Computer-aided tubing detection

1. A method for detecting tubing in a radiographic image of a patient, comprising:

obtaining a radiographic image for a patient;

detecting at least one tube segment in the image; and

forming at least one tubing candidate by growing the at least one detected tube segment by identifying a group of consecutive pixels along a fitted curve of the detected tube segment.

2. The method of claim 1 further comprising extracting one or more features to characterize the at least one tubing candidate.

3. The method of claim 2 further comprising analyzing extracted features to remove one or more false-positive tubing candidates.

4. The method of claim 3 wherein analyzing extracted features to remove one or more false-positive tubing candidates comprises analyzing one or more of curvature, length, position relative to patient anatomy, detected tip position, and tube width standard deviation using quadratic discriminate analysis.

5. The method of claim 2 wherein extracting one or more features comprises identifying a feature taken from the group comprised of tubing candidate width, 1-degree and 3-degree errors from curve-fitting of the at least one tubing candidate, tube/spine angle difference, mean value at the tubing candidate, angular position of the tubing candidate, percentage of tubing candidate pixels within a fitted curve, length of the detected tubing candidate, tubing candidate position relative to one or more anatomy structures, mean curvature of the tubing candidate, and the variation in curvature of the tubing candidate.

6. The method of claim 1 further comprising identifying a region of interest in the image for detection of tube segments.

7. The method of claim 1 wherein detecting at least one tube segment comprises:

forming at least one template-processed image by processing at least a portion of the radiographic image data using one or more gradient feature templates or using an enhanced tube pattern feature template; and

applying an image thresholding algorithm to the at least one template-processed image, forming a thresholded image thereby.

8. The method of claim 7 wherein the one or more gradient feature templates are selected according to an angular orientation of the patient's spine.

9. The method of claim 7 wherein the enhanced tube pattern feature template is selected according to an angular orientation.

10. The method of claim 7 wherein the enhanced tube pattern feature template is a Haar-like template.

11. The method of claim 7 wherein forming at least one template-processed image further comprises treating the image content using thresholding.

12. The method of claim 1 wherein detecting at least one tube segment comprises using a gradient feature template to identify one or more edges of the tube segment and using an enhanced tube pattern feature template to identify a center of the tube segment.

13. The method of claim 1 further comprising performing contrast enhancement on the radiographic image.

14. The method of claim 1 further comprising displaying the at least one tubing candidate.

15. The method of claim 14 wherein displaying the at least one tubing candidate comprises highlighting the at least one tubing candidate on a display screen.

16. The method of claim 1 wherein growing the at least one detected tube segment comprises merging two or more detected tube segments according to a distance between the two or more detected tube segments.

17. The method of claim 1 wherein detecting at least one tube segment comprises

processing at least a portion of the radiographic image data using at least one gradient feature template or using an enhanced tube pattern feature template, forming at least one template-processed image thereby;

applying a thresholding algorithm to the at least one template-processed image; and

identifying an edge or center pattern within the at least one template-processed image.

18. The method of claim 1 wherein growing is based on the analysis of thresholded template-processed images.