Rib suppression in radiographic images

1. A method for rib suppression in a chest x-ray image of a patient, executed at least in part by a computer, comprising:

detecting and labeling one or more ribs in a region of interest in the x-ray image that includes a lung region;

obtaining a rib template for one or more ribs of the image from a rib library comprising a plurality of rib templates;

modifying detection results for the one or more ribs by applying the rib template in the region of interest;

forming a conditioned x-ray image by suppressing rib content according to the modified detection results; and

storing, displaying, or transmitting the conditioned x-ray image.

2. The method of claim 1 wherein modifying the detection results comprises performing edge detection.

3. A method for rib suppression in a chest x-ray image of a patient, executed at least in part by a computer, comprising:

detecting and labeling one or more ribs in a region of interest in the x-ray image that includes a lung region;

obtaining a rib template for one or more ribs of the image from a rib library comprising a plurality of rib templates, wherein obtaining the rib template comprises selecting a rib template from a plurality of rib templates of a plurality of patients having similar patient characteristics;

modifying detection results for the one or more ribs by applying the rib template in the region of interest;

forming a conditioned x-ray image by suppressing rib content according to the modified detection results; and

storing, displaying, or transmitting the conditioned x-ray image.

4. The method of claim 1 wherein obtaining the rib template comprises generating a rib template according to the detection and labeling results.

5. The method of claim 3 further comprising modifying the rib template according to patient features in the x-ray image.

6. The method of claim 1 wherein detecting and labeling one or more ribs further comprises scaling the image to a reduced resolution.

7. The method of claim 1 wherein applying the rib template comprises predicting rib features for one or more ribs and wherein the rib template shows the position of a plurality of ribs.

8. The method of claim 1 wherein detecting and labeling one or more ribs further comprises extracting a medial axis from at least one of the one or more ribs.

9. The method of claim 1 wherein applying the rib template further comprises identifying rib edges.

10. The method of claim 1 wherein detecting and labeling one or more ribs in the image comprises classifying pixels within the lung region of interest as rib or non-rib pixels.

11. A method for rib suppression in a chest x-ray image of a patient, executed at least in part by a computer, comprising:

segmenting a lung region within the image;

detecting and labeling one or more ribs in a region of interest in the x-ray image that includes the lung region;

selecting a rib cage template for the one or more ribs in the region of interest from a rib cage library comprising a plurality of rib cage templates according to the one or more detected ribs;

adapting the selected rib cage template to the x-ray image according to the segmented lung region and applying the selected rib cage template for detecting rib edges for the one or more detected ribs within the region of interest;

forming a conditioned x-ray image by suppressing rib content according to the detection results for ribs and rib edges; and

storing, displaying, or transmitting the conditioned x-ray image.

12. The method of claim 11 further comprising generating cross rib profiles along the detected ribs and further conditioning the x-ray image according to the cross rib profiles.

13. The method of claim 11 further comprising:

selecting the rib cage template for the one or more ribs includes selecting a rib cage template from a rib cage library comprising a plurality of rib cage templates having similar patient characteristics, and

modifying the rib cage template according to patient features in the x-ray image.

14. The method of claim 11 wherein detecting and labeling one or more ribs further comprises scaling the image to a reduced resolution.

15. The method of claim 11 wherein applying the rib cage template comprises predicting rib features for one or more ribs according to the rib cage template.

16. The method of claim 11 wherein detecting and labeling one or more ribs further comprises extracting a medial axis from at least one of the one or more ribs.

17. The method of claim 11 further comprising recursively refining rib edge detection.

18. A method for rib suppression in a chest x-ray image of a patient, executed at least in part by a computer, comprising:

segmenting a lung region within the image;

detecting and labeling one or more ribs in a region of interest in the x-ray image that includes the lung region;

selecting a rib template for one or more ribs of the image from a rib library comprising a plurality of rib templates according to the one or more detected ribs;

modifying detection results for the one or more ribs by applying the selected rib template in the region of interest;

forming a conditioned x-ray image by suppressing rib content according to the modified detection results; and

storing, displaying, or transmitting the conditioned x-ray image.

19. The method of claim 18 further comprising adapting the generated rib template according to the lung region segmentation.

20. The method of claim 18 , wherein detecting and labeling one or more ribs in a region of interest comprises:

applying a pixel classification to the one or more detected ribs in the region of interest; and

using the pixel classification, labeling the one or more detected ribs in the region of interest.