Subtraction technique for computerized detection of small lung nodules in computer tomography images

• US 6,678,399 B2
• Filed: 11/23/2001
• Issued: 01/13/2004
• Est. Priority Date: 11/23/2001
• Status: Active Grant

• Current Assignee: University of Chicago The (University of Chicago)
• Original Assignee: University of Chicago
• Inventors: Ishida, Takayuki, Doi, Kunio, Katsuragawa, Shigehiko
• Primary Examiner(s): Johnson, Timothy M.
• Assistant Examiner(s): Choobin, Barry
• Application Number:
  US09/990,311
• Publication Number:
  US 20030099388A1
• Time in Patent Office: 781 Days
• Field of Search: 382/131, 382/128, 382/130, 382/220, 382/221, 382/257, 382/260, 382/300, 128/922, 600/431, 600/425, 378/4, 378/62, 324/307, 702/129
• US Class Current: 382/131
• CPC Class Codes: G06T 2207/10081 Computed x-ray tomography [CT]
• CPC Class Codes: G06T 2207/20224 Image subtraction
• CPC Class Codes: G06T 2207/30064 Lung nodule
• CPC Class Codes: G06T 5/30 Erosion or dilatation, e.g. thinning
• CPC Class Codes: G06T 5/50 using two or more images, e.g. averaging or subtraction
• CPC Class Codes: G06T 7/11 Region-based segmentation

Abstract

A method, system, computer readable medium and apparatus for computerized detection of lung nodules in computer tomography images, by which mask images are created such that subtractions of the mask image from a targeted CT section image reveal or highlight small lung nodules in the target CT section. The mask image is created utilizing the targeted CT section image along with other CT section images generated from the same CT scan. Based on these other section CT images and the targeted CT section image, a mask image can be created that is very similar to the target CT section image, but without the presence of small lung nodules. When the mask image is subtracted from the targeted CT section image, the differences between the mask images and the CT section images reveal small lung nodules. The mask image may be created by linear interpolation or a morphological filtered image.

Claims

1. A method for computerized detection of lung nodules in CT section images, comprising the following steps:

warping a first CT section image to match a second CT section image;

warping a third CT section image to match the second CT section image;

creating a mask image by linear interpolation of the warped first CT section image and the warped third CT section image;

subtracting the mask image from the second CT section image to from a subtraction image; and

detecting small lung nodules based on the subtraction image.

2. The method of claim 1, wherein:

the first, second, and third CT section images are part of sequential series on CT section images;

the first CT section image is prior to the second CT section image; and

the third CT section image is subsequent to the second CT section image.

3. The method of claim 2, wherein the first and third CT section images are both adjacent to the second CT section.

4. The method of claim 1, comprising the further step of warping the mask image to match the first and third warped CT section images.

5. The method of claim 1, comprising the further step of warping the mask image to match the first warped CT section image.

6. The method of claim 1, comprising the further step of warping the mask image to match the third warped CT section image.

11. A computer readable medium storing computer program instructions for computerized detection of lung nodules in CT section images, which when used to program a computer cause the computer to perform any one of the steps of claims 1-7 and 8-10.

12. A system for implementing the method recited in any one of claims 1-7 and 8-10.

7. A method for computerized detection of small lung nodules in CT section images, comprising the following steps:

creating a morphological filtered image from at least first, second, and third CT section images comprising the steps of;

forming a first 3-D erosion image by eroding the first and second CT section images;

Forming a first 2D dilution image by diluting the 3D erosion image;

Forming a second 3D erosion image by eroding the second and third Ct section images;

Forming a second 2D dilution image by diluting the second 3D erosion image;

Forming a 3D dilution image by diluting the first and second 2D dilution images;

Forming the morphological filtered image by eroding the 3D dilution image;

creating a mask image from the morphological filtered image;

subtracting the mask image from the second CT section image to form a subtraction image; and

detecting small lung nodules based on the subtraction image.

8. The method of claim 7, wherein:

the first, second, and third CT section images are part of sequential series of CT section images;

the first CT section image is prior to the second CT section image; and

the third CT section image is subsequent to the second CT section image.

9. The method of claim 8, wherein the first and third CT section images are adjacent to the second CT section image.

10. The method of claim 7, comprising the further steps of:

detecting the line components of the second image; and

replacing at least one section of the second image having detected line components by corresponding at least one section of the morphological filtered image.

13. An apparatus arranged computerized detection of lung nodules in CT section images comprising:

a means for warping a first CT section image to match a second CT section image;

a means for warping a third CT section image to match the second CT section image;

a means for creating a mask image by linear interpolation of the warped first CT section image and the warped third CT section image; and

a means for subtracting the mask image from the second CT section image.