METHOD AND APPARATUS FOR PROVIDING MEASUREMENT DATA OF AN ANOMALY IN A MEDICAL IMAGE

• US 20100189325A1
• Filed: 01/23/2009
• Published: 07/29/2010
• Est. Priority Date: 01/23/2009
• Status: Active Grant

• Current Assignee: Naveen Garg
• Original Assignee: Naveen Garg
• Inventors: Garg, Naveen
• Granted Patent: US 8,290,231 B2
• Time in Patent Office: Days
• US Class Current: 382/131
• CPC Class Codes: G06F 18/40 Software arrangements specially adapted for pattern recognition, e.g. user interfaces or toolboxes therefor
• CPC Class Codes: G06T 2200/24 involving graphical user interfaces [GUIs]
• CPC Class Codes: G06T 2207/10072 Tomographic images
• CPC Class Codes: G06T 2207/10116 X-ray image
• CPC Class Codes: G06T 2207/20104 Interactive definition of region of interest [ROI]
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/60 Analysis of geometric attributes
• CPC Class Codes: G06V 10/44 Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
• CPC Class Codes: G06V 10/945 User interactive design; Environments; Toolboxes

Abstract

Many image processing problems are concerned with determining measurements of an anomalous area in an image. Most automated systems suffer from low specificity, which may reduce their acceptance. An example embodiment of the present invention relates to a method and corresponding apparatus for providing measurement data of a region of interest in an image in a graphical user interface environment. The example embodiment locates a pair of edges in multiple dimensions of a region of interest selected by a user, calculates a center position between respective edges, and iterates until a convergence or divergence is determined. Linear calculation may be employed for rapid results, allowing an advance in speed of image processing over current techniques. In a case of convergence, the measurement data is reported. In a case of divergence, a failure state is reported. By reporting divergence, the example embodiment achieves high specificity, thereby reducing the number of false positive reports.

Claims

1. A method for providing measurement data of a region of interest in an image in a graphical user interface (GUI) environment, the method comprising:

locating a pair of edges in first and second dimensions of the region of interest selected by a user in a pixel field presented in the GUI;

calculating a center position between respective edges in the first and second dimensions;

repeating the locating and calculating until a convergence or divergence is determined;

computing the measurement data based on a final center position relative to edges associated with the final center position in an event convergence is determined; and

reporting the measurement data in the event convergence is detected or reporting a failure state in an event divergence is detected.

2. The method of claim 1 further including compensating for noise during the locating of the pairs of edges as a function of at least one:

averaging multiple pixels at each pixel position along each dimension during the locating of the edges or smoothing multiple pixels at each pixel position along each dimension during the locating of the edges.

3. The method of claim 1 further including locating the pair of edges as a function of at least one of:

identifying a pixel value deviation corrected for noise, transitioning outward from the center position along a single pixel line in the first and second dimensions until the respective pairs of edges are identified, using a gray-scale of the GUI and not a gray-scale of pixel values of the pixel field, or employing information stored in a Digital Imaging and Communications in Medicine (DICOM) image.

4. The method of claim 1 wherein computing the measurement data includes computing at least one of:

a size of the region of interest, a density of the region of interest optionally by computing the density of the region of interest as a function of using a gray-scale of the GUI, a texture of the region of interest, a position of the region of interest within the pixel field, a distance of the region of interest from the initial center position, or a distance of the region of interest from a second region of interest.

5. The method of claim 1 wherein the pixel field presented in the GUI is a radiological image, computed tomography image, or X-ray image and the region of interest selected by the user is an anomaly detected in a radiological image.

6. The method of claim 1 further including at least one of the following:

locating the pair of edges in response to a selection of a point in the region of interest by the user, repeating the locating and calculating for a selectable number of times, repeating the locating and calculating in the first or second dimensions but not both, or allowing divergence after repeating the locating and calculating for a predetermined number of times.

7. The method of claim 1 wherein the first and second dimensions are orthogonal dimensions.

8. The method of claim 1 wherein the region of interest is non-homogenous.

9. The method of claim 1 further including calibrating the measurement data based on a resolution of the screen.

10. The method of claim 1 wherein the reporting of the measurement data includes at least one of the following:

superimposing the measurement data on the pixel field, transmitting the measurement data via a data network, or storing the measurement data to a storage unit and optionally storing the measurement data in an electronic format.

11. An apparatus for providing measurement data of a region of interest in an image in a graphical user interface environment, the apparatus comprising:

a locator module to locate a pair of edges in first and second dimensions of the region of interest selected by a user in a pixel field presented in a GUI;

a calculation module to calculate an initial center position between respective edges in the first and second dimensions, the locator and calculation module continuing to locate and calculate until a convergence or divergence is determined;

a measurement data computation module to compute measurement data based on a final center position relative to edges associated with the final center position in an event convergence is determined; and

a reporting module to report the measurement data in the event convergence is detected or reporting a failure state in an event divergence is detected.

12. The apparatus of claim 11 wherein the locator module is configured to compensate for noise during the locating of the pairs of edges as a function of at least one of:

averaging multiple pixels at each pixel position along each dimension during the locating of the edges, or smoothing multiple pixels at each pixel position along each dimension during the locating of the edges.

13. The apparatus of claim 11 wherein the locator module is configured to locate the pair of edges as a function of at least one of:

identifying a pixel value deviation corrected for noise, transitioning outward from the center position along a single pixel line in the first and second dimensions until the respective pairs of edges are identified, using a gray-scale of the GUI and not a gray-scale of pixel values of the pixel field, or employing information stored in a DICOM image.

14. The apparatus of claim 11 wherein the measurement data computation module is configured to compute the measurement data as a function of computing at least one of:

a size of the region of interest, a density of the region of interest optionally by computing the density of the region of interest as a function of using a gray-scale of the GUI, a texture of the region of interest, a position of the region of interest within the pixel field, a distance of the region of interest from the initial center position, or a distance of the region of interest from a second region of interest.

15. The apparatus of claim 11 wherein the pixel field presented in the GUI is a radiological image, computed tomography, or X-ray image and the region of interest selected by the user is an anomaly detected in a radiological image.

16. The apparatus of claim 11 wherein the locator module is arranged to locate the pair of edges in response to at least one of the followings:

a selection of a point in the region of interest by the user, repeating locating and calculating for a selectable number of times, repeating locating and calculating in the first or second dimensions but not both, or allowing divergence after repeating the locating and calculating for a predetermined number of times.

17. The apparatus of claim 11 wherein the first and second dimensions are orthogonal dimensions.

18. The apparatus of claim 11 wherein the region of interest is non-homogenous.

19. The apparatus of claim 11 further including a calibration module configured to calibrate the measurement data based on a resolution of the screen.

20. The apparatus of claim 11 wherein the reporting module is arranged to report the measurement data as a function of at least one of:

superimposing the measurement data on the pixel field, transmitting the measurement data via a data network, or storing the measurement data to a storage unit and optionally storing the measurement data in an electronic format.

21. A computer program product comprising a computer readable medium having computer readable code stored thereon, which, when executed by a processor, causes the processor to:

locate a pair of edges in first and second dimensions of the region of interest selected by a user in a pixel field presented in a GUI;

calculate an initial center position between respective edges in the first and second dimensions;

continue to locate and calculate until a convergence or divergence is determined;

compute measurement data based on a final center position relative to edges associated with the final center position in an event convergence is determined; and

report the measurement data in the event convergence is detected or reporting a failure state in an event divergence is detected.

22. A method of training an image screener, the method comprising:

presenting an image in a GUI including a pixel field having multiple potential regions of interest;

determining whether convergence or divergence occurs in an attempt to locate a center of a region of interest selected by the user in an automated manner;

reporting to the user whether the selected region of interest resulted in a convergence or divergence to enable the user to make future selections of regions of interest that will result in an automated convergence.

23. The method of claim 22 wherein the image screener is a radiologist and the image is a radiological image, including a computed tomography image.

24. A computer program product comprising a computer readable medium having computer readable code stored thereon, which, when executed by a processor, causes the processor to:

present an image in a GUI including a pixel field having multiple potential regions of interest;

determine whether convergence or divergence occurs in an attempt to locate a center of a region of interest selected by the user in an automated manner;

report to the user whether the selected region of interest resulted in a convergence or divergence to enable the user to make future selections of regions of interest that will result in an automated convergence.