Automation of therapy planning

Patent metadata

Field	Value
Publication number	US-10022560-B2
Application number	US-201414908226-A
Country	US
Kind code	B2
Filing date	Jul 11, 2014
Priority date	Jul 31, 2013
Publication date	Jul 17, 2018
Grant date	Jul 17, 2018

Abstract

An automated treatment planning system having a planning image memory which stores a volume diagnostic image; a user interface device configured for a user to input data defining a plurality of regions of interest within the volume diagnostic image; and one or more processors. The processors are configured to receive the volume diagnostic image and plurality of user-defined regions of interest indicated within the volume diagnostic image; map the plurality of regions of interest to the body atlas to determine anatomical locations within the plurality of regions of interest; map each region of interest of the plurality of regions of interest to the body atlas to select correct corresponding anatomical structures; receive a treatment plan template based upon the anatomical structures from a knowledge base. A planning module is configured to generate a treatment plan using the treatment plan template.

First claim

The invention claimed is:

1. An automated treatment planning system comprising:
a planning image memory configured to store a volume diagnostic image;
a user interface device configured for a user to input data defining a plurality of regions of interest within the volume diagnostic image;
a ROI mapper having a processor configured to:
receive the volume diagnostic image and the plurality of regions of interest defined within the volume diagnostic image;
map the plurality of regions of interest within the volume diagnostic image to a body atlas to determine corresponding anatomical locations within the plurality of regions of interest; and
map each region of interest of the plurality of regions of interest to the body atlas to select correct corresponding anatomical structures by calculating a similarity metric score between each region of interest of the plurality of regions of interest and each anatomical structure of the body atlas; and

a planning module configured to generate a treatment plan using the mapped plurality of regions of interest.

2. The system according to claim 1 , wherein the ROI mapper is further configured to:
associate the anatomical structure of the body atlas having a highest similarity metric score with an individual region of interest.

3. The system according to claim 1 , wherein the planning module is further configured to:
receive a treatment plan template based upon the mapped regions of interests from a knowledgebase; and
generate an optimal treatment plan according to the treatment plan template.

4. The system according to claim 3 , wherein the treatment plan template includes automated clinical goals and priorities that are unique to the anatomical structures mapped to the plurality of regions of interest.

5. The system according to claim 1 , wherein the user interface device is configured to receive dose and plan requirements from a user.

6. The system according to claim 5 , wherein the planning module is further configured to:
determine whether the generated plan meets user input requirements; and
in response to the generated plan failing to satisfy the user input requirements, iteratively tune dose and plan constraints such that the user input requirements are satisfied.

7. A method of automating treatment planning, comprising:
receiving a volume anatomical image of a patient including a plurality of user-defined regions of interest indicated within the image volume;
mapping of the plurality of regions of interest to a body atlas to determine anatomical locations within the plurality of regions of interest; and
mapping each region of interest of the plurality of regions of interest to the body atlas to select correct corresponding anatomical structures includes including;
calculating a similarity metric score between each region of interest of the plurality of regions of interest and each anatomical structure of the body atlas; and
generating a treatment plan using the mapped plurality of regions of interest.

8. The method according to claim 7 , further including:
when a highest similarity metric score exceeds a threshold metric score associating the anatomical structure of the body atlas having a highest similarity metric score with an individual one of the plurality of regions of interest.

9. The method according to claim 7 , wherein the generating step includes:
receiving a treatment plan template based upon the mapped regions of interests from a knowledgebase; and
generating the treatment plan according to the treatment plan template.

10. The method according to claim 9 , wherein the treatment plan template includes automated clinical goals and priorities that are unique to the anatomical structure mapped to the plurality of regions of interest.

11. The method according to claim 7 , further including:
initially receiving dose and plan requirements from a user via a user input.

12. The method according to claim 11 , wherein the treatment plan generating step further includes:
determining whether the generated treatment plan satisfies the dose and plan requirements; and
in response to the dose and plan requirements not being satisfied, iteratively tuning dose and plan constraints until the dose and plan requirements are satisfied.

13. A non-transitory computer readable medium carrying software for controlling one or more processors to perform the method of claim 7 .

14. An automated treatment planning system comprising:
a planning image memory which stores a volume diagnostic image;
a user interface device configured for a user to input data defining a plurality of regions of interest within the volume diagnostic image; and
one or more processors configured to:
receive the volume diagnostic image and the plurality of regions of interest indicated within the volume diagnostic image;
map the plurality of regions of interest of the volume diagnostic image to anatomical structures using a body atlas;
rank anatomical structures in the body atlas according to a similarity score to a particular region of interest;
select a one of the anatomical structures ranked with a highest similarity score;
access a template associated with the selected one of the anatomical structures to receive dose and plan requirements; and
generate a treatment plan using the template requirements.

15. The automated treatment planning system according to claim 14 , wherein the one or more processors are further configured to:
determine whether the generated treatment plan meets user input requirements; and
in response to the user input requirements not being met, iteratively tune dose and plan constraints such that the user input requirements are satisfied.

Assignees

• Koninklijke Philips Nv

Inventors

• Kumar Prashant
• Bzdusek Karl Antonin

Classifications

• A61N5/1039 Primary

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

• A61N5/1038

  taking into account previously administered plans applied to the same patient, i.e. adaptive radiotherapy · CPC title