US20030174872A1
Expired / Lapsed
US
⏱️ 0.0 years remaining
System and method for mining quantitive information from medical images
Assignee: Cloud Software Group Inc
•
Filing: 2002-10-15
•
Granted: —
•
Expires: 2022-10-15
Abstract
Abstract A system for image registration and quantitative feature extraction for multiple image sets. The system includes an imaging workstation having a data processor and memory in communication with a database server in communication. The a data processor capable of inputting and outputting data and instructions to peripheral devices and operating pursuant to a software product and accepts instructions from a graphical user interface capable of interfacing with and navigating the imaging software product. The imaging software product is capable of instructing the data processor, to register images, segment images and to extract features from images and provide instructions to store and retrieve one or more registered images, segmented images, quantitative image features and quantitative image data and from the database server.
Inventors
- 👤 Vikram Chalana
- 👤 Stephen Fogarasi
- 👤 Lydia Ng
- 👤 John Oelund
- 👤 Sayan Pathak
- 👤 Steven Racki
- 👤 Bobbi Sparks
- 👤 Bradley Wyman
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 21:43
CPC Classifications
G; G16; G16H; G16H50/00; G16H50/70; G16Z; G16Z99/00; G06; G06V; G06V2201/00; G06V2201/03
Claims Analysis
Total Claims: 55
Claim 1
Independent Claim
121 words
1 . A system for image registration and quantitative feature extraction from the images, the system comprising: an imaging workstation; and a database server in communication with the imaging workstation, wherein the imaging workstation includes: a data processor with memory capable of inputting and outputting data and instructions to peripheral devices; a graphical user interface capable of interfacing with and navigating an imaging software product, wherein the imaging software product is capable of instructing the data processor, the imaging software product comprises: instructions to register images; instructions to segment images; instructions to extract features from images; and instructions to store and retrieve one or more registered images, segmented images, quantitative image features and quantitative image data and from the database server.
Claim 2
Dependent Claim
121 words
1 . A system for image registration and quantitative feature extraction from the images, the system comprising: an imaging workstation; and a database server in communication with the imaging workstation, wherein the imaging workstation includes: a data processor with memory capable of inputting and outputting data and instructions to peripheral devices; a graphical user interface capable of interfacing with and navigating an imaging software product, wherein the imaging software product is capable of instructing the data processor, the imaging software product comprises: instructions to register images; instructions to segment images; instructions to extract features from images; and instructions to store and retrieve one or more registered images, segmented images, quantitative image features and quantitative image data and from the database server.
Claim 3
Dependent Claim
22 words
2 . The system of claim 1 , wherein the software product further includes instructions to perform queries on the database server.
Claim 4
Dependent Claim
20 words
3 . The system of claim 1 , wherein the software product further comprises instructions to perform multi-modality image registration.
Claim 5
Dependent Claim
20 words
4 . The system of claim 1 , wherein the software product further includes instructions to perform multi-channel region segmentation.
Claim 6
Dependent Claim
19 words
5 . The system of claim 1 , wherein the software product further includes instructions to perform shape-based interpolation.
Claim 7
Dependent Claim
17 words
6 . The system of claim 1 , wherein the quantitative image data further includes serial/longitudinal data.
Claim 8
Dependent Claim
20 words
7 . The system of claim 6 , wherein the quantitative image data is extracted from 2D and 3D images.
Claim 9
Dependent Claim
20 words
8 . The system of claim 1 , wherein the quantitative image data is extracted from 2D and 3D images.
Claim 10
Dependent Claim
27 words
9 . The system of claim 5 , wherein the shaped-based interpolation is modified to perform a regional adjustment of the contour based on the image properties.
Claim 11
Dependent Claim
21 words
10 . The system of claim 1 , wherein the software product further includes instructions to fuse information from multiple modalities.
Claim 12
Dependent Claim
34 words
11 . The system of claim 1 , wherein the software product further includes instructions to display segmented images as one of translucent regions and boundaries as an overlay on top of an image.
Claim 13
Dependent Claim
20 words
12 . The system of claim 11 , wherein the degree of translucency of the regions and boundaries is adjustable.
Claim 14
Dependent Claim
18 words
13 . The system of claim 1 , that further includes capabilities for generating and storing audit trails.
Claim 15
Dependent Claim
105 words
14 . The system of claim 1 , wherein the software product further comprises instructions to: select an initial contour of a structure in an image set; identify each vertex of an initial contour; identify radial lines normal to each vertex of the initial contour, wherein the initial contour is restricted to move only along the radial lines; sample the image set along the radial lines; compute one-dimensional derivatives of the structure along the radial lines; and iteratively adjust positioning of the initial contour on the radial line and calculating total energy, wherein the initial contour is adjusted such that the total energy is minimized.
Claim 16
Dependent Claim
31 words
15 . The system of claim 14 , wherein the total energy is defined by E ( v )=Σ(α∥ v S ∥ 2 +β∥v SS ∥ 2 +λg ( v )).
Claim 17
Dependent Claim
27 words
16 . The system of claim 14 , wherein a final radial representation of the contour is converted back to a Cartesian-coordinate for presentation to the user.
Claim 18
Dependent Claim
112 words
17 . The system of claim 9 , wherein the regional adjustment of the contour based on the local image properties further comprises select an initial contour of a structure in an image set, identify each vertex of an initial contour, identify radial lines normal to each vertex of the initial contour, wherein the initial contour is restricted to move only along the radial lines, sample the image set along the radial lines, compute one-dimensional derivatives of the structure along the radial lines, and iteratively adjust positioning of the initial contour on the radial line and calculating total energy, wherein the initial contour is adjusted such that the total energy is minimized.
Claim 19
Dependent Claim
43 words
18 . The system of claim 1 , wherein the graphical user interface permits viewing of an arbitrary number of images in a grid by clicking and dragging a grid layout tool that shows a grid layout of the images to be displayed.
Claim 20
Dependent Claim
168 words
19 . A computer implemented method for performing a study on image data using a image analysis system having an imaging workstation, a database server in communication with the imaging workstation, wherein the imaging workstation includes a data processor with memory capable of inputting and outputting data and instructions to peripheral devices and a graphical user interface capable of interfacing with and navigating an imaging software product, wherein the imaging software product is capable of instructing the data processor, the method comprising: importing one or more image sequences from the database server for a one or more patients involved in the study; registering the images to align the different image sequences with one of each other and to a baseline image set; performing segmentation to find one or more objects of interest in the entire image sequence; performing feature extraction to determine quantitative information about the objects of interest; and storing the objects of interest and the quantitative information about the objects of interest in the database server.
Claim 21
Dependent Claim
168 words
19 . A computer implemented method for performing a study on image data using a image analysis system having an imaging workstation, a database server in communication with the imaging workstation, wherein the imaging workstation includes a data processor with memory capable of inputting and outputting data and instructions to peripheral devices and a graphical user interface capable of interfacing with and navigating an imaging software product, wherein the imaging software product is capable of instructing the data processor, the method comprising: importing one or more image sequences from the database server for a one or more patients involved in the study; registering the images to align the different image sequences with one of each other and to a baseline image set; performing segmentation to find one or more objects of interest in the entire image sequence; performing feature extraction to determine quantitative information about the objects of interest; and storing the objects of interest and the quantitative information about the objects of interest in the database server.
Claim 22
Dependent Claim
22 words
20 . The method of claim 19 further comprises performing a regional adjustment of the contour based on the local image characteristics.
Claim 23
Dependent Claim
17 words
21 . The method of claim 19 , wherein the quantitative image data further includes serial/longitudinal data.
Claim 24
Dependent Claim
20 words
22 . The method of claim 21 , wherein the quantitative image data is extracted from 2D and 3D images.
Claim 25
Dependent Claim
20 words
23 . The method of claim 19 , wherein the quantitative image data is extracted from 2D and 3D images.
Claim 26
Dependent Claim
14 words
24 . The method of claim 19 further comprising fusing information from multiple modalities.
Claim 27
Dependent Claim
27 words
25 . The method of claim 19 further comprising displaying segmented images as one of translucent regions and boundaries as an overlay on top of an image.
Claim 28
Dependent Claim
32 words
26 . The method of claim 25 further comprising the ability to vary the translucency of the regions and boundaries between a range or subset of a range from opaque to transparent.
Claim 29
Dependent Claim
103 words
27 . The method of claim 20 , wherein the regional adjustment further comprising: selecting an initial contour of a structure in an image set; identifying each vertex of the initial contour; identifying radial lines normal to each vertex of the initial contour, wherein the initial contour is restricted to move only along the radial lines; sampling the image set along the radial lines; computing one-dimensional derivatives of the structure along the radial lines; and iteratively adjusting positioning of the initial contour on the radial line and calculating total energy, wherein the initial contour is adjusted such that the total energy is minimized.
Claim 30
Dependent Claim
31 words
28 . The method of claim 27 , wherein the total energy is defined by E ( v )=Σ(α∥ v S ∥ 2 +β∥v SS ∥ 2 +λg ( v )).
Claim 31
Dependent Claim
27 words
29 . The method of claim 27 , wherein a final radial representation of the contour is converted back to a Cartesian-coordinate for presentation to the user.
Claim 32
Dependent Claim
30 words
30 . The method of claim 27 , wherein selecting the initial contour comprises one of the following: manual painting, polygon drawing, seed-fill, live-wire, multi-channel segmentation and single channel segmentation.
Claim 33
Dependent Claim
20 words
31 . The system of claim 19 further comprising storing audit data associated with the images in the database server.
Claim 34
Dependent Claim
127 words
32 . An image analysis system, comprising: an imaging workstation; a database server in communication with the imaging workstation; wherein the imaging workstation includes a data processor with memory capable of inputting and outputting data and instructions to peripheral devices and a graphical user interface capable of interfacing with and navigating an imaging software product, wherein the imaging software product is capable of instructing the data processor, the imaging software product comprises: instructions to store and retrieve one or more registered images, segmented images, quantitative image features and quantitative image data and from the database server; and instructions to store audit data in the database server that tracks the use and changes of the registered images, the segmented images, the quantitative image features and quantitative image data.
Claim 35
Dependent Claim
127 words
32 . An image analysis system, comprising: an imaging workstation; a database server in communication with the imaging workstation; wherein the imaging workstation includes a data processor with memory capable of inputting and outputting data and instructions to peripheral devices and a graphical user interface capable of interfacing with and navigating an imaging software product, wherein the imaging software product is capable of instructing the data processor, the imaging software product comprises: instructions to store and retrieve one or more registered images, segmented images, quantitative image features and quantitative image data and from the database server; and instructions to store audit data in the database server that tracks the use and changes of the registered images, the segmented images, the quantitative image features and quantitative image data.
Claim 36
Dependent Claim
103 words
33 . A method for segmenting images from a sequence of images, comprising: performing seeded region growing to generate a segmented region on one or more images and one or more regions of interest, the seeded region growing further comprising identifying a point within a region to be segmented on a particular image and identifying pixels surrounding the point having a similar intensity range; and performing shaped based interpolation that further comprises identifying the segmented region(s) identified during the seeded region growing on the other images in the sequence of images to segment the identified region(s) in all of the sequence of images.
Claim 37
Dependent Claim
103 words
33 . A method for segmenting images from a sequence of images, comprising: performing seeded region growing to generate a segmented region on one or more images and one or more regions of interest, the seeded region growing further comprising identifying a point within a region to be segmented on a particular image and identifying pixels surrounding the point having a similar intensity range; and performing shaped based interpolation that further comprises identifying the segmented region(s) identified during the seeded region growing on the other images in the sequence of images to segment the identified region(s) in all of the sequence of images.
Claim 38
Dependent Claim
177 words
34 . A method for segmenting images from a sequence of images, comprising: determining an initial contour for a segmented region in an image; performing shaped based interpolation that further comprises identifying the segmented region identified from the image for the other images in the sequence of images to segment the segmented region in all of the sequence of images; and performing snake segmentation on segmented regions in the sequence of images to generate a refined segmented region for the sequence of images, the snake segmentation further comprising selecting an initial contour of a structure in an image set; identifying each vertex of the initial contour; identifying radial lines normal to each vertex of the initial contour, wherein the initial contour is restricted to move only along the radial lines; sampling the image set along the radial lines; computing one-dimensional derivatives of the structure along the radial lines; and iteratively adjusting positioning of the initial contour on the radial line and calculating total energy, wherein the initial contour is adjusted such that the total energy is minimized.
Claim 39
Dependent Claim
177 words
34 . A method for segmenting images from a sequence of images, comprising: determining an initial contour for a segmented region in an image; performing shaped based interpolation that further comprises identifying the segmented region identified from the image for the other images in the sequence of images to segment the segmented region in all of the sequence of images; and performing snake segmentation on segmented regions in the sequence of images to generate a refined segmented region for the sequence of images, the snake segmentation further comprising selecting an initial contour of a structure in an image set; identifying each vertex of the initial contour; identifying radial lines normal to each vertex of the initial contour, wherein the initial contour is restricted to move only along the radial lines; sampling the image set along the radial lines; computing one-dimensional derivatives of the structure along the radial lines; and iteratively adjusting positioning of the initial contour on the radial line and calculating total energy, wherein the initial contour is adjusted such that the total energy is minimized.
Claim 40
Dependent Claim
31 words
35 . The method of claim 34 , wherein the total energy is defined by E ( v )=Σ(α∥ v S ∥ 2 +β∥v SS ∥ 2 +λg ( v )).
Claim 41
Dependent Claim
27 words
36 . The method of claim 34 , wherein a final radial representation of the contour is converted back to a Cartesian-coordinate for presentation to the user.
Claim 42
Dependent Claim
28 words
37 . The method of claim 34 , wherein determining the initial contour is one of the following: manual painting, polygon drawing, seed-fill, live-wire, multi- or single-channel segmentation.
Claim 43
Dependent Claim
32 words
38 . The method of claim 34 , wherein the method of identifying the initial contour is from using the contours identified on another image series for the same patient or subject.
Claim 44
Dependent Claim
23 words
39 . The method of claim 34 , wherein the method of identifying the initial contour is from a template or reference image.
Claim 45
Dependent Claim
148 words
40 . A method for segmenting images from a sequence of images, comprising: generating a segmented image from a reference image; determining registration between the reference image and a new image to generate a new image segmentation; performing snake segmentation on the new image segmentation to generate a segmented region within the particular image, the snake segmentation further comprising selecting an initial contour of a structure in an image set; identifying each vertex of the initial contour; identifying radial lines normal to each vertex of the initial contour, wherein the initial contour is restricted to move only along the radial lines; sampling the image set along the radial lines; computing one-dimensional derivatives of the structure along the radial lines; and iteratively adjusting positioning of the initial contour on the radial line and calculating total energy, wherein the initial contour is adjusted such that the total energy is minimized.
Claim 46
Dependent Claim
148 words
40 . A method for segmenting images from a sequence of images, comprising: generating a segmented image from a reference image; determining registration between the reference image and a new image to generate a new image segmentation; performing snake segmentation on the new image segmentation to generate a segmented region within the particular image, the snake segmentation further comprising selecting an initial contour of a structure in an image set; identifying each vertex of the initial contour; identifying radial lines normal to each vertex of the initial contour, wherein the initial contour is restricted to move only along the radial lines; sampling the image set along the radial lines; computing one-dimensional derivatives of the structure along the radial lines; and iteratively adjusting positioning of the initial contour on the radial line and calculating total energy, wherein the initial contour is adjusted such that the total energy is minimized.
Claim 47
Dependent Claim
73 words
41 . A method for segmenting images from a sequence of images, comprising: performing seed region segmentation to generate a segmented region within the particular image, the seed region segmentation further comprising identifying a point within a region to be segmented on a particular image and identifying pixels surrounding the point having a predetermined intensity; and performing multi-channel segmentation in order to segment the segmented region from each image in an image set.
Claim 48
Dependent Claim
73 words
41 . A method for segmenting images from a sequence of images, comprising: performing seed region segmentation to generate a segmented region within the particular image, the seed region segmentation further comprising identifying a point within a region to be segmented on a particular image and identifying pixels surrounding the point having a predetermined intensity; and performing multi-channel segmentation in order to segment the segmented region from each image in an image set.
Claim 49
Dependent Claim
145 words
42 . A method for segmenting images from a sequence of images, comprising: determining an initial contour for a segmented region in an image, the initial contour being determined a segmentation tool; and performing snake segmentation on segmented region of the image to generate a refined segmented region for the image, the snake segmentation further comprising selecting an initial contour of a structure in an image set; identifying each vertex of the initial contour; identifying radial lines normal to each vertex of the initial contour, wherein the initial contour is restricted to move only along the radial lines; sampling the image set along the radial lines; computing one-dimensional derivatives of the structure along the radial lines; and iteratively adjusting positioning of the initial contour on the radial line and calculating total energy, wherein the initial contour is adjusted such that the total energy is minimized.
Claim 50
Dependent Claim
145 words
42 . A method for segmenting images from a sequence of images, comprising: determining an initial contour for a segmented region in an image, the initial contour being determined a segmentation tool; and performing snake segmentation on segmented region of the image to generate a refined segmented region for the image, the snake segmentation further comprising selecting an initial contour of a structure in an image set; identifying each vertex of the initial contour; identifying radial lines normal to each vertex of the initial contour, wherein the initial contour is restricted to move only along the radial lines; sampling the image set along the radial lines; computing one-dimensional derivatives of the structure along the radial lines; and iteratively adjusting positioning of the initial contour on the radial line and calculating total energy, wherein the initial contour is adjusted such that the total energy is minimized.
Claim 51
Dependent Claim
31 words
43 . The method of claim 42 , wherein the total energy is defined by E ( v )=Σ(α∥ v S ∥ 2 +β∥V SS ∥ 2 +λg ( v )).
Claim 52
Dependent Claim
27 words
44 . The method of claim 43 , wherein a final radial representation of the contour is converted back to a Cartesian-coordinate for presentation to the user.
Claim 53
Dependent Claim
28 words
45 . The method of claim 42 , wherein the segmentation tool comprises one or more of manual painting, polygon drawing, seed-fill, live-wire, multi-channel segmentation and single-channel segmentation.
Claim 54
Dependent Claim
32 words
46 . The method of claim 42 , wherein the method of identifying the initial contour is from using the contours identified on another image series for the same patient or subject.
Claim 55
Dependent Claim
23 words
47 . The method of claim 42 , wherein the method of identifying the initial contour is from a template or reference image.
References Cited (Backward Citations)
US5970499A
Cited
US6430430B1
Cited
USPTO Annuity & Maintenance Windows
Maintenance schedule is calculated for granted US utility patents.