Patent US6909797B2 successfully refreshed from Google Patents.
US6909797B2
Expired / Lapsed
US
⏱️ 0.0 years remaining
Density nodule detection in 3-D digital images
Assignee: Mevis Medical Solutions AG
•
Filing: 2001-11-23
•
Granted: 2005-06-21
•
Expires: 2021-11-23
Abstract
Abstract An algorithm is quickly scans a digital image volume to detect density nodules. A first stage is based on a transform to quickly highlight regions requiring further processing. The first stage operates with somewhat lower sensitivity than is possible with more detailed analyses, but operates to highlight regions for further analysis and processing. The transform dynamically adapts to various nodule sizes through the use of radial zones. A second stage uses a detailed gradient distribution analysis that only operates on voxels that pass a threshold of the first stage.
Inventors
- 👤 Harlan M. Romsdahl
- 👤 Wei Zhang
- 👤 Alexander C. Schneider
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 21:57
CPC Classifications
G; G06; G06F; G06F3/00; G06F3/01; G06F3/048; G06F3/0481; A; A61; A61B; A61B6/00; A61B6/02; A61B6/03; A61B6/032; A61B6/46; A61B6/461; A61B6/466; G06F3/0484; G06F3/0485; G06F3/04855; G06T; G06T15/00; G06T15/08; G06T7/00; G06T7/0002; G06T7/0012; G06V; G06V10/00; G06V10/20; G06V10/25; G06V10/36; G06V10/40; G06V10/44; G06V10/457; A61B6/50; A61B6/502; G06F2203/00; G06F2203/048; G06F2203/04805; G06V2201/00; G06V2201/03
Claims Analysis
Total Claims: 30
Claim 1
Independent Claim
136 words
A method of determining regions of interest in an image that is an array of image elements comprising the steps of: at each image element in the image, determining if the image element contains an edge and determining a gradient of the edge, if any; generating a cumulative array of cells that identifies regions of interest in the image by: at each image element in the image that contains an edge, using the gradient to define a region in the cumulative array in a direction specified by said gradient, and at each cell in the cumulative array within the region defined with the gradient, incrementing a numerical value associated with the cell; and identifying regions of interest in the image by identifying those cells in the cumulative array that have numerical values that are local extrema.
Claim 2
Independent Claim
136 words
A method of determining regions of interest in an image that is an array of image elements comprising the steps of: at each image element in the image, determining if the image element contains an edge and determining a gradient of the edge, if any; generating a cumulative array of cells that identifies regions of interest in the image by: at each image element in the image that contains an edge, using the gradient to define a region in the cumulative array in a direction specified by said gradient, and at each cell in the cumulative array within the region defined with the gradient, incrementing a numerical value associated with the cell; and identifying regions of interest in the image by identifying those cells in the cumulative array that have numerical values that are local extrema.
Claim 3
Dependent Claim
29 words
The method of claim 1 further comprising the step of thresholding the cumulative array to identify regions of interest near locations where said cumulative array exceeds a threshold value.
Claim 4
Dependent Claim
49 words
The method of claim 1 wherein the step of determining the gradient comprises determining a gradient intensity value and a gradient direction value; and the step of using the gradient to define a region of interest uses the gradient intensity value and gradient direction value of the image elements.
Claim 5
Dependent Claim
43 words
The method of claim 3 wherein, for each region defined in the cumulative array, each cell in the cumulative array within that region is incremented by a numerical value corresponding to the gradient intensity value for the image element associated with that region.
Claim 6
Dependent Claim
33 words
The method of claim 1 wherein the region in the cumulative array is spaced from a projection of the image element onto the cumulative array and is aligned with the gradient direction value.
Claim 7
Dependent Claim
30 words
The method of claim 5 wherein the region extends from a first radial distance to a second radial distance from the projection of the image element onto the cumulative array.
Claim 8
Dependent Claim
45 words
The method of claim 1 wherein the region in the cumulative array is a volume extending from a first radial distance to a second radial distance from the projection of the image element onto the cumulative array and bounded by lines radiating from said projection.
Claim 9
Dependent Claim
12 words
The method of claim 1 wherein each image element is a voxel.
Claim 10
Dependent Claim
14 words
The method of claim 1 wherein the edge is detected by a Sobel operator.
Claim 11
Dependent Claim
14 words
The method of claim 1 wherein the region of interest is a lung nodule.
Claim 12
Independent Claim
98 words
A method of detecting regions of interest in an image composed of volume elements (voxels) comprising the steps of: calculating gradient vectors for voxels having edges, each said vector having a magnitude and a direction; applying a transform to the gradient vectors to create a transform output; classifying the transform output into output regions by projecting the transform output onto a cumulative array using the vector magnitudes and directions; accumulating the transform output as numerical values in the cumulative array; and processing the cumulative array to detect regions of interest by identifying numerical values that are local extrema.
Claim 13
Independent Claim
98 words
A method of detecting regions of interest in an image composed of volume elements (voxels) comprising the steps of: calculating gradient vectors for voxels having edges, each said vector having a magnitude and a direction; applying a transform to the gradient vectors to create a transform output; classifying the transform output into output regions by projecting the transform output onto a cumulative array using the vector magnitudes and directions; accumulating the transform output as numerical values in the cumulative array; and processing the cumulative array to detect regions of interest by identifying numerical values that are local extrema.
Claim 14
Dependent Claim
25 words
The method of claim 11 wherein the step of calculating gradient vectors is performed for a voxel in a window of interest of the image.
Claim 15
Dependent Claim
14 words
The method of claim 11 further including the step of initializing the cumulative array.
Claim 16
Dependent Claim
18 words
The method of claim 11 wherein the output regions represent a range of probabilities concerning the vector directions.
Claim 17
Dependent Claim
18 words
The method of claim 11 wherein substantially every voxel is examined to determine if it contains an edge.
Claim 18
Dependent Claim
29 words
The method of claim 11 wherein the step of accumulating the transform output comprises the step of accumulating in the cumulative array the transform output for each gradient vector.
Claim 19
Dependent Claim
34 words
The method of claim 11 wherein the cumulative array is incremented at array locations defined by a predetermined pattern extending from a voxel in the direction of the gradient vector calculated for that voxel.
Claim 20
Dependent Claim
37 words
The method of claim 17 wherein the predetermined pattern subtends an angle at the projection of the voxel onto the cumulative array and extends between a first radial distance and a second radial distance from said projection.
Claim 21
Dependent Claim
27 words
The method of claim 18 wherein the first radial distance and the second radial distance are selected according to the size of a desired region of interest.
Claim 22
Dependent Claim
35 words
The method of claim 11 wherein the step of accumulating the transform output comprises the step of incrementing by a first amount cells in the cumulative array within a volume oriented by the gradient vector.
Claim 23
Independent Claim
136 words
A method of determining regions of interest in an image that is an array of image elements comprising the steps of: at each image element in the image, determining if the image element contains a line and determining a direction of the line, if any; generating a cumulative array of cells that identifies regions of interest in the image by: at each image element in the image that contains a line, using the direction of the line to define a region in the cumulative array having an orientation specified by said direction, and at each cell in the cumulative array within the defined region, incrementing a numerical value associated with the cell; and identifying regions of interest in the image by identifying those cells in the cumulative array that have numerical values that are local extrema.
Claim 24
Independent Claim
136 words
A method of determining regions of interest in an image that is an array of image elements comprising the steps of: at each image element in the image, determining if the image element contains a line and determining a direction of the line, if any; generating a cumulative array of cells that identifies regions of interest in the image by: at each image element in the image that contains a line, using the direction of the line to define a region in the cumulative array having an orientation specified by said direction, and at each cell in the cumulative array within the defined region, incrementing a numerical value associated with the cell; and identifying regions of interest in the image by identifying those cells in the cumulative array that have numerical values that are local extrema.
Claim 25
Dependent Claim
29 words
The method of claim 21 further comprising the step of thresholding the cumulative array to identify regions of interest near locations where said cumulative array exceeds a threshold value.
Claim 26
Dependent Claim
34 words
The method of claim 21 wherein the region in the cumulative array is spaced from a projection of the image element onto the cumulative array and is aligned with the direction of the line.
Claim 27
Dependent Claim
30 words
The method of claim 23 wherein the region extends from a first radial distance to a second radial distance from the projection of the image element onto the cumulative array.
Claim 28
Dependent Claim
45 words
The method of claim 21 wherein the region in the cumulative array is a volume extending from a first radial distance to a second radial distance from the projection of the image element onto the cumulative array and bounded by lines radiating from said projection.
Claim 29
Dependent Claim
12 words
The method of claim 21 wherein each image element is a voxel.
Claim 30
Dependent Claim
14 words
The method of claim 21 wherein the region of interest is a spiculated mass.
References Cited (Backward Citations)
US6327377B1
Cited
US5231580A
Cited
US5889881A
Cited
US5656818A
Cited
US5832103A
Cited
US5937083A
Cited
US5815591A
Cited
US6198838B1
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2008-06-20 | 2008-12-20 | 2009-06-21 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2012-06-20 | 2012-12-20 | 2013-06-21 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2016-06-20 | 2016-12-20 | 2017-06-21 | $7700.00 | Window Closed / Lapsed |