Patent US6154518A successfully refreshed from Google Patents.
US6154518A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Three dimensional locally adaptive warping for volumetric registration of images
Assignee: General Electric Co
•
Filing: 1998-11-04
•
Granted: 2000-11-28
•
Expires: 2018-11-04
Abstract
Abstract Locally-adaptive, sub-voxel registration of two volumetric data sets is performed by generating match points and then, using the match points, generating a locally-adaptive image-to-warp transformation. Generation of the match points is accelerated by generating a volume hierarchy and then identifying a set of 3D points in the first volume for designation as interesting points. Interesting points in the first volume are then matched with their corresponding points in the second volume. After performing match point generation, points on a cubic grid in the first volume are matched to the corresponding match points in the second volume by resampling the match points on the cubic grid in the first volume. After a grid of match points has been identified, the displacement (dx, dy, dz) that should be added to each cubic grid point in the first volume to identify the coordinates of the corresponding point in the second volume is determined. Using the displacements in the match points, a warping transformation function that specifies the displacement for each point (x, y, z) in the first volume is determined. The transformation function maps the matched points in the first volume to corresponding points in the second volume by determining the amount of displacement in the x, y and z directions.
Inventors
- 👤 Rajiv Gupta
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 22:16
CPC Classifications
G; G06; G06T; G06T3/00; G06T3/14; G06T3/153; G06T7/00; G06T7/30; G06T7/32; G06T7/38; G06T2207/00; G06T2207/30; G06T2207/30004; G06T2207/30101
Claims Analysis
Total Claims: 23
Claim 1
Independent Claim
56 words
A method for generating points in a first volumetric image that register to points in a second volumetric image, comprising the steps of: generating match points between a set of the first volumetric image data and a set of the second volumetric image data; and generating a locally-adaptive volume-to-volume image transform using the generated match points.
Claim 2
Independent Claim
56 words
A method for generating points in a first volumetric image that register to points in a second volumetric image, comprising the steps of: generating match points between a set of the first volumetric image data and a set of the second volumetric image data; and generating a locally-adaptive volume-to-volume image transform using the generated match points.
Claim 3
Dependent Claim
31 words
A method in accordance with claim 1 wherein the step of generating match points comprises the steps of generating a volume hierarchy, and identifying interesting points in the first volumetric image.
Claim 4
Dependent Claim
37 words
A method in accordance with claim 2 wherein the step of generating a volume hierarchy comprises the step of generating multiple image data sets having successively reduced resolution for the first and second volumetric image data sets.
Claim 5
Dependent Claim
36 words
A method in accordance with claim 3 wherein an image data hierarchy is generated by successively reducing both volumetric images in a stereo pair to approximately about half their original size with subsampling using Gaussian convolution.
Claim 6
Dependent Claim
33 words
A method in accordance with claim 2 wherein the step of identifying interesting points in the first volumetric image is performed by basing identification of said interesting points on high local intensity variation.
Claim 7
Dependent Claim
142 words
A method in accordance with claim 1 wherein the step of generating match points comprises: generating a volume hierarchy; selecting image data of lowest resolution; and for the selected image data: (a) identifying a set of interesting points in the set of the first volumetric image data; (b) matching the interesting points in the set of the first volumetric image data with corresponding points in the set of the second volumetric image data; (c) determining a perspective transform for registering image subvolumes between the sets of first and second volumetric image data; and (d) selecting a set of next highest resolution volumetric image data and repeating steps (a)-(c) if a set of volumetric image data of highest resolution has not been selected; and (e) ending the match point generation when the set of volumetric image data of highest resolution has been selected.
Claim 8
Dependent Claim
78 words
A method in accordance with claim 1 wherein the step of generating a locally-adaptive volume-to-volume image transform using the generated match points comprises the steps of: matching a set of points on a cubic grid in the first volume with corresponding match points in the second volume; and determining a displacement (dx, dy, dz) to be added to each cubic grid point in the first volume to identify coordinates of the corresponding match point in the second volume.
Claim 9
Dependent Claim
34 words
A method in accordance with claim 7 wherein displacement terms dx, dy and dz are related by: ##EQU2## where f, g, and h are unknown functions whose values are known only at grid points.
Claim 10
Dependent Claim
29 words
A method in accordance with claim 8 further comprising the step of determining values of f, g, and h at an arbitrary point in the first image by interpolation.
Claim 11
Dependent Claim
32 words
A method in accordance with claim 9 wherein each pixel in the first volumetric image is transformed by the displacement given by interpolation to find the corresponding pixel in the second image.
Claim 12
Dependent Claim
32 words
A method in accordance with claim 1 further comprising the step of subtracting the logarithm of a warp image data value from the logarithm of a corresponding second volumetric image data value.
Claim 13
Dependent Claim
58 words
Apparatus for generating registering points in a first volumetric image to points in a second volumetric image, said apparatus comprising a processor programmed to generate match points between a set of the first volumetric image data and a set of the second volumetric image data, and to generate a locally-adaptive volume-to-volume image transform using the generated match points.
Claim 14
Dependent Claim
58 words
Apparatus for generating registering points in a first volumetric image to points in a second volumetric image, said apparatus comprising a processor programmed to generate match points between a set of the first volumetric image data and a set of the second volumetric image data, and to generate a locally-adaptive volume-to-volume image transform using the generated match points.
Claim 15
Dependent Claim
31 words
Apparatus in accordance with claim 12 wherein, to generate said match points, said processor is programmed to generate a volume hierarchy and to identify interesting points in the first volumetric image.
Claim 16
Dependent Claim
146 words
Apparatus in accordance with claim 12 wherein, to generate said match points, said processor is programmed to: generate a volume hierarchy; select the image data of lowest resolution; and for the selected image data, to: (a) identify a set of interesting points in the set of the first volumetric image data; (b) match the interesting points in the set of the first volumetric image data with corresponding points in the set of the second volumetric image data; (c) determine a perspective transform for registering image subvolumes between the sets of first and second volumetric image data; and (d) select a set of next highest resolution volumetric image data and repeat steps (a)-(c) if a set of volumetric image data of highest resolution has not been selected; and (e) end the match point generation when the set of volumetric image data of highest resolution has been selected.
Claim 17
Dependent Claim
77 words
Apparatus in accordance with claim 12 wherein, to generate a locally-adaptive volume-to-volume image transform using the generated match points, said processor is programmed to match a set of points on a cubic grid in the first volume with corresponding match points in the second volume, and to determine a displacement (dx, dy, dz) to be added to each cubic grid point in the first volume to identify coordinates of the corresponding match point in the second volume.
Claim 18
Dependent Claim
33 words
Apparatus in accordance with claim 15 wherein displacement terms dx, dy and dz are related by: ##EQU3## where f, g, and h are unknown functions whose values are known only at grid points.
Claim 19
Dependent Claim
33 words
Apparatus in accordance with claim 12 wherein said processor is further programmed to subtract the logarithm of a warp image data value from the logarithm of a corresponding second volumetric image data value.
Claim 20
Dependent Claim
81 words
Apparatus for generating registering points in a volumetric mask image data set to points in a volumetric opacified image data set, said apparatus comprising a processor programmed to: generate match points between the volumetric mask image data set and the opacified image data set; generate a locally-adaptive volume-to-volume image transform using the generated match points to generate a volumetric warp image; and subtract the logarithm of a warp image data value from the logarithm of a corresponding opacified image data value.
Claim 21
Dependent Claim
81 words
Apparatus for generating registering points in a volumetric mask image data set to points in a volumetric opacified image data set, said apparatus comprising a processor programmed to: generate match points between the volumetric mask image data set and the opacified image data set; generate a locally-adaptive volume-to-volume image transform using the generated match points to generate a volumetric warp image; and subtract the logarithm of a warp image data value from the logarithm of a corresponding opacified image data value.
Claim 22
Dependent Claim
119 words
Apparatus in accordance with claim 18 wherein, to generate said match points, said processor is programmed to: generate a volume hierarchy; select the image data of lowest resolution; and for the selected image data, to: (a) identify a set of interesting points in the mask image data; (b) match the interesting points in the mask image data with corresponding points in the opacified image data; (c) determine a perspective transform for registering image subvolumes between the mask and opacified image data; and (d) select next highest resolution image data and repeat steps (a)-(c) if the highest resolution image data have not been selected; and (e) end the match point generation when the highest resolution image data have been selected.
Claim 23
Dependent Claim
80 words
Apparatus in accordance with claim 18 wherein to generate a locally-adaptive volume-to-volume image transform using the generated match points, said processor is programmed to match a set of points on a cubic grid in the mask image data with corresponding match points in the opacified image data, and to determine a displacement (dx, dy, dz) to be added to each cubic grid point in the mask image data to identify coordinates of the corresponding point in the opacified image data.
References Cited (Backward Citations)
US5048103A
Cited
US5210415A
Cited
US5490221A
Cited
US5568384A
Cited
EP0599345A2
Cited
WO1994018639A1
Cited
EP0655712A2
Cited
US5839440A
Cited
US5647360A
Cited
US5690106A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2003-11-28 | 2004-05-29 | 2004-11-28 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2007-11-28 | 2008-05-29 | 2008-11-28 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2011-11-28 | 2012-05-29 | 2012-11-28 | $7700.00 | Window Closed / Lapsed |