Unlock instant, AI-driven research and patent intelligence for your innovation.

Systems and methods for optimizing detection and labeling of anatomical structures of interest

A technology for structures of interest, anatomical structures, used in character and pattern recognition, instrumentation, healthcare informatics, etc. to improve patient care and optimize delivery

Active Publication Date: 2022-07-29
KONINKLJIJKE PHILIPS NV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, the data retrieval process (from the image storage device such as the PACS to the workstation) takes a non-negligible amount of time in the workflow of a radiologist who wants to review the data

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
  • Systems and methods for optimizing detection and labeling of anatomical structures of interest
  • Systems and methods for optimizing detection and labeling of anatomical structures of interest
  • Systems and methods for optimizing detection and labeling of anatomical structures of interest

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] Anatomical regions in medical images can be identified using a variety of image processing techniques, including classification-based anatomical structure detection, registration using statistical templates, and model-based segmentation, or a combination of those techniques. A possible embodiment is the sliding window method. In this context, anatomy detection is a classification task. Using a feature-based representation of a set of positive and negative image patches, machine learning is used to discriminate between the two classes. In the detection phase, the classified images are used in order to identify image regions with high probability for the target anatomy. Using this method, a large number of detectors may have to be applied to the image in order to estimate the likelihood of all anatomical structures under consideration. Furthermore, the selection of an appropriate accepted threshold for likelihood is critical to balance the tradeoff between false positiv...

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

This application describes systems and methods for optimal detection and labeling of structures of interest. The system includes a current patient studies database containing current patient studies with clinical background information. The department also includes: an image metadata processing engine configured to extract metadata to prepare input for the anatomy classifier; a natural language processing engine configured to extract clinical context information from previous patient files; anatomical structure detection and a tagging engine; and a display device configured to display findings from the current patient study. The anatomical structure detection and labeling engine is configured to identify and label one or more structures of interest from the extracted metadata and clinical context information. The processor is also configured to aggregate the series level data. Specifically, once patient information is retrieved from the current patient study, the marked anatomy and high risk anatomy are combined to form a prioritized list of structures of interest.

Description

technical field [0001] This application relates generally to detecting and visualizing relevant patient information and finding-specific recommendations in a radiology workflow. This application is particularly applicable in connection with providing finding-specific recommendations to radiologists of relevant anatomy to review patients based on information extracted from non-image data such as previous patient reports and DICOM information, and will specifically It is described with reference to it. This application is also specifically used in connection with, and will be described with specific reference to, providing these finding-specific recommendations to the radiologist based on the radiologist's priority to review. However, it should be understood that the present application also applies to other usage scenarios and is not necessarily limited to the aforementioned applications. Background technique [0002] It has been recognized that quantitative imaging aids in...

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): G16H30/20G16H10/60G16H70/60
CPCG06F16/5866G16H30/20G16H70/60G06F40/30
Inventor K·卢A·格罗特钱悦晨A·扎尔巴赫R·N·特利斯D·贝斯特罗夫R·科亨B·发迪达L·沃尔洛赫
Owner KONINKLJIJKE PHILIPS NV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com