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

A boundary-aware double-attention-guided liver segment segmentation method

A kind of attention and dual technology, applied in neural learning methods, image analysis, image data processing, etc., can solve the problems of inability to adapt to multi-type data features, low efficiency, insufficient robustness, etc., and achieve liver function preservation and accuracy High, high segmentation efficiency

Pending Publication Date: 2021-09-03
BEIJING UNIV OF TECH
View PDF0 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Applying the deep network to the liver segment segmentation task can effectively solve the problems of insufficient robustness, inability to adapt to multi-type data characteristics, and low efficiency.

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
  • A boundary-aware double-attention-guided liver segment segmentation method
  • A boundary-aware double-attention-guided liver segment segmentation method
  • A boundary-aware double-attention-guided liver segment segmentation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The present invention will be described in further detail below in conjunction with specific embodiments and with reference to the accompanying drawings.

[0025] The overall structure diagram of the present invention is as figure 1 As shown, the process flow of the method is as follows figure 2 As shown, the proposed boundary-aware dual attention module as image 3 as shown, Figure 4 In order to annotate the MRI data according to the Couinaud classification method, the following steps are specifically included:

[0026] Step 1, collect abdominal MRI-enhanced portal phase scan sequences of clinical cases.

[0027] The clinically collected cases involve the MRI portal phase scan sequence of various focal liver lesions, so as to ensure that the training model can ensure high accuracy in liver segment segmentation under different lesions, and improve the robustness of the model. The collected MRI data invited experienced radiologists to divide the liver into eight pa...

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 boundary-aware double-attention-guided liver segment segmentation method, which is called a boundary-aware double-attention-guided symmetric coding and decoding network and is used for accurately judging the position of a liver tumor. According to the method, the feature learning effect of the boundary in the medical image can be enhanced, and the segmentation precision of the liver segment is improved by accurately positioning the edge position. A double attention mechanism proposed by the method is composed of a space attention module and a semantic attention module in parallel. According to the invention, the low-level feature map with rich boundary position information is weighted from two dimensions of space and channel, and is spliced with the corresponding high-level feature map in the decoding path, so that the boundary feature expression is clearer and more prominent, the positioning of the liver segment boundary is facilitated, the segmentation accuracy is improved, and the liver segment segmentation problem is effectively solved.

Description

technical field [0001] The invention belongs to the field of image segmentation in computer vision, and in particular relates to a liver segment segmentation method guided by boundary perception and double attention. Background technique [0002] A transverse section through the bifurcation of the main portal vein divides the lobes of the liver into eight segments as described in Couinaud's classification, which is widely used in liver anatomy. Segmentation of the liver into separate segments is crucial in surgical management, as the part involved in the tumor can be removed separately without damaging the rest, allowing as much liver function as possible to be preserved. Radiographic images (such as computed tomography (CT) or magnetic resonance imaging (MRI)) used together with contrast agents can clearly show anatomical structures such as hepatic veins, portal veins and their vascular branches, which are useful for delineating liver segments Therefore, accurate liver seg...

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): G06T7/12G06K9/62G06N3/04G06N3/08G06T3/40
CPCG06T7/12G06N3/08G06T3/4038G06T2207/10088G06T2207/30056G06N3/045G06F18/253
Inventor 贾熹滨钱宸杨正汉韩昕君
Owner BEIJING UNIV OF TECH
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