Cirrhotic portal hypertension non-invasive evaluation method based on 3D multi-channel convolutional neural network
A technology of convolutional neural network and portal hypertension, which is applied in the fields of radiological diagnostic instruments, medical science, diagnosis, etc., can solve problems affecting accuracy, difficult operation, high risk, etc., and achieve high sensitivity and accuracy , Improve the quality of life and reduce the financial burden
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0045] The present invention aims to propose a non-invasive assessment method for cirrhosis and portal hypertension based on 3D multi-channel convolutional neural network, which provides a new way for non-invasive assessment of patients with portal hypertension; A multi-channel 3D convolutional neural network structure system composed of three convolutional layers, three pooling layers and one fully connected layer, using convolutional neural network to extract 3D CT image features of liver, spleen and portal system, through Softmax function With the expected portal hypertension grading results as the output, the output probability is calculated, and the output weight of each neuron is adjusted through repeated learning and training, and an artificial intelligence evaluation system for cirrhosis portal hypertension risk classification based on CTA images is constructed. The individualized precise diagnosis and treatment of portal hypertension provides non-invasive auxiliary dec...
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