System and method for the validation and quality assurance of computerized contours of human anatomy

Patent metadata

Field	Value
Publication number	US-11324968-B2
Application number	US-201916451760-A
Country	US
Kind code	B2
Filing date	Jun 25, 2019
Priority date	Aug 8, 2013
Publication date	May 10, 2022
Grant date	May 10, 2022

Abstract

A system and method for validating the accuracy of delineated contours in computerized imaging using statistical data for generating assessment criterion that define acceptable tolerances for delineated contours, with the statistical data being conditionally updated and/or refined between individual processes for validating delineated contours to thereby adjust the tolerances defined by the assessment criterion in the stored statistical data, such that the stored statistical data is more closely representative of a target population. In an alternative embodiment, a system and method for validating the accuracy of delineated contours in computerized imaging using machine learning for assessing delineated contours, with the machine learning training data being used to generate geometric attributes, and the geometric attributes used to construct intra- and interstructural geometric attribute distribution models to automatically detect contouring errors. The present invention may be used to facilitate, as one example, radiation therapy.

First claim

What is claimed is:

1. A method for validating accuracy of delineated contours in computerized imaging, comprising:
retrieving one or more approved radiation therapy contours;
retrieving a contour to be evaluated;
calculating an attribute of one or more of the one or more approved radiation therapy contours;
constructing assessment criterion parameters using machine learning;
calculating an attribute based on the contour to be evaluated; and
detecting a contouring error by fitting the attributes of the contour to be evaluated against the assessment criterion parameters.

2. The method of claim 1 , wherein the attribute of the one or more of the one or more approved radiation therapy contours is a geometric attribute.

3. The method of claim 1 , further comprising visualizing the contouring error by a graphical user interface, or, using graphics techniques.

4. The method of claim 3 , wherein visualizing the contouring error by a graphical user interface or using graphics techniques further comprises presenting differences between patient contours and the assessment criterion parameters.

5. The method of claim 1 , further comprising generating an error report based on the contouring error.

6. The method of claim 5 , further comprising transmitting the error report over a computer network.

7. The method of claim 1 , further comprising adding the contour to be evaluated to the one or more approved radiation therapy contours.

8. The method of claim 1 further comprising allowing clinicians to directly modify one or more reported incorrect radiation therapy contours by moving control points of the one or more reported incorrect radiation therapy contours.

9. The method of claim 1 wherein the contour to be evaluated is a patient specific radiation therapy contour that corresponds to a patient receiving adaptive radiation therapy.

10. The method of claim 1 wherein the contour to be evaluated is a patient specific radiation therapy contour that corresponds to a patient receiving on-line adaptive radiation therapy.

Assignees

• Univ Washington

Inventors

• Chen Hsin-Chen
• Mutic Sasa
• Tan Jun
• Altman Michael
• Kavanaugh James
• Li Hua

Classifications

• G06T7/13 Primary

  Edge detection · CPC title

• G06T2207/10081

  Computed x-ray tomography [CT] · CPC title

• G06T7/60

  Analysis of geometric attributes · CPC title

• A61N5/1039 Primary

  using functional images, e.g. PET or MRI · CPC title

• G06T2207/30004

  Biomedical image processing · CPC title