which leads to under-reporting and false-reporting of some cases. Computer Aided Diagnosis (CAD) system as a "second reader's opinion" has the advantages of consistency, reliability, and speed, so it is becoming more and more popular. The CAD system can provide radiologists with effective auxiliary diagnostic opinions, which can improve the accuracy of mammography image detection. [0003] In the CAD system of the breast, the automatic detection of ...

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): G06T7/00G06T7/11G06N3/04G06N3/08
CPCG06N3/08G06T7/0012G06T7/11G06T2207/30068G06T2207/10116G06N3/045
Inventor 陆遥马祥园
Owner PERCEPTION VISION MEDICAL TECH CO LTD
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com