Systems and methods for identifying an imaged needle in an ultrasound image

1. A method of identifying an imaged needle in an ultrasound image, the method comprising:

performing edge detection on the ultrasound image to generate an edge-detected data set corresponding to the ultrasound image;

performing a straight line detection operation on the edge-detected data set to detect one or more straight lines;

based on the one or more straight lines detected in the edge-detected data set, identifying a region of interest (ROI) on the ultrasound image;

transforming the ROI of the ultrasound image from a spatial domain to an analysis domain, to generate a transformed ROI;

analyzing the transformed ROI to determine whether the transformed ROI, in the analysis domain, corresponds to a needle signature; and

if the transformed ROI corresponds to the needle signature, identifying the detected one or more straight lines as the imaged needle.

2. The method of claim 1 , wherein the transforming comprises performing a Fourier transform on the ROI, and the analysis domain comprises the spatial frequency domain.

3. The method of claim 1 , wherein the transformed ROI comprises first pixel values in the analysis domain having a first orientation relationship, and the needle signature comprises a second orientation relationship, and the analyzing comprises comparing the first orientation relationship of the first pixel values to the second orientation relationship.

4. The method of claim 3 , wherein the first orientation relationship comprises a linearity measurement of the first pixel values, and the second orientation relationship comprises a threshold for the linearity measurement.

5. The method of claim 4 , wherein the linearity measurement comprises an eigenvalue ratio of the first pixel values.

6. The method of claim 1 , wherein prior to performing the straight line detection operation, the method further comprises:

performing a contour filtering operation on the edge-detected data set.

7. The method of claim 1 , wherein the straight line detection operation comprises a Hough transform operation.

8. The method of claim 1 , further comprising clustering the one or more straight lines detected on the edge-detected data set.

9. The method of claim 8 , wherein the identifying the ROI is based on a density of the clustered one or more straight lines.

10. The method of claim 8 , wherein the clustering results in groups of clustered lines, and the identifying the ROI is based on respective sizes of the groups of clustered lines.

11. The method of claim 1 , wherein the edge-detected data set comprises a binary image corresponding to the ultrasound image.

12. The method of claim 1 , further comprising downsampling the ultrasound image, and wherein the edge detection is performed on the downsampled ultrasound image.

13. The method of claim 1 , wherein upon identifying the detected one or more straight lines as the imaged needle, the method further comprises:

creating a mask highlighting the imaged needle; and

combining the mask with the ultrasound image.

14. The method of claim 13 , wherein the mask is upsampled prior to the combining of the mask with the ultrasound image.

15. An ultrasound imaging apparatus for identifying an imaged needle in an ultrasound image comprising:

a processor; and

a memory storing instructions for execution by the processor, wherein when the instructions are executed by the processor, the processor is configured to:

perform edge detection on the ultrasound image to generate an edge-detected data set corresponding to the ultrasound image;

perform a straight line detection operation on the edge-detected data set to detect one or more straight lines;

based on the one or more straight lines detected in the edge-detected data set, identify a region of interest (ROI) on the ultrasound image;

transform the ROI of the ultrasound image from a spatial domain to an analysis domain, to generate a transformed ROI;

analyze the transformed ROI to determine whether the transformed ROI, in the analysis domain, corresponds to a needle signature; and

if the transformed ROI corresponds to the needle signature, identify the detected one or more straight lines as the imaged needle.

16. The ultrasound imaging apparatus of claim 15 , wherein the transform comprises performing a Fourier transform on the ROI, and the analysis domain comprises the spatial frequency domain.

17. The method of claim 15 , wherein the transformed ROI comprises first pixel values in the analysis domain having a first orientation relationship, and the needle signature comprises a second orientation relationship, and the analyzing comprises comparing the first orientation relationship of the first pixel values to the second orientation relationship.

18. The method of claim 17 , wherein the first orientation relationship comprises a linearity measurement of the first pixel values, and the second orientation relationship comprises a threshold for the linearity measurement.

19. A non-transitory computer readable medium storing instructions for identifying an imaged needle in an ultrasound image, the instructions for execution by a processor of a computing device, wherein when the instructions are executed by the processor, the processor is configured to:

perform edge detection on the ultrasound image to generate an edge-detected data set corresponding to the ultrasound image;

perform a straight line detection operation on the edge-detected data set to detect one or more straight lines;

based on the one or more straight lines detected in the edge-detected data set, identify a region of interest (ROI) on the ultrasound image;

transform the ROI of the ultrasound image from a spatial domain to an analysis domain, to generate a transformed ROI;

analyze the transformed ROI to determine whether the transformed ROI, in the analysis domain, corresponds to a needle signature; and

if the transformed ROI corresponds to the needle signature, identify the detected one or more straight lines as the imaged needle.

20. The computer readable medium of claim 19 , wherein the transform comprises performing a Fourier transform on the ROI, and the analysis domain comprises the spatial frequency domain.