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

Breast lump benign and malignant judgment method and equipment

A breast and tumor technology, applied in the field of image processing, can solve the problems of not using the characteristics of breast tumors, complex processing process, and low discrimination accuracy, and achieve the effect of improving discrimination accuracy and detection efficiency

Pending Publication Date: 2020-04-24
HARBIN INST OF TECH SHENZHEN GRADUATE SCHOOL
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, most of the methods for distinguishing benign from malignant breast masses are to directly extract low-level features such as texture and geometry of breast masses from breast masses, or use deep neural networks to extract benign and malignant abstract semantic features of breast masses. , the processing process is complex, and the accuracy of discrimination is not high, and the characteristics of breast masses are not used. Therefore, it is necessary to propose a method for judging benign and malignant breast masses by using the characteristics of breast masses.

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
  • Breast lump benign and malignant judgment method and equipment
  • Breast lump benign and malignant judgment method and equipment
  • Breast lump benign and malignant judgment method and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] Embodiment 1 of the present invention provides a method for preprocessing mammography images, figure 1 A flow chart of the implementation of a mammography image preprocessing method provided in this embodiment, as shown in figure 1 As shown, the method includes the following steps:

[0048] S11: acquiring a mammography image;

[0049] S12: Preprocessing the mammography images. In this embodiment, the preprocessing includes: denoising, increasing contrast, rough contour segmentation, contour refinement, extracting breast images, and adjusting the size of breast images, specifically as follows:

[0050]1) The denoising process is as follows: firstly, the median filter is used for preliminary denoising, and then the result of the preliminary denoising is denoised again using the wavelet threshold method to obtain the breast image.

[0051] For example, a 3X3 median filter is optional, the wavelet threshold method uses haar wavelet, and the level of wavelet decomposition ...

Embodiment 2

[0069] This embodiment provides a breast mass target detection and positioning method, such as image 3 As shown, it is a flow chart of the implementation of the breast mass target detection and positioning method in this embodiment, including:

[0070] S21: Acquire a mammographic image, and perform preprocessing using a preprocessing method for a mammographic image as in Embodiment 1, to obtain a mammographic image to be detected;

[0071] S22: Input the mammography image to be detected into the target detection and positioning network for target detection and positioning to obtain the position of the mammary gland mass.

[0072] This embodiment uses the YOLOv3 target detection framework to realize the positioning and detection of breast masses. YOLOv3 innovates on the basis of v1 and v2. On the premise of maintaining the speed advantage, the prediction accuracy is improved, especially the recognition of small objects is strengthened. ability. Since YOLOv3 has the character...

Embodiment 3

[0079] According to the observation of breast lumps from the perspective of clinical medicine, benign breast lumps are mostly characterized by regular shapes and clear edges, while malignant breast lumps are mostly characterized by irregular shapes and blurred borders. Therefore, it can be combined with the characteristics of breast lumps The characteristics are judged as benign or malignant. This embodiment provides a method for judging benign and malignant breast masses.

[0080] like Figure 5 As shown, it is a flow chart of realizing the method for judging benign and malignant breast lumps in this embodiment, including:

[0081] S31: Obtain a mammography mass image obtained through a method for detecting and locating a breast mass target as described in any one of Embodiment 2;

[0082] S32: Input the mammography mass image into the target classification network, perform shape prediction and edge prediction, and simultaneously obtain the classification result of the corr...

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 breast lump benign and malignant judgment method and equipment. The method and the equipment relate to an image processing field, the method comprises the following steps: acquiring a mammography image; and pre-treating it, obtaining a mammography image to be detected; inputting the mammary gland X-ray photographic image to be detected into a target detection positioningnetwork for target detection positioning to obtain a mammary gland lump position, inputting the detected mammary gland X-ray photographic image of the mammary gland lump into a target classification network for shape prediction and edge prediction, and meanwhile obtaining a classification result of the corresponding breast cancer lump. The method is based on semantic description features corresponding to characterization features of breast lumps. Through the target classification network, benign and malignant judgment on the breast lumps in mammography is realized, and weighted fusion is performed on the probability scores of the attributes according to the target classification network to obtain a final breast lump benign and malignant judgment result, so that the judgment accuracy and the detection efficiency are improved.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a method and equipment for judging benign and malignant breast masses. Background technique [0002] Mammography image is an image data analysis of the whole breast and is widely used as a tool for early detection of breast cancer. It has the advantages of low cost, less waste rate and high detection rate. Mammography mainly reflects the density of breast tissue through the degree of absorption of X-rays by human tissue, and then the doctor observes the imaging of mammography to observe the presence of lesions in the breast. Breast lumps are a common symptom of breast disease and the main manifestation of breast cancer. Therefore, automatic and accurate discrimination of benign and malignant breast masses is one of the methods to effectively control and treat breast cancer. [0003] At present, most of the methods for distinguishing benign and malignant breast masses are to dire...

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): G06T7/00G06T7/13G06T7/187G06K9/62G06N3/04G06N3/08
CPCG06T7/0012G06T7/13G06T7/187G06N3/082G06T2207/10116G06T2207/30068G06T2207/30096G06N3/045G06F18/2415G06F18/253
Inventor 王俊茜徐勇
Owner HARBIN INST OF TECH SHENZHEN GRADUATE SCHOOL
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