Ultrasonic carotid artery distal recognition device and method based on convolutional neural network
A convolutional neural network and convolutional neural network technology, applied in the field of medical image processing, can solve the problems of difficult selection of velocity field parameters, algorithm boundary leakage, and high algorithm time complexity, so as to enhance network adaptability, avoid feature extraction, The effect of reducing training parameters
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0049] IMT is the main criterion for predicting cardiovascular and cerebrovascular diseases. In the past 30 years, a large number of algorithms for measuring IMT have been proposed. These algorithms are mainly aimed at ROI acquisition and carotid artery lumen-intima boundary (Lumn-Intima Interface, LII), intima-media boundary (Media-Adventitia Interface, MAI) in two parts. Accurate extraction of ROI is very important, and the present invention aims to develop a fully automatic, fast and accurate method for extracting ROI.
[0050] Convolutional Neural Network (CNN) is a specially designed multi-layer perceptron inspired by biological neurology. Neurons in the visual cortex receive information locally, meaning that these neurons only respond to stimuli in certain areas. It is generally believed that the pixels in the local space of the image are closely related, while the correlation of pixels far away is weak. Inspired by biological neurology, each neuron only needs to perc...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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