Apparatus and method for identifying specific bone regions in digital X-ray images

• US 5,696,805 A
• Filed: 09/17/1996
• Issued: 12/09/1997
• Est. Priority Date: 09/17/1996
• Status: Expired due to Fees

• Current Assignee: CareStream Health Incorporated
• Original Assignee: Eastman Kodak Company
• Inventors: Pawlicki, Thaddeus Francis, Gaborski, Roger Stephen
• Primary Examiner(s): Porta, David P.
• Assistant Examiner(s): Bruce, David Vernon
• Application Number:
  US08/713,683
• Time in Patent Office: 448 Days
• Field of Search: 378/54, 378/55, 378/56
• US Class Current: 378/54
• CPC Class Codes: G01N 23/04 and forming images of the material
• CPC Class Codes: G06T 2207/10116 X-ray image
• CPC Class Codes: G06T 2207/20044 Skeletonization; Medial axis transform
• CPC Class Codes: G06T 2207/30008 Bone
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/60 Analysis of geometric attributes

Abstract

A method of automatically segmenting the bone regions in a digital radiograph of a body extremity comprising the steps of: providing a digital radiographic image of a body extremity having one or more digits; estimating the upper and lower threshold values of the provided image; binarizing the provided image by a binarization system which uses the estimated upper and lower threshold values to produce a bi-tonal image; removing noise from the binarized image by a noise removal system; processing the noise removed binary image by a skeletonization technique in order to form an initial estimate of the central axis of each body extremity digit; approximating the locus of points generated by the processing step by a linear fit system; joining lines with near end points with a line linking system which results in a piece wise linear approximation of the central axis for each body extremity digit; for each point along the axes, generating perpendicular projections which extend a fixed pixel distance; for each perpendicular projection, averaging the pixel values by a trace generation system; convolving each density trace with a matched filter; analyzing the output of the matched filter step by a joint detection system to locate digit joints; for each body extremity digit, determining the bone edges between two joints; and determining the average density of the digit region between the digit joints and bone edges.

Claims

1. A method of automatically segmenting the bone regions in a digital radiograph of a body extremity comprising the steps of:

providing a digital radiographic image of a body extremity having one or more digits;

estimating upper and lower threshold values of said provided image;

binarizing said provided image by a binarization system which uses said estimated upper and lower threshold values to produce a bi-tonal image;

removing noise from said bi-tonal image by a noise removal system;

processing said noise removed bi-tonal image by a skeletonization technique in order to form an initial estimate of the central axis of each body extremity digit;

approximating the locus of points generated by said processing step by a linear fit system;

joining lines with near end points with a line linking system which results in a piece wise linear approximation of the central axis for each body extremity digit;

for each point along the axes, generating perpendicular projections which extend a fixed pixel distance;

for each perpendicular projection, averaging the pixel values by a trace generation system;

convolving each density trace with a matched filter;

analyzing the output of said matched filter step by a joint detection system to locate digit joints;

for each body extremity digit, determining the bone edges between two joints; and

determining the average density of the digit region between said digit joints and bone edges.

2. The method of claim 1 wherein said providing step provides a digital radiographic image of a hand and a standard wedge;

wherein said estimating step includes the steps of estimating the upper and lower threshold values of the hand by a histogram analysis system and of estimating the upper and lower threshold value of said standard wedge by steps including region growing, labeling, shape analysis, wedge identification, and upper and lower threshold estimation and wherein said threshold values for said hand and said wedge are combined to determine optimal values for the upper and lower threshold.

3. The method of claim 2 wherein said combining step uses a weighted average of the two estimates for each threshold value.

4. The method of claim 1 wherein said noise removing step uses morphological processing to remove noise.

5. The method of claim 1 wherein in said processing step, short lines and spurious points are discarded.

6. The method of claim 1 wherein in said joining step, unlinked end points of each segment are extended until they encounter either an image boundary or a region identified as background.

7. The method of claim 1 including the step of generating the average density of the body extremity.

8. The method of claim 7 including the step of estimating the risk of osteoporosis based on said bone density values.

9. The method of claim 1 wherein said skeletonization technique used in said processing step is a medial-axis transform.

10. A computer storage product comprising:

a computer readable storage medium having a computer program stored thereon for performing a method of automatically segmenting the bone regions in a digital radiograph of a body extremity comprising the steps of;

providing a digital radiographic image of a body extremity having one or more digits;

estimating upper and lower threshold values of said provided image;

binarizing said provided image by a binarization system which uses said estimated upper and lower threshold values to produce a bi-tonal image;

removing noise from said bi-tonal image by a noise removal system;

processing said noise removed bi-tonal image by a skeletonization technique in order to form an initial estimate of the central axis of each body extremity digit;

approximating the locus of points generated by said processing step by a linear fit system;

joining lines with near end points with a line linking system which results in a piece wise linear approximation of the central axis for each body extremity digit;

for each point along the axes, generating perpendicular projections which extend a fixed pixel distance;

for each perpendicular projection, averaging the pixel values by a trace generation system;

convolving each density trace with a matched filter;

analyzing the output of said matched filter step by a joint detection system to locate digit joints;

for each body extremity digit, determining the bone edges between two joints; and

determining the average density of the digit region between said digit joints and bone edges.