US5937083A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Image registration using closest corresponding voxels with an iterative registration process
Assignee: DEPARTMENT HEALTH AND HUMAN SERVICES United States, Secretary of
•
Filing: 1997-04-28
•
Granted: 1999-08-10
•
Expires: 2017-04-28
Abstract
Abstract A robust, automatic volume registration process based on intensity gradients successfully performs registrations under conditions of unrelated intervolume voxel intensities, significant object displacements and/or significant amounts of missing data. The process allows a user to visualize the registration convergence, clearly illustrating any source of registration errors. The process includes steps of matching, based on iteratively finding a correspondence of the closest voxels containing a high three-dimensional (3D) intensity gradient magnitude. The process is a powerful method of sequence-independent MR volume registration which is simple to both use and understand.
Inventors
- 👤 John Ostuni
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-06 16:10
CPC Classifications
G; G06; G06T; G06T3/00; G06T3/14; G06T7/00; G06T7/30; G06T7/33; G06T7/38; G06T2207/00; G06T2207/30; G06T2207/30004; G06T2207/30016
Claims Analysis
Total Claims: 21
Claim 1
Independent Claim
193 words
A method of registering three-dimensional (3D) volume images, wherein a volume image is represented by an array of voxel color values characterizing physical parameters of a volume of a 3D object, wherein the 3D object is characterized, at least in part, by the volume images being registered, the method comprising the steps of: capturing a first volume image, the first volume image characterizing a first set of physical characteristics of a scanned 3D object; capturing a second volume image, the second volume image characterizing a second set of physical characteristics of the scanned 3D object; generating voxel pairs, wherein each voxel pair comprises a first voxel from a first of the two volume images and a second voxel from the second of the two volume images, when the second voxel has a characteristic that is common to both the first voxel and the second voxel and the second voxel is at least as close to the first voxel as any other voxel in the second volume image having the characteristic; and iteratively determining a registration transformation from the generated voxel pairs, where the registration transformation is a transformation relating the two volume images.
Claim 2
Independent Claim
193 words
A method of registering three-dimensional (3D) volume images, wherein a volume image is represented by an array of voxel color values characterizing physical parameters of a volume of a 3D object, wherein the 3D object is characterized, at least in part, by the volume images being registered, the method comprising the steps of: capturing a first volume image, the first volume image characterizing a first set of physical characteristics of a scanned 3D object; capturing a second volume image, the second volume image characterizing a second set of physical characteristics of the scanned 3D object; generating voxel pairs, wherein each voxel pair comprises a first voxel from a first of the two volume images and a second voxel from the second of the two volume images, when the second voxel has a characteristic that is common to both the first voxel and the second voxel and the second voxel is at least as close to the first voxel as any other voxel in the second volume image having the characteristic; and iteratively determining a registration transformation from the generated voxel pairs, where the registration transformation is a transformation relating the two volume images.
Claim 3
Dependent Claim
31 words
The method of claim 1, wherein the characteristic that is in common is a characteristic of the first voxel and the second voxel having a common value for a voxel property.
Claim 4
Dependent Claim
30 words
The method of claim 1, wherein the characteristic that is in common is a characteristic of the first voxel and the second voxel having similar values for a voxel property.
Claim 5
Dependent Claim
18 words
The method of claim 3, wherein the similar values are both values within a predetermined range of values.
Claim 6
Dependent Claim
20 words
The method of either claim 2 or claim 3, wherein the voxel property is a function of a voxel intensity.
Claim 7
Dependent Claim
21 words
The method of either claim 2 or claim 3, wherein the voxel property is a function of a voxel intensity gradient.
Claim 8
Dependent Claim
26 words
The method of either claim 2 or claim 3, wherein the voxel property is a function of a voxel intensity value and neighboring voxel intensity values.
Claim 9
Dependent Claim
22 words
The method of either claim 2 or claim 3, wherein the voxel property is a function of a binarized voxel intensity gradient.
Claim 10
Dependent Claim
19 words
The method of claim 1, wherein the step of generating voxel pairs excludes voxels meeting a predetermined exclusion criteria.
Claim 11
Dependent Claim
17 words
The method of claim 9, wherein the predetermined exclusion criteria is a function of voxel color value.
Claim 12
Dependent Claim
16 words
The method of claim 9, wherein the predetermined exclusion criteria is a function of voxel intensity.
Claim 13
Dependent Claim
22 words
The method of claim 9, wherein the predetermined exclusion criteria is whether a voxel has an intensity value within an exclusion range.
Claim 14
Dependent Claim
22 words
The method of claim 9, wherein the predetermined exclusion criteria is whether a voxel has an intensity value outside an inclusion range.
Claim 15
Dependent Claim
16 words
The method of claim 9, wherein the predetermined exclusion criteria is a function of voxel location.
Claim 16
Dependent Claim
20 words
The method of claim 9, wherein the predetermined exclusion criteria is whether a voxel is located within an exclusion range.
Claim 17
Dependent Claim
20 words
The method of claim 9, wherein the predetermined exclusion criteria is whether a voxel is located outside an inclusion range.
Claim 18
Independent Claim
172 words
A method of registering two-dimensional (2D) images, wherein an image is represented by an array of pixel color values characterizing physical parameters of an area of an object, wherein the object is characterized, at least in part, by the images being registered, the method comprising the steps of: capturing a first image characterizing a first set of physical characteristics of a scanned object; capturing a second image characterizing a second set of physical characteristics of the scanned object; generating pixel pairs wherein each pixel pair comprises a first pixel from a first of the two images and a second pixel from the second of the two images, when the second pixel has a characteristic that is common to both the first pixel and the second pixel and the second pixel is at least as close to the first pixel as any other pixel in the second image having the characteristic; and iteratively determining a registration transformation from the generated pixel pairs, where the registration transformation is a transformation relating the two images.
Claim 19
Independent Claim
172 words
A method of registering two-dimensional (2D) images, wherein an image is represented by an array of pixel color values characterizing physical parameters of an area of an object, wherein the object is characterized, at least in part, by the images being registered, the method comprising the steps of: capturing a first image characterizing a first set of physical characteristics of a scanned object; capturing a second image characterizing a second set of physical characteristics of the scanned object; generating pixel pairs wherein each pixel pair comprises a first pixel from a first of the two images and a second pixel from the second of the two images, when the second pixel has a characteristic that is common to both the first pixel and the second pixel and the second pixel is at least as close to the first pixel as any other pixel in the second image having the characteristic; and iteratively determining a registration transformation from the generated pixel pairs, where the registration transformation is a transformation relating the two images.
Claim 20
Dependent Claim
128 words
The method of claim 17, further comprising the steps of: generating a second set of pixel pairs, wherein each pixel pair in the second set of pixel pairs comprises a first pixel from the first image and a second pixel from the second image, when the first pixel has a characteristic that is common to both the first pixel and the second pixel and the first pixel is at least as close to the second pixel as any other pixel in the first image having the characteristic; and wherein the step of iteratively determining a registration transformation is performed using the pixel pairs generated in the step of generating pixel pairs and using the pixel pairs generated in the step of generating the second set of pixel pairs.
Claim 21
Dependent Claim
131 words
The method of claim 1, further comprising the steps of: generating a second set of voxel pairs, wherein each voxel pair in the second set of voxel pairs comprises a first voxel from the first volume image and a second voxel from the second volume image, when the first voxel has a characteristic that is common to both the first voxel and the second voxel and the first voxel is at least as close to the second voxel as any other voxel in the first volume image having the characteristic; and wherein the step of iteratively determining a registration transformation is performed using the voxel pairs generated in the step of generating voxel pairs and using the voxel pairs generated in the step of generating the second set of voxel pairs.
References Cited (Backward Citations)
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2002-08-09 | 2003-02-08 | 2003-08-10 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2006-08-09 | 2007-02-08 | 2007-08-10 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2010-08-09 | 2011-02-08 | 2011-08-10 | $7700.00 | Window Closed / Lapsed |