Segmentation of sheet objects from image generated using radiation imaging modality

Patent metadata

Field	Value
Publication number	US-9846935-B2
Application number	US-201214403292-A
Country	US
Kind code	B2
Filing date	May 31, 2012
Priority date	May 31, 2012
Publication date	Dec 19, 2017
Grant date	Dec 19, 2017

Abstract

Among other things, one or more systems and/or techniques for segmenting a representation of a sheet object from an image are provided herein. To identify elements of an image (e.g., pixels and/or voxels) representative of sheet objects, a constant false alarm rate (CFAR) score and a topological score are computed for respective elements being analyzed. The CFAR score indicates a relationship between an element and a neighborhood of elements when viewed as a collective unit. The topological score indicates a relationship between the element and a neighborhood of elements when viewed neighbor-by-neighbor. When the CFAR score is within a specified range of CFAR scores and the topological score is within a specified range of topological scores, the element is labeled as being associated with a sheet object. A connected component labeling (CCL) approach may be used to group elements labeled as being associated with a sheet object.

First claim

What is claimed is:

1. A method for segmenting a sheet object represented in an image generated using radiation imaging modality, comprising:
identifying a plurality of elements in the image, respective elements associated with a value;
for a first element of the plurality of elements:
selecting a first plurality of neighboring elements in spatial proximity to the first element to define a first neighborhood and a second plurality of neighboring elements in spatial proximity to the first element to define a second neighborhood;
computing a constant false alarm rate (CFAR) score for the first element, the CFAR score determined by comparing the value associated with the first element to a statistical measure for the first neighborhood;

computing a topological score for the first element, the topological score determined by comparing the value associated with the first element to respective values associated with elements comprised within the second neighborhood, wherein computing the topological score for the first element, comprises:
comparing the value associated with the first element to respective values associated with elements comprised within the second neighborhood; and at least one of:
determining a number of neighboring elements comprised within the second neighborhood that are associated with values within a specified range of the value associated with the first element; or
determining a number of neighboring elements comprised within the second neighborhood that are associated with values outside of the specified range of the value associated with the first element; and

labeling the first element as being associated with the sheet object when the CFAR score is within a first specified range and when the topological score is within a second specified range.

2. The method of claim 1 , the first neighborhood different than the second neighborhood.

3. The method of claim 1 , the statistical measure for the first neighborhood comprising a mean value for the first neighborhood.

4. The method of claim 1 , identifying a plurality of elements in the image, comprising at least one of:
identifying a plurality of voxel elements in the image; or
identifying a plurality of pixel elements in the image.

5. The method of claim 1 , wherein the value associated with respective elements is at least one of a density value, a z-effective value, a Compton score value, or a material property value.

6. The method of claim 1 , computing the CFAR score for the first element, comprising:
computing the statistical measure for the first neighborhood, the statistical measure comprising a mean value for the first neighborhood; and
comparing the value associated with the first element to the statistical measure by computing a difference between the value associated with the first element and the mean value.

7. The method of claim 6 , computing the CFAR score for the first element, comprising:
computing a standard deviation for the first neighborhood relative to the mean value; and
dividing the difference between the value associated with the first element and the mean value by the standard deviation.

8. The method of claim 1 , wherein the topological score is representative of at least one of:
the number of neighboring elements comprised within the second neighborhood that are associated with values within the specified range of the value associated with the first element; or
the number of neighboring elements comprised within the second neighborhood that are associated with values outside of the specified range of the value associated with the first element.

9. The method of claim 1 , the radiation imaging modality comprising a computed tomography (CT) imaging modality.

10. The method of claim 1 , comprising at least one of:
computing the CFAR score and the topological score concurrently;
computing the topological score when the CFAR score is within the first specified range; or
computing the CFAR score when the topological score is within the second specified range.

11. A security imaging modality, comprising:
a processing unit; and
a computer readable medium comprising computer executable instructions that when executed by the processing unit perform operations, the operations comprising:
computing a constant false alarm rate (CFAR) score for a first element of an image by comparing a value associated with the first element to a statistical measure for a first neighborhood of elements;
computing a topological score for the first element by comparing the value associated with the first element to respective values associated with elements comprised within a second neighborhood of elements, wherein the topological score for the first element is a function of a number of neighboring elements comprised within the second neighborhood of elements that are associated with values within a specified range of the value associated with first element; and
labelling the first element as being associated with a sheet object when the CFAR score is within a first specified range and when the topological score is within a second specified range to facilitate segmenting the sheet object from other sub-objects represented in the image.

12. The security imaging modality of claim 11 , wherein at least one of:
the first element is a first voxel of the image, the first neighborhood of elements comprising a first set of voxels that neighbor the first voxel, and the second neighborhood of elements comprising a second set of voxels that neighbor the first voxel, or
the first element is a first pixel of the image, the first neighborhood of elements comprising a first set of pixels that neighbor the first pixel and the second neighborhood of elements comprising a second set of pixels that neighbor the first pixel.

13. The security imaging modality of claim 11 , wherein the value associated with the first element and the respective values associated with elements comprised within at least one of the first neighborhood of elements or the second neighborhood of elements are at least one of a density value, a z-effective value, a Compton score value, or a material property value.

14. The security imaging modality of claim 11 , wherein computing the CFAR score comprises:
computing the statistical measure for the first neighborhood of elements, the statistical measure comprising a mean value for the first neighborhood of elements;
comparing the value associated with the first element to the statistical measure by computing a difference between the value associated with the first element and the mean value;
computing a standard deviation for the first neighborhood of elements relative to the mean value; and
dividing the difference between the value associated with the first element and the mean value by the standard deviation.

15. The security imaging modality of claim 11 , wherein the security imaging modality is a computed tomography imaging modality configured to generate volumetric data and to generate the image using the volumetric data, the image being at least one of a three-dimensional image or a two-dimensional image.

16. The security imaging modality of claim 11 , wherein the operations comprise at least one of:
computing the CFAR score and the topological score concurrently;
computing the topological score merely when the CFAR score is within the first specified range; or
computing the CFAR score merely when the topological score is within the second specified range.

17. The security imaging modality of claim 11 , comprising an ionizing radiation source.

Assignees

• Simanovsky Sergey
• Pavlovich Julia
• Naidu Ram
• Analogic Corp

Inventors

• Simanovsky Sergey
• Pavlovich Julia
• Naidu Ram

Classifications

• G06T7/0012 Primary

  Biomedical image inspection · CPC title

• G06V10/443

  by matching or filtering · CPC title

• G06K9/4609

  Physics · mapped topic

• G06K2009/4666

  Physics · mapped topic

• G06T2207/10081

  Computed x-ray tomography [CT] · CPC title