METHOD AND SYSTEM FOR EVALUATING TWO TIME-SEPARATED MEDICAL IMAGES

• US 20080159607A1
• Filed: 06/28/2007
• Published: 07/03/2008
• Est. Priority Date: 06/28/2006
• Status: Active Grant

• Current Assignee: Siemens Healthcare GMBH (Siemens AG)
• Original Assignee: Siemens AG
• Inventors: Littmann, Arne
• Granted Patent: US 7,933,440 B2
• Time in Patent Office: Days
• US Class Current: 382/128
• CPC Class Codes: A61B 2090/374 NMR or MRI
• CPC Class Codes: A61B 34/10 Computer-aided planning, simulation or modelling of surgical operations
• CPC Class Codes: A61B 5/055 involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
• CPC Class Codes: A61B 5/4064 Evaluating the brain A61B5/031, A61B5/369, A61B5/14553 take precedence
• CPC Class Codes: A61B 5/4088 Diagnosing of monitoring cognitive diseases, e.g. Alzheimer, prion diseases or dementia
• CPC Class Codes: A61B 6/03 Computed tomography [CT] echo-tomography A61B8/14
• CPC Class Codes: A61B 6/463 characterised by displaying multiple images or images and diagnostic data on one display
• CPC Class Codes: G06T 7/30 Determination of transform parameters for the alignment of images, i.e. image registration

Abstract

In a method for evaluation of two images of an organ system acquired at different points in time to establish a pathological variation, the organ system exhibits a first region and a second region that are present in and that are differentiated in each of the images, with the second region of the pathological variation being acquired more strongly than the first region. A registration is determined that causes the respective first region in two images to be in registration with each other. Imaging system-dependent differences, in particular deformations, are determined and compensated between the two images. After an extension of the registration such that the second region is encompassed as well by the extended registration, via a transformation one of the two images to the other can be made, presented and/or stored that includes the second region, using the extended registration. A medical imaging system with a computer can implement the method.

Claims

1. A method for assisting evaluation of first and second images, respectively acquired at different points in time, of an organ system, said first and second images containing corresponding representations of said organ system with said organ system, in each of said first and second images, exhibiting a first region and a differentiatable second region representing a pathological condition, with said pathological condition being represented more strongly in said first region of each of said first and second images, said method comprising the steps of:

automatically electronically determining a registration that causes the respective first regions in the first and second images to be in registration with each other;

extending said registration determined for said first region to encompass said second region in one of said first and second images, thereby obtaining an extended registration;

transforming said one of said first and second images using said extended registration to cause said one of said first and second images to conform to the other of said first and second images, thereby obtaining a transformed image; and

automatically presenting an evaluation result that establishes a change in said pathological condition between said respective points in time, said result being selected from the group consisting of visually presenting said transformed image and the other image, and automatically determining a difference image from said transformed image and said other image.

2. A method as claimed in claim 1 wherein said change in said pathological condition is represented in said first and second images only in said second region.

3. A method as claimed in claim 1 comprising determining said registration by bringing only said first region in said first image into congruency with said first region in said second image.

4. A method as claimed in claim 1 comprising determining said registration as a non-linear registration of said first region in each of said first and second images.

5. A method as claimed in claim 1 comprising extending said registration by enlarging said first region in one of said first and second images and expanding the registration of said first region in said first image with said first region in said image corresponding to the enlarged first region.

6. A method as claimed in claim 5 comprising iteratively enlarging said first region.

7. A method as claimed in claim 1 comprising segmenting said first region before determining said registration.

8. A method as claimed in claim 1 comprising employing three-dimensional images of said organ system, generated with an imaging modality selected from the group consisting of a magnetic resonance apparatus and a computed tomography apparatus, as said first and second images.

9. A method as claimed in claim 1 comprising employing first and second images of the brain of a patient as said organ system in said first and second images.

10. A method as claimed in claim 9 wherein said first region represents white brain matter and wherein said second region represents gray brain matter.

11. A method as claimed in claim 9 comprising acquiring said first and second images at an interval in a range between three to six months from each other.

12. A medical image evaluation system for assisting evaluation of first and second images, respectively acquired at different points in time, of an organ system, said first and second images containing corresponding representations of said organ system with said organ system, in each of said first and second images, exhibiting a first region and a differentiatable second region representing a pathological condition, with said pathological condition being represented more strongly in said first region of each of said first and second images, said system comprising:

a computer that automatically determines a registration that causes the respective first regions in the first and second images to be in registration with each other, and that extends said registration determined for said first region to encompass said second region in one of said first and second images, thereby obtaining an extended registration, and that transforms said one of said first and second images using said extended registration to cause said one of said first and second images to conform to the other of said first and second images, thereby obtaining a transformed image, and automatically generates an evaluation result that establishes a change in said pathological condition between said respective points in time, said result being selected from the group consisting of generating first display data to visually present said transformed image and the other image, and generating second display data representing a difference image from said transformed image and said other image; and

a display unit connected to said computer that displays said evaluation result.