Method and device for registering two medical image data sets taking into account scene changes

Inventors

Horn, Andreas • König, Thomas • Fleischmann, Christof

Assignees

Ziehm Imaging GmbH

Abstract

A method of registering two sets of medical image data taking into account scene changes can include providing a first and a second medical image data set by means of a medical device, subdividing the first and second medical image data sets into an equal number of sub-images, performing a number of individual registrations between the first and second medical image data sets with respective optimization of a similarity measure, identifying the sub-images that have a scene change, and performing a final registration between the first and the second medical image data set by masking out the identified sub-images or a masked out sub-image combination. For each individual registration, at least one sub-image of the first and/or second medical image data set can be masked out by means of a random process when determining the respective measure of similarity.

Core Innovation

The disclosed invention relates to registering two sets of medical image data taking into account scene changes. A first medical image data set and a second medical image data set are received from one or more medical devices and each is subdivided into an equal number of sub-images.

A plurality of individual registrations are performed between the first and second medical image data sets with optimization of a similarity measure. For each individual registration, at least one sub-image of the first and/or second medical image data set is masked out by means of a random process when determining the respective similarity measure, so that different masking is applied across the plurality of registrations.

Sub-images that have a scene change are identified, and a final registration between the first medical image data set and the second medical image data set is performed by masking out the sub-images identified as having a scene change or a masked-out sub-image combination used in the individual registrations. Scene-change identification is based on ranking similarity measures and using a frequency distribution that exceeds a threshold value.

Claims Coverage

The independent claim covers registering two sets of medical image data while accounting for scene changes using subdivided sub-images, multiple individual registrations with random masking during similarity-measure optimization, scene-change sub-image identification via ranking and frequency exceeding a threshold, and a final registration using masked-out scene-change sub-images or masked-out combinations from intermediate registrations.

Overall, the claim coverage centers on identifying scene-change sub-images after multiple similarity-measure optimizations performed under random masking, and then using those identified scene-change sub-images or masked-out combinations from intermediate registrations to drive a final registration between the two medical image datasets.

Stated Advantages

Documented Applications