SYSTEM AND METHOD FOR SHAPE BASED RETRIEVAL OF PRIOR PATIENTS FOR AUTOMATION AND QUALITY CONTROL OF RADIATION THERAPY TREATMENT PLANS

• US 20110153547A1
• Filed: 06/22/2010
• Published: 06/23/2011
• Est. Priority Date: 06/23/2009
• Status: Active Grant

• Current Assignee: Johns Hopkins University
• Original Assignee: Johns Hopkins University
• Inventors: Simari, Patricio, McNutt, Todd, Wu, Binbin, Kazhdan, Michael, Taylor, Russell H.
• Granted Patent: US 8,688,618 B2
• Time in Patent Office: Days
• US Class Current: 706/54
• CPC Class Codes: A61N 2005/1041 using a library of previously administered radiation treatment applied to other patients
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G16H 20/40 relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

A system and method for determining at least one new treatment plan for at least one new patient, comprising: providing at least one representation of the at least one new patient'"'"'s at least one organ at risk relative to at least one target; searching for at least one prior treatment plan for at least one prior patient with at least one similar representation; and reviewing the at least one prior treatment plan for the at least one prior patient in order to determine whether the at least one new treatment plan can be improved based on information in the at least one prior treatment plan.

Claims

1. A method for determining at least one new treatment plan for at least one new patient, comprising:

providing, utilizing at least one overlap volume histogram (OVH) module, at least one representation of the at least one new patient'"'"'s at least one organ at risk relative to at least one target;

searching, utilizing at least one matching module, for at least one prior treatment plan for at least one prior patient with at least one similar representation; and

reviewing the at least one prior treatment plan for the at least one prior patient in order to determine whether the at least one treatment plan can be improved based on information in the at least one prior treatment plan.

2. The method of claim 1, wherein the at least one representation comprises at least one shape metric that captures the geometries of the at least one target and the at least one organ at risk and their configurations relative to each other.

3. The method of claim 1, wherein the at least one representation computes the distribution of distances of points in the at least one organ at risk from the at least one target.

4. The method of claim 3, further comprising:

defining, utilizing the at least one OVH module, at least one OVH comprising at least one one-dimensional distribution measuring each organ at risk'"'"'s proximity to the at least one target.

5. The method of claim 4, wherein the at least one OVH is computed as follows:

using segmented CT scans, computing the volume of the at least one target'"'"'s signed distance transform for each segment of the target; and

evaluating the distance transform of the at least one target.

6. The method of claim 4, wherein the following formula is used for the OVH:

7. The method of claim 4, wherein at least one OVH value is utilized to determine at least one dose volume histogram (DVH) value.

8. The method of claim 7, wherein the at least one DVH value is utilized as at least one input parameter for inverse planning utilizing at least one IMRT.

17. The method of claim 1, further comprising:

determining whether delivering at least one lower dose to the at least one organ at risk is feasible.

9. A system for determining at least one new treatment plan for at least one new patient, comprising:

at least one computer;

at least one application coupled to the at least one computer, the at least one application configured for;

providing at least one representation of the at least one new patient'"'"'s at least one organ at risk relative to at least one target;

searching for at least one prior treatment plan for at least one prior patient with at least one similar representation; and

reviewing the at least one prior treatment plan for the at least one prior patient in order to determine whether the at least one new treatment plan can be improved based on information in the at least one prior treatment plan.

10. The system of claim 9, wherein the at least one representation comprises at least one shape metric that captures the geometries of the at least one target and the at least one organ at risk and their configurations relative to each other.

11. The system of claim 9, wherein the at least one representation computes the distribution of distances of points in the at least one organ at risk from the at least one target.

12. The system of claim 11, wherein the at least one application further comprises:

defining at least one overlap volume histogram (OVH) comprising at least one one-dimensional distribution measuring each organ at risk'"'"'s proximity to the at least one target.

13. The system of claim 12, wherein the at least one application computes the at least one OVH as follows:

using segmented CT scans, computing the volume of the at least one target'"'"'s signed distance transform for each segment of the target; and

evaluating the distance transform of the at least one target.

14. The system of claim 12, wherein the at least one application utilizes the following formula for the OVH:

15. The system of claim 12, wherein the at least one application utilizes the at least one OVH value to determine at least one dose volume histogram (DVH) value.

16. The system of claim 15, wherein the at least one application utilizes the at least one DVH value as at least one input parameter for inverse planning utilizing at least one IMRT.

18. The system of claim 9, wherein the at least one application is further configured for determining whether delivering at least one lower does to the at least one organ at risk is feasible.