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

Feature identification in medical imaging

A technology for medical imaging and feature recognition, which is applied in the field of medical imaging and can solve the problem of not providing further information on different types of image features.

Pending Publication Date: 2020-06-05
KONINKLJIJKE PHILIPS NV
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditional approaches to this merely create "heatmaps" (e.g., visual representations of decision-relevant locations in medical images) without providing any further information related to different types of image features

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
  • Feature identification in medical imaging
  • Feature identification in medical imaging
  • Feature identification in medical imaging

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] A concept is proposed for identifying image features in medical images and associating a measure of uncertainty with such features. This may enable the provision of information that may be useful for evaluating and / or improving model output.

[0043] In particular, GAN and BDL networks can be employed. The combined use of GAN and BDL networks can capture different types of uncertainty. For example, BDL can capture uncertainties related to (insufficient) sample size, borderline cases, and accidental uncertainties (e.g., uncertainties related to noise inherent in observations), while GANs can capture out-of-sample uncertainties , that is, the part of the image that differs significantly from the data generating distribution. Associating such uncertainty measures with image features may allow visual features (eg, graphical overlays of textual descriptions with associated uncertainty measures) to be associated with image features. This can facilitate easy and fast evalua...

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

Presented are concepts for feature identification in medical imaging of a subject. One such concept processes a medical image with a Bayesian deep learning network to determine a first image feature of interest and an associated uncertainty value, the first image feature being located in a first sub-region of the image. It also processes the medical image with a generative adversarial network to determine a second image feature of interest within the first sub-region of the image and an associated uncertainty value. Based on the first and second image features and their associated uncertaintyvalues, the first sub-region of the image is classified.

Description

technical field [0001] The present invention relates generally to medical imaging of objects such as people or patients, and more particularly to identifying features in medical images of objects. Background technique [0002] Recent technological advances have led to the use of models designed to assist in the analysis of medical images (eg, for the purpose of identifying medical features and / or making clinical decisions). [0003] In medical image analysis, it is preferable to be able to explain the reasoning behind a model's decision(s). This is especially important in the field of healthcare, where medical practitioners need to understand the results of the analysis and accept or adjust the model's decisions accordingly. [0004] To facilitate model validation, it is known to associate interpretations with visual features superimposed on medical images (ie, visual overlays of images) so that medical practitioners can quickly and easily inspect or verify decisions about ...

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 Applications(China)
IPC IPC(8): G16H30/20G06V10/764
CPCG16H30/20G06T7/0012G06T2207/10081G06T2207/20084G06T2207/30096G06V2201/032G06V10/82G06V10/809G06V10/764G06F18/254G06T2207/20081G06V2201/03G06F18/2431G06F18/24155
Inventor D·马夫罗伊迪斯B·巴克S·特拉亚诺夫斯基
Owner KONINKLJIJKE PHILIPS NV
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