Image based clinical trial assessment

Patent metadata

Field	Value
Publication number	US-9420972-B2
Application number	US-201414334757-A
Country	US
Kind code	B2
Filing date	Jul 18, 2014
Priority date	Jan 13, 2009
Publication date	Aug 23, 2016
Grant date	Aug 23, 2016

Abstract

A method for assessing a treatment in a trial includes obtaining images generated from image data acquired at different times during a trial time period for a same region of interest of a subject. The treatment is administered to the subject for the trial. The method further includes co-registering the images and mapping the co-registered images to a reference image representing the region of interest. The method further includes generating a trial image of the region of interest showing at least one of structural or functional physiological changes that occurred during the trial time period based on the mapped co-registered images, and displaying the trial image.

First claim

The invention is claimed to be:

1. A computer implemented method for determining an efficacy of a treatment in a trial, comprising:
co-registering images of a set of images corresponding to a same region of interest of a subject to a baseline image via an affine registration by way of computer, wherein the baseline image is from the set of images and the set of images are acquired at different times after administering a trial treatment to the subject;
applying a computer implemented transformation to the co-registered images to fit the co-registered images to an anatomical model representing the region of interest;
generating a value representing a physiological change in the region of interest based on the mapped co-registered images; and
determining an efficacy of the treatment based on the value.

2. The computer implemented method of claim 1 , wherein the value is compared to a predetermined threshold value.

3. The computer implemented method of claim 1 , wherein the value represents one or more voxels in the region of interest.

4. The computer implemented method of claim 1 , further comprising:
co-registering a second set of images corresponding to the same region of interest of a second subject, wherein the images are acquired at different times after administering a second treatment or a placebo to the second subject;
applying the computer implemented transformation to the second co-registered images to fit the second co-registered images to the anatomical model representing the region of interest;
generating a second value representing a physiological change in the region of interest based on the second mapped co-registered images; and
determining the efficacy of the treatment based on a difference between the value and the second value.

5. The computer implemented method of claim 4 , further comprising displaying a difference image visually presenting the difference between the value and the second value.

6. The computer implemented method of claim 1 , further comprising visually displaying the value.

7. The computer implemented method of claim 1 , further comprising superimposing indicia representing the value over an image of the region of interest.

8. The computer implemented method of claim 1 , wherein the co-registration includes an affine registration.

9. The computer implemented method of claim 1 , wherein the transformation includes a single elastic fitting.

10. The computer implemented method of claim 1 , wherein a trial population size is determined by a trial population estimator based on a given statistical power and an image analysis algorithm, which includes transforming the co-registered images to the anatomical model.

11. The computer implemented method of claim 10 , wherein an estimated trial cost is determined by a trial cost estimator based on the estimated trial population size.

12. The computer implemented method of claim 11 , wherein the trial population estimator and the trial cost estimator are part of a networked based service.

13. The computer implemented method of claim 12 , wherein the service determines a suitable image analysis algorithm based on a trial budget and a predetermined statistical power.

14. The computer implemented method of claim 1 , further comprising:
generating the computer implemented transformation by generating a transform for only a single one of the co-registered images, wherein the generated transform is applied to fit each of the co-registered images to the anatomical model.

15. The computer implemented method of claim 1 , further comprising:
generating the computer implemented transformation by taking an average of the co-registered images and generating a transform for the average image, wherein the generated transform is applied to fit each of the co-registered images to the anatomical model.

16. The computer implemented method of claim 1 , wherein determining the efficacy includes assessing a safety of the treatment.

17. The computer implemented method of claim 1 , wherein determining the efficacy includes assessing an effectiveness of the treatment.

18. The computer implemented method of claim 1 , wherein determining the efficacy determining whether a new treatment is more effective than a previously used treatment.

19. The computer implemented method of claim 1 , wherein the co-registered images are transformed in parallel once all of the images are acquired.

20. The computer implemented method of claim 1 , wherein the co-registered images are transformed sequentially as images are obtained.

Assignees

• Thiele Frank O
• Minoshima Satoshi
• Koninklijke Philips Nv

Inventors

• Thiele Frank O
• Minoshima Satoshi

Classifications

• G06Q10/06313 Primary

  Resource planning in a project environment · CPC title

• G06F19/366

  Physics · mapped topic

• G06T7/0024

  Physics · mapped topic

• G06T2207/10072

  Tomographic images · CPC title

• G06T7/0032

  Physics · mapped topic