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

Generating natural language representations of mental content from functional brain images

A technology of image generation and natural language, applied in medical images, semantic analysis, medical imaging, etc.

Active Publication Date: 2021-06-04
SIEMENS MEDICAL SOLUTIONS USA INC
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Perform base learning to learn image fundamentals directly

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
  • Generating natural language representations of mental content from functional brain images
  • Generating natural language representations of mental content from functional brain images
  • Generating natural language representations of mental content from functional brain images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] This embodiment involves decoding general mental content from functional brain images into a form or representation understandable by humans. This embodiment models how stimuli, such as textual articles, are processed by the human brain. The model is constructed by acquiring brain imaging data while the subject is mentally processing one of a set of stimuli, and the model is used to decode mental content from brain imaging acquired while the subject is processing a different set of stimuli. For example, by using known training data, the model is trained to decode brain imaging data captured while subjects were exposed to unknown and / or test data.

[0030] This embodiment can also generate natural language sentences describing mental content. For example, quantitative representations of mental content are generated, and a separate model generates sentences from those quantitative representations. figure 1 Embodiments for generating natural language representations of m...

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

By way of introduction, the present embodiments described below include apparatus and methods for generating natural language representations of mental content from functional brain images. Given functional imaging data collected while a subject reads a textual article, a reconstruction of the textual article is produced. Linguistic semantic vector representations are assigned (1301) to words, phrases or sentences to be used as training stimuli. Basis learning is performed ( 1305 ) using brain imaging data acquired ( 1303 ) when the subject is exposed to the training stimuli and the corresponding semantic vectors for the training stimuli to directly learn the image basis. Semantic vector decoding is performed ( 1309 ) using the functional brain imaging data for the test stimuli and using the image basis to generate semantic vectors representing the test image stimuli. Text generation is then performed (1311) using the decoded semantic vectors representing the test imaging stimuli.

Description

[0001] Cross References to Related Applications [0002] This patent document claims priority to U.S. Provisional Application No. 62 / 245,593, filed October 23, 2015, and U.S. Provisional Application No. 62 / 249,825, filed November 2, 2015, which are adopted in their entirety References are hereby incorporated. [0003] research agreement [0004] This research is based on work supported in part by the Office of the Director of National Intelligence (ODNI), Intelligence Advanced Research Projects Agency (IARPA) through the Air Force Research Laboratory (AFRL) under contract number FA8650-14-C-7358. The government has certain rights in this invention. Background technique [0005] This embodiment involves decoding mental content from functional brain images. The most common form of brain decoding determines which of a limited set of stimuli to show a subject using brain imaging. In contrast, generative brain decoding generates complete artifacts to represent mental content an...

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
Patent Type & Authority Patents(China)
IPC IPC(8): A61B5/055A61B5/369A61B5/24G16H30/40G16H50/50G16H50/20
CPCA61B34/10A61B5/055A61B5/7267A61B5/0042A61B2576/026G16H30/40G16H50/20G16H50/50A61B5/0263G06N3/08G06F40/30A61B5/378
Inventor F.佩赖拉娄彬A.拉扎尔伊道
Owner SIEMENS MEDICAL SOLUTIONS USA INC
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