System and method for detection of acoustic shadows and automatic assessment of image usability in 3D ultrasound images
A method for automatically assessing medical ultrasound (US) image usability, includes extracting one or more features from at least one part of a medical ultrasound image, calculating for each feature a feature score for each pixel of the at least one part of the ultrasound image, and classifying one or more image pixels of the at least one part as either usable or unusable, based on a combination of feature scores for each pixel, where usable pixels have intensity values substantially representative of one or more anatomical structures.
1. A computer-implemented method for automatically assessing medical ultrasound (US) image usability, the method comprising the steps of:
extracting one or more features from at least one part of a medical ultrasound image;
calculating for each feature a feature score for each pixel of said at least one part of said ultrasound image; and
classifying one or more image pixels of said at least one part as either usable or unusable, based on a combination of feature scores for each pixel, wherein usable pixels have intensity values substantially representative of one or more anatomical structures.
2. The method of claim 1 , wherein extracting one or more features from the at least one part of the ultrasound image comprises:
labeling each pixel in the at least one part with a label that is inversely proportional to the size of the region to which it belongs, to calculate a dark regions score for each pixel;
scanning the at least one part of the image in each radial direction to measure a length of the at least one part from beginning to end, and assigning a grayscale value to each pixel indicating said length of the at least one part to which said pixel belongs, to calculate a radial extent score for each pixel;
calculating a maximum edge score by detecting edges in the at least one part of said image and assigning each pixel n the at least one part a maximum gradient of the at least one part;
forming for each pixel in the at least one part a vector in a feature space defined by its dark regions score, radial extent score, and maximum edge score; and
classifying each pixel in the at least one part of the image as either a bright usable pixel, a dark usable pixel, or a dark-unusable pixel based on its feature vector, wherein a usable region includes the bright usable pixels and the dark usable pixels, and a unusable region contains dark unusable pixels.
3. The method of claim 2 , further comprising segmenting the image into bright and dark regions based on Otsu's criteria.
4. The method of claim 3 , wherein calculating a maximum edge score comprises calculating for each pixel in a bright region a gradient intensity for that pixel.
5. The method of claim 2 , further comprising calculating a local intensity score and a local variance score for each pixel in the at least one part, wherein the Local Intensity is an average of the local intensity, and the Local Variance is its variance, and incorporating said local intensity score and said local variance score as additional dimensions in said feature space.
6. The method of claim 2 , wherein said edges are detected using a Sobel filter on the image.
7. The method of claim 2 , further comprising calculating a mean edge score by assigning each pixel in the at least one part the mean gradient of the at least one part, and incorporating said mean edge score as an additional dimension in said feature space.
8. The method of claim 1 , further comprising training a 3-class classifier on pixels of the at least one part of said image in a feature space defined by the feature scores for each feature that can classify a pixel as a bright usable pixel, a dark usable pixel, or a dark-unusable pixel, wherein the usable pixels include the bright usable pixels and the dark-usable pixels.
9. The method of claim 8 , wherein training a 3-class classifier comprises training a binary classifier to determine whether or not a pixel is a bright pixel or a dark pixel, and training a binary classifier to determine whether the dark pixel is a dark-usable pixel or a dark-unusable pixel.
10. The method of claim 9 , wherein said binary classifier is a support vector machine.
11. A method for automatically assessing medical ultrasound (US) image usability, the method comprising the steps of:
segmenting a medical ultrasound image into bright and dark regions;
labeling each pixel in the dark regions with a label that is inversely proportional to the size of the region to which it belongs, to calculate a dark regions score for each pixel;
scanning the image in each radial direction to measure a length of each crossed dark region from beginning to end, and assigning a grayscale value to each pixel indicating said length of the dark region to which said pixel belongs, to calculate a radial extent score for each pixel;
calculating a maximum edge score by detecting edges in said image and assigning each pixel in a dark region a maximum gradient of the dark region;
forming for each pixel a vector in a feature space defined by its dark regions score, radial extent score, and maximum edge score; and
training a 3-class classifier on pixels in said feature space that can classify a pixel as a bright usable pixel, a dark usable pixel, or a dark-unusable pixel.
12. The method of claim 11 , further comprising applying the classifier to classify pixels on a new US image as either bright usable pixels, dark usable pixels, or dark-unusable pixels.
13. The method of claim 11 , wherein training a 3-class classifier comprises training a binary classifier to determine whether or not a pixel is a useful bright pixel of a dark pixel, and training a binary classifier to determine whether the dark pixel is a dark-usable pixel or a dark-unusable pixel, wherein said binary classifier is a support vector machine.
14. A program storage device readable by a computer, tangibly embodying a program of instructions executable by the computer to perform the method steps for automatically assessing medical ultrasound (US) image usability, the method comprising the steps of:
extracting one or more features from at least one part of a medical ultrasound image;
calculating for each feature a feature score for each pixel of said at least one part of said ultrasound image; and
classifying one or more image pixels of said at least one part as either usable or unusable, based on a combination of feature scores for each pixel, wherein usable pixels have intensity values substantially representative of one or more anatomical structures.
15. The computer readable program storage device of claim 14 , wherein extracting one or more features from the at least one part of the ultrasound image comprises:
labeling each pixel in the at least one part with a label that is inversely proportional to the size of the region to which it belongs, to calculate a dark regions score for each pixel;
scanning the at least one part of the image in each radial direction to measure a length of the at least one part from beginning to end, and assigning a grayscale value to each pixel indicating said length of the at least one part to which said pixel belongs, to calculate a radial extent score for each pixel;
calculating a maximum edge score by detecting edges in the at least one part of said image and assigning each pixel in the at least one part a maximum gradient of the at least one part;
forming for each pixel in the at least one part a vector in a feature space defined by its dark regions score, radial extent score, and maximum edge score; and
classifying each pixel in the at least one part of the image as either a bright usable pixel, a dark usable pixel, or a dark-unusable pixel based on its feature vector, wherein a usable region includes the bright usable pixels and the dark usable pixels, and a unusable region contains dark unusable pixels.
16. The computer readable program storage device of claim 15 , the method further comprising segmenting the image into bright and dark regions based on Otsu's criteria.
17. The computer readable program storage device of claim 16 , wherein calculating a maximum edge score comprises calculating for each pixel in a bright region a gradient intensity for that pixel.
18. The computer readable program storage device of claim 15 , the method further comprising calculating a local intensity score and a local variance score for each pixel in the at least one part, wherein the Local Intensity is an average of the local intensity, and the Local Variance is its variance, and incorporating said local intensity score and said local variance score as additional dimensions in said feature space.
19. The computer readable program storage device of claim 15 , wherein said edges are detected using a Sobel filter on the image.
20. The computer readable program storage device of claim 15 , the method further comprising calculating a mean edge score by assigning each pixel in the at least one part the mean gradient of the at least one part, and incorporating said mean edge score as an additional dimension in said feature space.
21. The computer readable program storage device of claim 14 , the method further comprising training a 3-class classifier on pixels of the at least one part of said image in a feature space defined by the feature scores for each feature that can classify a pixel as a bright usable pixel, a dark usable pixel, or a dark-unusable pixel, wherein the usable pixels include the bright usable pixels and the dark-usable pixels.
22. The computer readable program storage device of claim 21 , wherein training a 3-class classifier comprises training a binary classifier to determine whether or not a pixel is a bright pixel or a dark pixel, and training a binary classifier to determine whether the dark pixel is a dark-usable pixel or a dark-unusable pixel.
23. The computer readable program storage device of claim 22 , wherein said binary classifier is a support vector machine.