US Patent Application 17786135. SYSTEMS AND METHODS FOR MEDICAL IMAGING simplified abstract

From WikiPatents
Jump to navigation Jump to search

SYSTEMS AND METHODS FOR MEDICAL IMAGING

Organization Name

KONINKLIJKE PHILIPS N.V.


Inventor(s)

Tobias Wissel of Lübeck (NL)

Irina Waechter-stehle of Hamburg (DE)

Scott Holland Settlemier of Marlborough MA (US)

Frank Michael Weber of Norderstedt (DE)

Arne Ewald of Hamburg (DE)

Matthias Lenga of Mainz (DE)

Jochen Peters of Norderstedt (DE)

André Goossen of Eldena (DE)

Sebastian Wild of Hamburg (DE)

SYSTEMS AND METHODS FOR MEDICAL IMAGING - A simplified explanation of the abstract

This abstract first appeared for US patent application 17786135 titled 'SYSTEMS AND METHODS FOR MEDICAL IMAGING

Simplified Explanation

The invention is a method for determining the confidence of an image segmentation.

  • Obtaining an image of an anatomical structure and a model of the structure.
  • Processing the image to generate multiple image segmentation outputs.
  • Each output contains a set of values associated with nodes in the model.
  • Determining a confidence value for each node based on the values associated with it.
  • Generating a confidence map of the anatomical structure based on the confidence values of each node.


Original Abstract Submitted

The invention provides a method for determining a confidence value for an image segmentation. The method includes obtaining an image, wherein the image comprises a view of an anatomical structure and a model of the anatomical structure is obtained, wherein the model comprises a plurality of nodes. The image is processed to generate a plurality of image segmentation outputs, wherein each image segmentation output comprises a set of values for the view, wherein each value of the set of values is associated with a node of the plurality of nodes of the model. For each node of the model, a confidence value is determined based on the plurality of values corresponding to the node. A confidence map of the anatomical structure is generated based on the confidence value of each node.