Breast lump image segmentation method and system based on pruning U-Net + +

An image segmentation and breast technology, applied in the field of breast mass image segmentation based on pruning U-Net++, can solve the problems of inability to efficiently and accurately segment breast ultrasound images, improve generalization ability, improve segmentation effect, and reduce complexity Effect

Pending Publication Date: 2022-05-31
HEFEI UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the deficiencies of the prior art, the present invention provides a breast mass image segmentation method and system based on pruning U-N...

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 image segmentation method and system based on pruning U-Net + +
  • Breast lump image segmentation method and system based on pruning U-Net + +
  • Breast lump image segmentation method and system based on pruning U-Net + +

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] First, see figure 1 , the present invention at first proposes a kind of breast lump image segmentation method based on pruning U-Net++, and this method comprises:

[0058] S1. Acquiring an original breast ultrasound image and performing preprocessing on the original breast ultrasound image;

[0059] S2. Construct a pruned U-Net++ breast ultrasound image segmentation model based on the U-Net++ network; the pruned U-Net++ breast ultrasound image segmentation model includes: fusing the feature expressions of each branch U-Net through skip connections, and introducing residuals at the same time The connection replaces the dense connection in the U-Net++ network;

[0060] S3. Segment the original breast ultrasound image based on the pruned U-Net++ breast ultrasound image segmentation model.

[0061] It can be seen that the breast mass image segmentation method and system based on pruning U-Net++ in this embodiment is based on the U-Net++ network, uses skip connections to f...

Embodiment 2

[0112] Second aspect, the present invention also provides a kind of breast mass image segmentation system based on pruning U-Net++, and this system comprises:

[0113] An image acquisition and processing module, configured to acquire an original breast ultrasound image and preprocess the original breast ultrasound image;

[0114] Model construction module, for building pruning U-Net++ mammary gland ultrasound image segmentation model based on U-Net++ network; Described pruning U-Net++ mammary gland ultrasound image segmentation model includes: fusion of the feature expression of each branch U-Net by skip connection, At the same time, the residual connection is introduced to replace the dense connection in the U-Net++ network;

[0115] An image segmentation module, configured to segment the original breast ultrasound image based on the pruned U-Net++ breast ultrasound image segmentation model.

[0116] Optionally, the preprocessing of the original breast ultrasound image by th...

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 provides a breast lump image segmentation method and system based on pruning U-Net + +, and relates to the technical field of ultrasonic image segmentation. The constructed pruning U-Net + + breast lump image segmentation model is based on a U-Net + + network, feature expressions of all branch U-Net are fused through jump connection, residual connection is introduced to replace dense connection in the U-Net + + method, and an obtained original breast ultrasound image is segmented through the model. According to the constructed pruning U-Net + + breast ultrasound image segmentation model, when the lumps in the breast ultrasound image are segmented, the model overfitting problem caused by the small data set problem of medical image data can be avoided, and the generalization ability of the ultrasound image breast lump segmentation model is improved; meanwhile, the scale of the model parameters is far smaller than that of the prior art, the complexity of the network model is reduced, the calculation time of network training can be shortened, the memory occupation of network training is reduced, and the model training efficiency is improved.

Description

technical field [0001] The invention relates to the technical field of ultrasonic image segmentation, in particular to a method and system for segmenting breast mass images based on pruned U-Net++. Background technique [0002] Breast B-ultrasound examination is one of the most common ways to detect and classify breast abnormalities. Doctors give diagnostic opinions and classify breast diseases according to the patient's physical signs and the characteristics of breast masses in ultrasound images. However, limited by the doctor's diagnostic experience and energy, the identification of breast masses in ultrasound images has problems such as time-consuming and low accuracy. With the rapid development of computer technology, computer-aided diagnosis technology is gradually involved in the medical diagnosis process. How to efficiently and accurately identify and segment tumors in complex breast ultrasound images is an urgent problem to be solved. [0003] At present, methods fo...

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): G06T7/11G06T3/00G06V10/80G06V10/764G06V10/82G06V10/25G06K9/62G06N3/04G06N3/08A61B8/08
CPCG06T7/11G06T3/0012G06N3/082G06N3/084A61B8/0825A61B8/5215G06T2207/20081G06T2207/20084G06T2207/20132G06N3/045G06F18/241G06F18/253
Inventor 付超吕晗笑王冬越常文军
Owner HEFEI UNIV OF TECH
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