Automated method and system for region decomposition in digital radiographic images

• US 5,757,953 A
• Filed: 02/29/1996
• Issued: 05/26/1998
• Est. Priority Date: 02/29/1996
• Status: Expired due to Fees

• Current Assignee: CareStream Health Incorporated
• Original Assignee: Eastman Kodak Company
• Inventors: Jang, Ben K.
• Primary Examiner(s): Boudreau, Leo
• Assistant Examiner(s): Tran, Phuoc
• Application Number:
  US08/608,899
• Time in Patent Office: 817 Days
• Field of Search: 382/132, 382/133, 382/130, 382/173, 382/180, 382/192, 382/224, 382/225, 382/257, 382/260, 382/264, 382/308, 382/299
• US Class Current: 382/132
• CPC Class Codes: G06T 2207/10116 X-ray image
• CPC Class Codes: G06T 2207/20016 Hierarchical, coarse-to-fine, multiscale or multiresolution image processing; Pyramid transform
• CPC Class Codes: G06T 2207/30061 Lung
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/155 involving morphological operators
• CPC Class Codes: G06V 10/267 by performing operations on regions, e.g. growing, shrinking or watersheds
• CPC Class Codes: G06V 10/457 by analysing connectivity, e.g. edge linking, connected component analysis or slices
• CPC Class Codes: G06V 2201/03 Recognition of patterns in medical or anatomical images

Abstract

A digital radiographic image is segmented into various regions and a region thereof is further decomposed into subregions, wherein digital image data is acquired and subjected to multiple phases of digital imaging processes. The region decomposition method first uses progressively smoothing techniques to generate smoothed regions at multiple scales. Next, the number of connected components at each scale is computed for each smoothed region. A shape spectrum, which is the number of connected components as a function of scale, is subsequently constructed to determine the most stable range of scales and the most stable number of subregions into which the region is decomposed. Each pixel is then classified into subregions, according to the geometrical relationship of the connected components detected at most stable scales. Finally, a decomposed map is generated to function as multivalued templates for any further image processing to be done on various decomposed subregions.

Claims

1. An automated method for decomposing a region in a radiographic image into subregions, comprising the steps of:

(a) smoothing the region at a plurality of scales to generate a plurality of smoothed regions;

(b) computing, at each scale from each smoothed region, the number of connected components in each smoothed region;

(c) determining the most stable range of scales and the most stable number of subregions contained within the range;

(d) classifying each pixel based on the determined range of scales and the determined number of subregions; and

(e) generating a decomposed map for further image processing.

2. The method of claim 1 wherein the subregions are physically or anatomically meaningful subregions.

3. The method of claim 1 wherein the step of smoothing a region at a plurality of scales includes the use of one or more morphological smoothing techniques.

4. The method of claim 1 wherein the step of determining the most stable range of scales comprises the step of constructing a shape spectrum by the number of connected components as a function of scale.

5. The method of claim 4 wherein the step of determining the most stable number of subregions comprises determining the span of a continuum of the broadest constant spectrum.

6. The method of claim 4 wherein the step of determining the most stable range of scales comprises determining the range of the broadest constant spectrum.

7. The method of claim 4 wherein the step of classifying each pixel includes the use of a lower bound of the broadest constant spectrum.

8. The method of claim 1 wherein the step of generating a decomposed map includes the use of a multiple-valued image that functions as multiple templates for any further image processing to be done on the various decomposed subregions of the image.

9. A system for decomposing a region in a radiographic image into subregions, comprising:

(a) means for smoothing the region at a plurality of scales to generate a plurality of smoothed regions;

(b) means for computing, at each scale from each smoothed region, the number of connected components in each smoothed region;

(c) means for determining the most stable range of scales and the most stable number of subregions contained within the range;

(d) means for classifying each pixel based on the determined range of scales and the determined number of subregions; and

(e) means for generating a decomposed map for further image processing.

10. The apparatus of claim 9 wherein said means for smoothing a region at a plurality of scales includes one or more morphological smoothing techniques.

11. The apparatus of claim 9 wherein said means for determining the most stable range of scales and the most stable number of subregions comprises means for constructing a shape spectrum by the number of connected components as a function of scale.

12. The apparatus of claim 11 wherein said means for constructing a shape spectrum to determine the most stable number of subregions further includes means for determining the span of a continuum of the broadest constant spectrum.

13. The apparatus of claim 9 wherein said means for generating a decomposed map includes the generation of a multiple-valued image that functions as multiple templates for any further image processing to be done on the various decomposed subregions of the image.

14. The apparatus of claim 9 wherein the image is a subsampled image.

15. The apparatus of claim 9 wherein the image is a non-subsampled image.