Multi-modal nuclear magnetic resonance image case report automatic generation method
A nuclear magnetic resonance, automatic generation technology, applied in medical reports, medical automatic diagnosis, medical images, etc., can solve problems such as lack of correlation sorting, results are not readable text, etc., to ease the work of radiologists.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment approach
[0040] (1) Data preprocessing
[0041] (1.1) Image data: Use N4ITK and Nyul to adjust the brightness of the image, and get the following figure 1 The results shown; the image is divided into several adjacent areas of 44*44*20, and a small block of 132*132*108 is extracted for each area, that is, 44 padding is added in three directions (for the area outside the boundary of the original image The area is filled with 0); the ground truth of the image segmentation result is divided into 44*44*20 areas. (Note: In order to increase the size of the training set, the 44*44*20 area can be overlapped)
[0042] (1.2) Text data: 1) Remove repeated spaces and punctuation marks in the text; 2) Treat the text as a sample with a period as a unit. 3) Use FoolNLTK to segment the text, and use gensim to get the dictionary and word vector model (set the dimension of the vector to 512). For example ['skull base','structure',',','signal','no disease','rationality','change'], 'morphology' can be ...
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