Granted Patent B2

US 7,912,263 · App. 11/834,222 · Granted Mar 22, 2011

Abstract

Claims (37)

1. A method for detecting clipped anatomy in a radiographic image having a border, executed by a processor, comprising:

obtaining image data for the radiographic image;

arranging the image data according to a predetermined image orientation;

forming a set comprising one or more regions of interest located proximate the border of the image;

analyzing image content of each region of interest of the set to identify a region having clipped anatomy; and displaying at least a portion of the image with the clipped anatomy identified.

2. The method of claim 1 wherein forming the set of regions of interest comprises:

locating one or more reference features from the radiographic image;

calculating patient size and position according to the located reference features; and

identifying one or more regions of interest according to the calculated patient size and position and according to the one or more reference features.

3. The method of claim 2 wherein the one or more reference features indicate the location of the lungs.

4. The method of claim 1 wherein analyzing image content in each region in the set and identifying any region with clipped anatomy further comprises:

extracting at least one image feature according to at least one image characteristic;

forming a feature vector for the at least one image feature;

applying feature reduction to the feature vector for the extracted image feature to obtain a reduced image feature vector;

applying a trained classifier to assess the reduced image feature vector; and

generating a probability value of clipped anatomy according to results from the trained classifier.

5. The method of claim 4 wherein applying feature reduction comprises using principal component analysis.

6. The method of claim 4 wherein forming a feature vector comprises using dimensional data from the at least one extracted image feature.

7. The method of claim 1 wherein the image data is from a chest x-ray.

8. The method of claim 1 further comprising printing at least a portion of the image with the clipped anatomy highlighted.

9. The method of claim 1 wherein the one or more reference features indicate the location of the spine.

10. The method of claim 1 further comprising sub-sampling the image to reduce the amount of image data that is processed for clipped anatomy detection.

11. The method of claim 1 wherein analyzing image content comprises sub-sampling the image data.

12. A method for detecting clipped anatomy in a radiographic image, executed by a processor, comprising:

obtaining image data for the radiographic image;

arranging the image data according to a predetermined image orientation;

outlining anatomical structures in the image;

analyzing the position and geometrical properties of the anatomical structures in the image and identifying one or more clipped anatomical structures; and displaying at least a portion of the image with the clipped anatomy highlighted.

13. The method of claim 12 wherein outlining anatomical structures in the image comprises applying digital unsharp masking.

14. A method for detecting clipped anatomy in a radiographic image, executed by a processor, comprising:

obtaining image data for the radiographic image;

arranging the image data according to a predetermined image orientation;

forming a set comprising one or more regions of interest that are located near the borders of the image by:

(a) locating one or more reference features from the image;

calculating patient size and position according to the located reference features; and

(c) identifying the one or more regions of interest according to the calculated patient size and position and according to the one or more reference features; and

analyzing image content in each region of interest in the set and identifying one or more regions with clipped anatomy.

Assignments (12)