METHOD, APPARATUS AND STORAGE MEDIUM FOR DETECTING CARDIO, THORACIC AND DIAPHRAGM BORDERS

• US 20060285751A1
• Filed: 06/15/2006
• Published: 12/21/2006
• Est. Priority Date: 06/15/2005
• Status: Active Grant

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: WU, DAWEI, Peng, Miao
• Granted Patent: US 7,965,893 B2
• Time in Patent Office: Days
• US Class Current: 382/199
• CPC Class Codes: G06T 2207/10116 X-ray image
• CPC Class Codes: G06T 2207/20132 Image cropping
• CPC Class Codes: G06T 2207/30048 Heart; Cardiac
• CPC Class Codes: G06T 2207/30061 Lung
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06V 10/26 Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion

Abstract

The present invention provides a method of detecting borders in a chest image. The method comprises calculating the gray level difference between neighboring pixels of the chest image to get a differential image; filtering the differential image to reduce noise and enhance the target; binarizing the filtered image; picking out the outside edges of the area with high gray level from the binarized image; and determining a final border from the edges according to the character of the border to be found. The present invention also provides an apparatus and a storage medium for implementing the above-mentioned method and a method and an apparatus for automatically measuring the Cardiothoracic Ratio of a chest image.

Claims

1. A method of detecting borders in a chest image, characterized by comprising steps of:

calculating the gray level difference between neighboring pixels of said chest image to get a differential image;

filtering said differential image to reduce noise and enhance target by at least one filter;

binarizing the filtered image;

picking out the outside edges of the area with high gray level from the binarized image; and

determining a final border from said edges according to the character of the border to be found.

2. The method according to claim 1, characterized in that said method further comprises a step of finding landmark lines of the chest image according to project profile of said chest image, before said step of calculating the gray level difference.

3. The method according to claim 1, characterized in that said step of calculating the gray level difference between neighboring pixels of said chest image comprises:

determining that the direction for calculating the gray level difference between neighboring pixels is from the brighter side of the border to be found to the darker side.

4. The method according to claim 1, characterized in that said step of calculating the gray level difference between neighboring pixels of said chest image further comprises steps of:

transforming the gray value of said differential image into 0˜

L gray value space by linear transformation; and

computing the histogram of said differential image to get the maximum value position MP, then stretching the histogram from MP˜

L to 0˜

L.

5. The method according to claim 1, characterized in that the step of filtering said differential image is performed using an average filter and/or a medium filter.

6. The method according to claim 5, characterized in that said filter is chosen according to the border'"'"'s character.

7. The method according to claim 1, characterized in that said step of binarizing the filtered image comprises steps of:

defining a Region of interest (ROI) according the midline of the chest image;

defining a binary threshold according to the average gray value of the ROI; and

binarizing the filtered image according to said binary threshold.

8. The method according to claim 1, characterized in that said step of picking out the outside edges comprises the steps of:

finding out the pixels on the edges of the determined side of the high gray level areas;

setting the gray level of pixels found on the edges into highest gray level and setting the gray level of other pixels into lowest gray level; and

dilating the image by an operator to ensure connectivity of the edges.

9. The method according to claim 8, characterized in that the operator is determined according to the character of the border to be found.

10. The method according to claim 1, characterized in that said step of determining a final border comprises the steps of:

tracing the outside edges to get the candidate borders; and

choosing the curve in the candidate borders that has the most proper position information to be the correct border according to the character of former found borders and the character of the border to be found.

11. The method according to claim 10, characterized in that said step of choosing the curve in the candidate borders treats ribcage, diaphragm and heart differently, and includes

for ribcage border:

filtering the candidate borders based on the length information of border, and using the position information of filtered borders to decide the ribcage border;

for diaphragm border;

filtering the candidate borders based on the length information of border, and using the relative position of found ribcage border that is on the same side as diaphragm border to decide the diaphragm border, and if the certain ribcage border is not found, using the position information of diaphragm borders to decide directly; and

for heart border;

filtering the candidate borders based on the length information of border, and using the relative position of found diaphragm border that is on the same side as the heart border to decide the heart border, and if the certain diaphragm border is not found, using the position information of the heart border to decide directly.

22. A method of automatically measuring the Cardiothoracic Ratio of a chest image, characterized by comprising steps of:

detecting left and right lung borders firstly, then detecting left and right diaphragms using the detected lung borders and finally detecting left and right heart borders using the detected diaphragm borders in the chest image by the method according to any one of claims 1 to 11;

searching for the maximum value TL of left lung border in horizontal direction, the minimum value TR of right lung border in horizontal direction, the maximum value CL of left heart border in horizontal direction and the minimum value CR of right heart border in horizontal direction; and

calculating Cardiothoracic Ratio (CTR) of the chest image by the following expression;

CTR=(CL−

CR)/(TL−

TR)*100%.

23. An apparatus for automatically measuring the Cardiothoracic Ratio of a chest image, characterized by comprising:

means for detecting left and right lung borders, left and right diaphragms and left and right heart borders in the chest image by the method according to any one of claims 1 to 11;

means for searching for the maximum value TL of left lung border in horizontal direction, the minimum value TR of right lung border in horizontal direction, the maximum value CL of left heart border in horizontal direction and the minimum value CR of right heart border in horizontal direction; and

means for calculating Cardiothoracic Ratio (CTR) of the chest image by the following expression;

CTR=(CL−

CR)/(TL−

TR)*100%.

24. A storage medium encoded with machine-readable computer program code for detecting borders in a chest image, the storage medium including instructions for causing a processor to implement the method according to any one of claims 1 to 11.

12. An apparatus for detecting borders in a chest image, characterized by comprising:

means for calculating the gray level difference between neighboring pixels of said chest image to get a differential image;

means for filtering said differential image to reduce noise and enhance target;

means for binarizing the filtered image;

means for picking out the outside edges of the area with high gray level from the binarized image; and

means for determining a final border from said edges according to the character of the border to be found.

13. The apparatus according to claim 12, characterized in that said means for calculating the gray level difference between neighboring pixels of said chest image comprises:

means for determining which side of the border to be found is brighter; and

means for determining that the direction for calculating the gray level difference between neighboring pixels is from the brighter side of the border to be found to the darker side.

14. The apparatus according to claim 12, characterized in that said means for calculating the gray level difference between neighboring pixels of said chest image further comprises:

means for transforming the gray value of said differential image into 0˜

L gray value space by linear transformation; and

means for computing the histogram of said differential image to get the maximum value position MP, and then stretching the histogram from MP˜

L to 0˜

L.

15. The apparatus according to claim 12, characterized in that the means for filtering said differential image comprises an average filter or a medium filter.

16. The apparatus according to claim 15, characterized in that said filter is chosen according to the border'"'"'s character.

17. The apparatus according to claim 12, characterized in that said means for binarizing the filtered image comprises:

means for defining a Region of interest (ROI) according to the midline of the chest image;

means for defining a binary threshold according to the average gray value of the ROI; and

means for binarizing the filtered image according to said binary threshold.

18. The apparatus according to claim 12, characterized in that said means for picking out the outside edges comprises:

means for determining the border to be found locating on which side of high gray level areas;

means for finding out the pixels on the edges of the determined side of the high gray level areas;

means for setting the gray level of pixels found on the edges into highest gray level and setting the gray level of other pixels into lowest gray level; and

means for dilating the image by an operator to ensure connectivity of the edges.

19. The apparatus according to claim 18, characterized in that the operator is determined according to the character of the border to be found.

20. The apparatus according to claim 12, characterized in that said means for determining a final border comprises:

means for tracing the outside edges to get the candidate borders; and

means for choosing the curve in the candidate borders that has the most proper position information to be the correct border.

21. The apparatus according to claim 20, characterized in that said means for choosing the curve in the candidate borders treats ribcage, diaphragm and heart differently:

ribcage border;

filtering the candidate borders based on the length information of border, and using the position information of filtered borders to decide the ribcage border;

diaphragm border;

filtering the candidate borders based on the length information of border, and using the relative position of the found ribcage border that is on the same side as the diaphragm border to decide the diaphragm border, and if the certain ribcage border is not found, using the position information of diaphragm borders to decide directly; and

heart border;

filtering the candidate borders based on the length information of border, and using the relative position of the found diaphragm border that is on the same side as the heart border to decide the heart border, and if the certain diaphragm border is not found, using the position information of the heart border to decide directly.