Method for segmenting objects in images

• US 8,369,590 B2
• Filed: 05/21/2008
• Issued: 02/05/2013
• Est. Priority Date: 05/21/2007
• Status: Active Grant

• Current Assignee: Cornell University
• Original Assignee: Cornell University
• Inventors: Wang, Yi, Codella, Noel C. F., Lee, Hae-Yeou
• Primary Examiner(s): ARANA, LOUIS M
• Application Number:
  US12/124,973
• Publication Number:
  US 20080292169A1
• Time in Patent Office: 1,721 Days
• Field of Search: 382/128, 382/131, 382/132, 382/173, 382/174
• US Class Current: 382/128
• CPC Class Codes: G06T 2207/10072 Tomographic images
• CPC Class Codes: G06T 2207/10088 Magnetic resonance imaging [MRI]
• CPC Class Codes: G06T 2207/30048 Heart; Cardiac
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/174 involving the use of two or more images
• CPC Class Codes: G06T 7/62 of area, perimeter, diameter or volume

Abstract

A method for identifying an attribute of an object represented in an image comprising data defining a predetermined spatial granulation for resolving the object, where the object is in contact with another object. In an embodiment, the method comprises identifying data whose values indicate they correspond to locations completely within the object, determining a contribution to the attribute provided by the data, and identifying additional data whose values indicate they are not completely within the object. The method next interpolates second contributions to the attribute from the values of the additional data and finds the attribute of the object from the first contribution and second contributions. The attribute may be, for example, a volume, and the values may correspond, for example, to intensity.

Claims

1. A computer-implemented method for determining an attribute of a region of interest represented by a plurality of voxels, the method comprising:

identifying a seed voxel that corresponds to a location completely within the region of interest;

performing region-growth to identify a set of voxels, including voxels that correspond to locations completely within the region of interest and voxels that correspond to locations that are partially within the region of interest; and

calculating the attribute of the region of interest, wherein the calculation includes applying a weighting function to the corresponding attribute of voxels of the set of voxels, wherein the corresponding attribute of the voxels of the set of voxels are weighted according to signal intensity.

2. The method of claim 1, wherein the plurality of voxels are obtained using one or more of (1) magnetic resonance imaging, (2) computed tomography (CT), (3) ultrasound, (4) X-ray and (5) single photon emission computed tomography (SPECT).

3. The method of claim 1, further comprising correcting the plurality of voxels.

4. The method of claim 1, wherein the attribute is volume.

5. The method of claim 1, wherein the values correspond to intensity.

6. The method of claim 1, wherein performing region growth to identify the set of voxels includes identifying neighboring voxels whose values are within a predetermined amount of a value indicating that a voxel corresponds to a location completely within the object.

7. A computer-implemented method for determining volume of a blood-containing region of interest represented by a plurality of voxels, the method comprising:

identifying a seed voxel that corresponds to a full-blood location completely within the region of interest;

performing region-growth to identify a set of voxels, including full-blood voxels that corresponds to full-blood locations completely within the region of interest and partial-blood voxels corresponding to partial-blood locations that are partially within the region of interest; and

calculating the volume of the region of interest, wherein the calculation includes applying a weighting function to volumes of voxels of the set of voxels, wherein volumes of the voxels of the set of voxels are weighted according to signal intensity.

8. The method of claim 7, wherein the signal intensities of the voxels to which the weighting function is applied are proportional to the amount of blood represented by the locations corresponding to the voxels.

9. The method of claim 7, wherein the blood-containing region of interest is part of a heart, and the weighting function is a function that takes into account the signal intensities of the set of voxels, a constant signal intensity associated with a full-blood voxel, and a constant signal intensity associated with a full-myocardium voxel.

10. The method of claim 9, wherein the weighting function is represented by the equation:

11. The method of claim 7, wherein the blood-containing region of interest is the left ventricle of a heart.