Automated method and system for the delineation of the chest wall in computed tomography scans for the assessment of pleural disease

• US 20030086599A1
• Filed: 11/13/2002
• Published: 05/08/2003
• Est. Priority Date: 06/15/2001
• Status: Active Grant

• Current Assignee: University of Chicago
• Original Assignee: University of Chicago
• Inventors: Oxnard, Geoffrey R., Armato, Samuel G. III, MacMahon, Heber
• Granted Patent: US 6,813,375 B2
• Time in Patent Office: Days
• US Class Current: 382/131
• CPC Class Codes: A61B 5/1075 for measuring dimensions by non-invasive methods, e.g. for determining thickness of tissue layer A61B8/0858 takes precedence
• CPC Class Codes: G06T 2207/10081 Computed x-ray tomography [CT]
• 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 7/12 Edge-based segmentation

Abstract

A method, system, and computer program product for automated and semi-automated measurements of pleural space and/or pleural thickening in thoracic CT images to identify the presence and quantify the extent of pleura-based disease, including obtaining a CT image including the pleural space and/or the pleural thickening, segmenting lungs in the obtained image, obtaining an initial endpoint on a chest wall or a mediastinum boundary; determining a terminal endpoint on a boundary of the at least one segmented lung; and determining a distance between said initial endpoint and said the terminal endpoint as the extent of the pleural space and/or the pleural thickening. Exemplary embodiments include determining the extent of pleural space and/or pleural thickening based on linear distance, area, and volume of the space between the lung boundary and at least one of the chest wall and the mediastinum boundary. These pleural determinations may be used to quantify the extent of disease in a particular case as additional information to be incorporated into a radiologist'"'"'s decision-making process, or as part of a computer-aided diagnostic scheme that alerts radiologists of the potential for pleural disease in the case.

Claims

1. A method for determining an extent of at least one of a pleural space and a pleural thickening, comprising:

obtaining an image including at least one of the pleural space and the pleural thickening;

segmenting at least one lung in the obtained image;

obtaining an initial endpoint on one of a chest wall and a mediastinum boundary;

determining a terminal endpoint on a boundary of the at least one segmented lung; and

determining a distance between said initial endpoint and said terminal endpoint as the extent of the at least one of the pleural space and the pleural thickening.

2. The method of claim 1, wherein the step of determining a terminal endpoint comprises:

selecting, as the terminal endpoint, a pixel on the boundary of the at least one segmented lung for which a distance between the pixel and the initial endpoint is minimum.

3. The method of claim 1, wherein the step of determining a terminal endpoint comprises:

selecting, as the terminal endpoint, a pixel on the boundary of the at least one segmented lung for which a distance between the pixel and the initial endpoint is maximum,

the pixel being located within a predetermined distance of the initial endpoint.

4. The method of claim 1, wherein the step of determining a terminal endpoint comprises:

selecting, as the terminal endpoint, a pixel on the boundary of the at least one segmented lung that lies on a line connecting the initial endpoint with a center-of-mass of the at least one segmented lung.

5. The method of claim 1, wherein the step of determining a terminal endpoint comprises:

determining as a set of candidate terminal endpoints those pixels on the boundary of the at least one segmented lung having an associated normal line that extends within a predetermined number of pixels of the initial endpoint; and

selecting, as the terminal endpoint, a pixel from the set of candidate terminal endpoints for which the associated normal line is most closely aligned with a line from the initial endpoint to a center-of-mass of the at least one segmented lung.

6. The method of claim 1, wherein the step of determining a terminal endpoint comprises:

constructing a set of lines passing through the initial endpoint at different angles;

determining a standard deviation of gray levels of a predetermined number of pixels on each line in the set of lines;

selecting, as a tangent line, a line in the set of lines having a smallest standard deviation, as determined in the preceding determining step; and

selecting, as the terminal endpoint, a pixel on the boundary of the at least one segmented lung that lies on a line normal to the tangent line selected in the preceding selecting step.

7. The method of claim 1, wherein the obtaining step comprises:

obtaining a computed-tomographic image including at least one of the pleural space and the pleural thickening.

8. The method of claim 1, wherein the obtaining step comprises:

obtaining a magnetic resonance image including at least one of the pleural space and the pleural thickening.

13. A computer program product storing program instructions for execution on a computer system, which when executed by the computer system, cause the computer system to perform the method recited in any one of claims 1-12.

15. A system configured to determine an extent of at least one of a pleural space and a pleural thickening by performing the steps recited in claim 1.

16. The system of claim 15, further comprising a graphical user interface (GUI).

17. The system of claim 16, wherein the GUI comprises:

a display controller configured to display a representation of the extent of the at least one of the pleural space and the pleural thickening.

18. The system of claim 17, wherein the display controller comprises:

a first control section configured to display at least one measurement of the extent of the at least one of the pleural space and the pleural thickening obtained by at least one observer.

19. The system of claim 17, wherein the display controller comprises:

a second control section configured to display a plurality of measurements of the extent of the at least one of the pleural space and the pleural thickening obtained at a plurality of different times.

20. The system of claim 17, wherein the display controller comprises:

a third control section configured to compare a plurality of measurements of the extent of the at least one of the pleural space and the pleural thickening obtained by a plurality of observers.

21. The system of claim 18, further comprising:

a device configured to store the at least one measurement of the extent of the at least one of the pleural space and the pleural thickening obtained by at least one observer.

22. The system of claim 15, further comprising:

a display configured to display a representation of the extent of the at least one of the pleural space and the pleural thickening.

9. A method for determining an extent of at least one of a pleural space and a pleural thickening, comprising:

obtaining an image including at least one of the pleural space and the pleural thickening;

segmenting at least one lung in the obtained image;

selecting at least two pixels, each of the two pixels being on one of a chest wall and a mediastinum boundary;

determining a contour passing through the at least two pixels; and

calculating an area between a boundary of the at least one segmented lung and the contour as the extent of the at least one of the pleural space and the pleural thickening.

10. The method of claim 9, further comprising:

initializing a volume to zero;

adding the area calculated in the calculating step to the volume;

repeating the obtaining, segmenting, selecting, determining, calculating, and adding steps for each image in a set of images; and

outputting the volume as the extent of the at least one of the pleural space and the pleural thickening.

14. A system configured to determine an extent of at least one of a pleural space and a pleural thickening by performing the steps recited in any one of claims 2-12.

11. A method for determining an extent of at least one of a pleural space and a pleural thickening, comprising the steps of:

obtaining an image including at least one of the pleural space and the pleural thickening;

segmenting lungs in the obtained image;

constructing a chest wall image from the obtained image using a lung boundary obtained in the segmenting step and a series of normal rays extending away from the lung boundary;

identifying ribs in the chest wall image;

mapping a location of the identified ribs back into the obtained image; and

determining in the obtained image the extent of the at least one of the pleural space and the pleural thickening between the identified ribs mapped back to the obtained image and at least one segmented lung.

12. The method of claim 11, wherein the constructing step comprises:

identifying anterior- and posterior-most pixels along the lung boundary of the at least one segmented lung;

constructing the series of normal rays originating on the lung boundary nearest a chest wall between the anterior- and posterior-most pixels, and extending in a normal direction away from the lung boundary; and

constructing the chest wall image as columns of pixels intercepted by the series of normal rays.