Patent US6795521B2 successfully refreshed from Google Patents.
US6795521B2
Expired / Lapsed
US
⏱️ 0.0 years remaining
Computer-aided diagnosis system for thoracic computer tomography images
Assignee: Riverain Medical Group LLC
•
Filing: 2002-08-08
•
Granted: 2004-09-21
•
Expires: 2022-08-08
Abstract
Abstract A method of detecting and analyzing abnormalities, like lung nodules, in thoracic computer tomography (CT) images uses digital image processing techniques and adaptive computing methods. The techniques include an automatic detection process to detect candidate abnormalities, an image matching process to match CT slices from two different CT scans, and a measurement process that determines parameters of the candidate abnormalities. Final results and processed CT images are displayed on a user interface.
Inventors
- 👤 Li-Yueh Hsu
- 👤 Fleming Y.-M. Lure
- 👤 Ruiping Li
- 👤 Xin-Wei Xu
- 👤 Jyh-Shyan Lin
- 👤 Edward A. Martello
- 👤 H.-Y. Michael Yeh
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 22:04
CPC Classifications
G; G06; G06T; G06T7/00; G06T7/0002; G06T7/0012; G06T7/10; G06T7/11; G06T7/136; G06T2207/00; G06T2207/10; G06T2207/10072; G06T2207/10081; G06T2207/20; G06T2207/20112; G06T2207/20156; G06T2207/30; G06T2207/30004; G06T2207/30061; G06T2207/30064; Y; Y10; Y10S; Y10S378/00; Y10S378/901
Claims Analysis
Total Claims: 37
Claim 1
Independent Claim
106 words
A method of detecting and analyzing suspected abnormalities in thoracic computer tomography (CT) images, comprising the steps of: receiving at least first and second CT images and performing volume reformatting on the second CT image using information about the first CT image; performing object processing to segment different anatomical structures in the CT images in at least one of two-dimensional CT slices and three-dimensional CT scans, resulting in at least one segmented image; processing said at least one segmented image, said processing including at least one of image enhancement, object analysis, object detection, and image matching; and outputting at least one result of said processing step.
Claim 2
Independent Claim
106 words
A method of detecting and analyzing suspected abnormalities in thoracic computer tomography (CT) images, comprising the steps of: receiving at least first and second CT images and performing volume reformatting on the second CT image using information about the first CT image; performing object processing to segment different anatomical structures in the CT images in at least one of two-dimensional CT slices and three-dimensional CT scans, resulting in at least one segmented image; processing said at least one segmented image, said processing including at least one of image enhancement, object analysis, object detection, and image matching; and outputting at least one result of said processing step.
Claim 3
Dependent Claim
23 words
The method according to claim 1 , wherein the step of performing volume reformatting comprises at least one of volume subsampling and interpolation.
Claim 4
Dependent Claim
66 words
The method according to claim 1 , wherein the step of performing object processing comprises the steps of: performing image thresholding on at least one of said CT images; extracting at least one lung image from the at least one of said CT images based on the results of the image thresholding; and extracting at least one lung contour from said at least one lung image.
Claim 5
Dependent Claim
136 words
The method according to claim 3 , wherein the step of image thresholding comprises the steps of: constructing a gray-level histogram based on the output of the step of performing object processing; performing least squares fitting of a Gaussian curve to a low-intensity range of said histogram and selecting a background threshold based thereon; using the background threshold to eliminate low-intensity background noise from the output of the step of performing object processing; performing voxel threshold determination, comprising the steps of: generating a plurality of thresholded images using a plurality of possible thresholds; and performing a statistical correlation between each of the plurality of thresholded images and at least one original image to thereby determine a voxel threshold; and generating a voxel thresholded image by applying thresholding using the voxel threshold, thereby generating a binary image.
Claim 6
Dependent Claim
34 words
The method according to claim 3 , wherein the step of extracting at least one lung image comprises the step of: performing connected component labeling on an output of said step of image thresholding.
Claim 7
Independent Claim
149 words
A method of detecting and analyzing suspected abnormalities in thoracic computer tomography (CT) images, comprising the steps of: performing object processing to segment different anatomical structures in the CT images in at least one of two-dimensional CT slices and three-dimensional CT scans, resulting in at least one segmented image, said object processing including: performing image thresholding on at least one of said CT images; performing top- and bottom-most slices padding on the output of said step of image thresholding; extracting at least one lung image from the at least one of said CT images based on the results of the image thresholding; and extracting at least one lung contour from said at least one lung image; processing said at least one segmented image, said processing including at least one of image enhancement, object analysis, object detection, and image matching; and outputting at least one result of said processing step.
Claim 8
Independent Claim
149 words
A method of detecting and analyzing suspected abnormalities in thoracic computer tomography (CT) images, comprising the steps of: performing object processing to segment different anatomical structures in the CT images in at least one of two-dimensional CT slices and three-dimensional CT scans, resulting in at least one segmented image, said object processing including: performing image thresholding on at least one of said CT images; performing top- and bottom-most slices padding on the output of said step of image thresholding; extracting at least one lung image from the at least one of said CT images based on the results of the image thresholding; and extracting at least one lung contour from said at least one lung image; processing said at least one segmented image, said processing including at least one of image enhancement, object analysis, object detection, and image matching; and outputting at least one result of said processing step.
Claim 9
Independent Claim
168 words
A method of detecting and analyzing suspected abnormalities in thoracic computer tomography (CT) images, comprising the steps of: performing object processing to segment different anatomical structures in the CT images in at least one of two-dimensional CT slices and three-dimensional CT scans, resulting in at least one segmented image, said object processing including: performing image thresholding on at least one of said CT images; removing small objects from the at least one lung image, prior to the step of extracting at least one lung contour, wherein the step of removing small objects comprises performing reversed connected component labeling; extracting at least one lung image from the at least one of said CT images based on the results of the image thresholding; and extracting at least one lung contour from said at least one lung image; processing said at least one segmented image, said processing including at least one of image enhancement, object analysis, object detection, and image matching; and outputting at least one result of said processing step.
Claim 10
Independent Claim
168 words
A method of detecting and analyzing suspected abnormalities in thoracic computer tomography (CT) images, comprising the steps of: performing object processing to segment different anatomical structures in the CT images in at least one of two-dimensional CT slices and three-dimensional CT scans, resulting in at least one segmented image, said object processing including: performing image thresholding on at least one of said CT images; removing small objects from the at least one lung image, prior to the step of extracting at least one lung contour, wherein the step of removing small objects comprises performing reversed connected component labeling; extracting at least one lung image from the at least one of said CT images based on the results of the image thresholding; and extracting at least one lung contour from said at least one lung image; processing said at least one segmented image, said processing including at least one of image enhancement, object analysis, object detection, and image matching; and outputting at least one result of said processing step.
Claim 11
Independent Claim
147 words
A method of detecting and analyzing suspected abnormalities in thoracic computer tomography (CT) images, comprising the steps of: performing object processing to segment different anatomical structures in the CT images in at least one of two-dimensional CT slices and three-dimensional CT scans, resulting in at least one segmented image, said object processing including: performing image thresholding on at least one of said CT images; extracting at least one lung image from the at least one of said CT images based on the results of the image thresholding; and extracting at least one lung contour from said at least one lung image; smoothing the at least one lung contour using an active contour smoothing algorithm; processing said at least one segmented image, said processing including at least one of image enhancement, object analysis, object detection, and image matching; and outputting at least one result of said processing step.
Claim 12
Independent Claim
147 words
A method of detecting and analyzing suspected abnormalities in thoracic computer tomography (CT) images, comprising the steps of: performing object processing to segment different anatomical structures in the CT images in at least one of two-dimensional CT slices and three-dimensional CT scans, resulting in at least one segmented image, said object processing including: performing image thresholding on at least one of said CT images; extracting at least one lung image from the at least one of said CT images based on the results of the image thresholding; and extracting at least one lung contour from said at least one lung image; smoothing the at least one lung contour using an active contour smoothing algorithm; processing said at least one segmented image, said processing including at least one of image enhancement, object analysis, object detection, and image matching; and outputting at least one result of said processing step.
Claim 13
Dependent Claim
17 words
The method according to claim 8 , wherein the active contour smoothing algorithm is a snake algorithm.
Claim 14
Independent Claim
98 words
A method of detecting and analyzing suspected abnormalities in thoracic computer tomography (CD images, comprising the steps of: performing object processing to segment different anatomical structures in the CT images in at least one of two-dimensional CT slices and three-dimensional CT scans, resulting in at least one segmented image; processing said at least one segmented image, said processing including image enhancement, including at least one step of histogram window leveling performed on the at least one segmented image; and outputting at least one result of said processing step, wherein the at least one result include an enhanced image.
Claim 15
Independent Claim
98 words
A method of detecting and analyzing suspected abnormalities in thoracic computer tomography (CD images, comprising the steps of: performing object processing to segment different anatomical structures in the CT images in at least one of two-dimensional CT slices and three-dimensional CT scans, resulting in at least one segmented image; processing said at least one segmented image, said processing including image enhancement, including at least one step of histogram window leveling performed on the at least one segmented image; and outputting at least one result of said processing step, wherein the at least one result include an enhanced image.
Claim 16
Dependent Claim
57 words
The method according to claim 10 , wherein said at least one step of histogram window leveling comprises the steps of: lung area histogram window leveling; and mediastinum area histogram window leveling; and wherein the results of the steps of lung area histogram window leveling and mediastinum area window leveling are combined to produce an output image.
Claim 17
Dependent Claim
35 words
The method according to claim 13 , wherein the step of object analysis includes analysis of at least one of sphericity, size, HU value, and a vessel/nodule tree in the at least one segmented image.
Claim 18
Independent Claim
163 words
A method of detecting and analyzing suspected abnormalities in thoracic computer tomography (CT) images, comprising the steps of: performing object processing to segment different anatomical structures in the CT images in at least one of two-dimensional CT slices and three-dimensional CT scans, resulting in at least one segmented image; processing said at least one segmented image, said processing including object analysis, said object analysis comprising: computing a seed position for a consecutive measurement process; performing gray-level thresholding on the at least one segmented image; performing morphological shape processing on the output of said gray-level thresholding; performing connected component labeling on the output of said morphological shape processing; adjusting contours obtained in said connected component labeling; reconstructing at least one three-dimensional object based on the adjusted contours; and performing measurements on the at least one three-dimensional object; and outputting at least one result of said processing step, the at least one result comprising at least one of an image, a feature, or a measurement.
Claim 19
Independent Claim
163 words
A method of detecting and analyzing suspected abnormalities in thoracic computer tomography (CT) images, comprising the steps of: performing object processing to segment different anatomical structures in the CT images in at least one of two-dimensional CT slices and three-dimensional CT scans, resulting in at least one segmented image; processing said at least one segmented image, said processing including object analysis, said object analysis comprising: computing a seed position for a consecutive measurement process; performing gray-level thresholding on the at least one segmented image; performing morphological shape processing on the output of said gray-level thresholding; performing connected component labeling on the output of said morphological shape processing; adjusting contours obtained in said connected component labeling; reconstructing at least one three-dimensional object based on the adjusted contours; and performing measurements on the at least one three-dimensional object; and outputting at least one result of said processing step, the at least one result comprising at least one of an image, a feature, or a measurement.
Claim 20
Dependent Claim
30 words
The method according to claim 13 , wherein the step of computing a seed position comprises the step of: determining a center of gravity from a predefined local image window.
Claim 21
Dependent Claim
21 words
The method according to claim 13 , wherein the step of adjusting contours comprises the step of: performing neighbor profile tracing.
Claim 22
Dependent Claim
42 words
The method according to claim 1 , wherein the step of processing comprises a step of object detection, and wherein the at least one result output in the outputting step comprises at least one of an image, a feature, and a measurement.
Claim 23
Dependent Claim
29 words
The method according to claim 16 , wherein the step of object detection includes at least one of image enhancement, initial selection, three-dimensional object grouping, feature extraction, and classification.
Claim 24
Dependent Claim
74 words
The method according to claim 16 , wherein the step of object detection comprises the steps of: filtering an input image; performing gray-level thresholding on the filtered input image; making an initial nodule selection based on the output of the gray-level thresholding; extracting features based on the output of the initial nodule selection; and classifying objects determined in the step of initial nodule selection using the features extracted in the step of extracting features.
Claim 25
Dependent Claim
25 words
The method according to claim 18 , wherein the step of filtering comprises the step of: performing enhancement filtering for matching a nodule's intensity profile.
Claim 26
Dependent Claim
37 words
The method according to claim 18 , wherein the step of classifying objects comprises the step of: analyzing relationships between features arising at different threshold levels with respect to at least one of size, shape, and location.
Claim 27
Independent Claim
102 words
A method of detecting and analyzing suspected abnormalities in thoracic computer tomography (CT) images, comprising the steps of: performing object processing to segment different anatomical structures in the CT images in at least one of two-dimensional CT slices and three-dimensional CT scans, resulting in at least one segmented image; processing said at least one segmented image, said processing including: object analysis performed on the output of said object processing; and measuring doubling time based on results of said object analysis; and outputting at least one result of said processing step, wherein the at least one result comprises a measurement of doubling time.
Claim 28
Independent Claim
102 words
A method of detecting and analyzing suspected abnormalities in thoracic computer tomography (CT) images, comprising the steps of: performing object processing to segment different anatomical structures in the CT images in at least one of two-dimensional CT slices and three-dimensional CT scans, resulting in at least one segmented image; processing said at least one segmented image, said processing including: object analysis performed on the output of said object processing; and measuring doubling time based on results of said object analysis; and outputting at least one result of said processing step, wherein the at least one result comprises a measurement of doubling time.
Claim 29
Dependent Claim
78 words
The method according to claim 21 , wherein the step of measuring doubling time comprises the step of: calculating doubling time based on at least two time-differenced CT scans. 23 .The method according to claim 1 , wherein the step of processing comprises a step of image matching based on the output of said object processing, and wherein the at least one result output in the outputting step comprises at least one of an image and a measurement.
Claim 30
Independent Claim
124 words
A method of detecting and analyzing suspected abnormalities in thoracic computer tomography (CT) images, comprising the steps of: performing object processing to segment different anatomical structures in the CT images in at least one of two-dimensional CT slices and three-dimensional CT scans, resulting in at least one segmented image; processing said at least one segmented image, said processing including image matching based on an output of said object processing, wherein said image matching includes at least one of slice matching, volume matching, or slice warping, and wherein said image matching involves results obtained from at least two CT images; and outputting at least one result of said processing step, said at least one result comprising at least one of an image or a measurement.
Claim 31
Independent Claim
124 words
A method of detecting and analyzing suspected abnormalities in thoracic computer tomography (CT) images, comprising the steps of: performing object processing to segment different anatomical structures in the CT images in at least one of two-dimensional CT slices and three-dimensional CT scans, resulting in at least one segmented image; processing said at least one segmented image, said processing including image matching based on an output of said object processing, wherein said image matching includes at least one of slice matching, volume matching, or slice warping, and wherein said image matching involves results obtained from at least two CT images; and outputting at least one result of said processing step, said at least one result comprising at least one of an image or a measurement.
Claim 32
Dependent Claim
66 words
The method according to claim 24 , wherein the step of processing comprises a step of slice matching, and wherein the step of slice matching comprises the steps of: generating a curve from two-dimensional features in each CT image; computing a gradient for each curve; correlating gradients of the curves; and determining a shift distance in one CT image with respect to the other CT image.
Claim 33
Independent Claim
161 words
A method of detecting and analyzing suspected abnormalities in thoracic computer tomography (CT) images, comprising the steps of: performing object processing to segment different anatomical structures in the CT images in at least one of two-dimensional CT slices and three-dimensional CT scans, resulting in at least one segmented image; processing said at least one segmented image, said processing including image matching based on an output of said object processing, said image matching comprising: inputting the outputs of said object processing corresponding to two CT images obtained at different times; computing a lung area curve for each of the CT images; fitting the two lung area curves thus computed to each other; registering lung surface volume based on the results of the step of fitting; and warping one of the CT images to the other CT image; and outputting at least one result of said processing step, said at least one result comprising at least one of an image or a measurement.
Claim 34
Independent Claim
161 words
A method of detecting and analyzing suspected abnormalities in thoracic computer tomography (CT) images, comprising the steps of: performing object processing to segment different anatomical structures in the CT images in at least one of two-dimensional CT slices and three-dimensional CT scans, resulting in at least one segmented image; processing said at least one segmented image, said processing including image matching based on an output of said object processing, said image matching comprising: inputting the outputs of said object processing corresponding to two CT images obtained at different times; computing a lung area curve for each of the CT images; fitting the two lung area curves thus computed to each other; registering lung surface volume based on the results of the step of fitting; and warping one of the CT images to the other CT image; and outputting at least one result of said processing step, said at least one result comprising at least one of an image or a measurement.
Claim 35
Dependent Claim
34 words
The method according to claim 26 , wherein the step of fitting the two lung area curves comprises the step of: comparing the two lung area curves to minimize a sum of squared differences.
Claim 36
Dependent Claim
41 words
The method according to claim 26 , wherein the step of registering lung surface volume comprises the step of: using an iterative closest point algorithm to determine a transformation by which to transform one CT image onto the other CT image.
Claim 37
Dependent Claim
36 words
The method according to claim 28 , wherein said step of warping comprises the step of: transforming the one CT image onto the other CT image using the transformation determined using the iterative closest point algorithm.
References Cited (Backward Citations)
US5359513A
Cited
US5633951A
Cited
US5871018A
Cited
US5946425A
Cited
US6078680A
Cited
US6067373A
Cited
US6240201B1
Cited
US6470092B1
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2007-09-21 | 2008-03-22 | 2008-09-21 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2011-09-21 | 2012-03-22 | 2012-09-21 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2015-09-21 | 2016-03-22 | 2016-09-21 | $7700.00 | Window Closed / Lapsed |