Model-based grayscale registration of medical images

• US 20050013471A1
• Filed: 07/18/2003
• Published: 01/20/2005
• Est. Priority Date: 07/18/2003
• Status: Active Grant

• Current Assignee: Hologic Incorporated
• Original Assignee: R2 Technology, Inc. (Hologic Incorporated)
• Inventors: Karssemeijer, Nico, Snoeren, Peter R.
• Granted Patent: US 7,668,358 B2
• Time in Patent Office: Days
• US Class Current: 382/131
• CPC Class Codes: G06T 2207/30068 Mammography; Breast
• CPC Class Codes: G06T 7/35 using statistical methods

Abstract

Numerical image processing of two or more medical images to provide grayscale registration thereof is described, the numerical image processing algorithms being based at least in part on a model of medical image acquisition. The grayscale registered temporal images may then be displayed for visual comparison by a clinician and/or further processed by a computer-aided diagnosis (CAD) system for detection of medical abnormalities therein. A parametric method includes spatially registering two images and performing gray scale registration of the images. A parametric transform model, e.g., analog to analog, digital to digital, analog to digital, or digital to analog model, is selected based on the image acquisition method(s) of the images, i.e., digital or analog/film. Gray scale registration involves generating a joint pixel value histogram from the two images, statistically fitting parameters of the transform model to the joint histogram, generating a lookup table, and using the lookup table to transform and register pixel values of one image to the pixel values of the other image. The models take into account the most relevant image acquisition parameters that influence pixel value differences between images, e.g., tissue compression, incident radiation intensity, exposure time, film and digitizer characteristic curves for analog image, and digital detector response for digital image. The method facilitates temporal comparisons of medical images such as mammograms and/or comparisons of analog with digital images.

Claims

1. A method for grayscale registration of a first medical image and a second medical image, comprising the steps of:

spatially registering the first medical image and the second medical image relative to each other;

generating at least one pixel value histogram based on pixel values of the first and second medical images;

generating a lookup table based at least in part on the at least one pixel value histogram, a first image acquisition method for the first medical image and a second image acquisition method for the second medical image; and

applying the lookup table to the pixel values of the first medical image to generate a third medical image, the third medical image being transformed from the first medical image and registered to the second medical image.

2. The method of claim 1, wherein the step of generating at least one pixel value histogram includes generating ajoint pixel value histogram of the first and second medical images.

3. The method of claim 1, wherein the step of generating the lookup table includes:

selecting a parametric transform function from a plurality of predetermined, parametric transform functions based on the first and second medical image acquisition methods for the first and second medical images, respectively; and

statistically fitting parameters of the selected parametric transform function to the at least one pixel value histogram, the statistically fitting determines values of the parameters, wherein the lookup table is generated using the selected parametric transform function and the values of the fitted parameters.

4. The method of claim 3, wherein the plurality of predetermined parametric transform functions are one-dimensional monotonic functions.

5. The method of claim 3, wherein each of the first and second medical image is selected from a digitized analog image and a digitally acquired image and wherein the plurality of predetermined parametric transform functions includes:

(1) a function for registering a digitized analog image to another digitized analog image, (2) a function for registering a digitally acquired image to another digitally acquired image, (3) a function for registering a digitally acquired image to a digitized analog image, and (4) a function for registering a digitized analog image to a digitally acquired image.

6. The method of claim 3, wherein each of the plurality of predetermined parametric transform functions models image acquisition parameters, the image acquisition parameters being at least one of incident radiation intensity, exposure time, film characteristic curve for an analog image, digitizer characteristic for digitizing an analog image, and digital detector response for a digitally acquired image.

7. The method of claim 3, wherein each of the first and second medical images is a mammogram, and wherein each of the plurality of predetermined parametric transform functions models image acquisition parameters, the image acquisition parameters being at least one of breast thickness, incident radiation intensity, exposure time, film characteristic curve for an analog image, digitizer characteristic for digitizing an analog image, and digital detector response for a digitally acquired image.

8. The method of claim 1, further comprising the steps of:

performing computer aided detection process for comparing the second and third medical images; and

displaying the second and third medical images with results of said computer aided detection process.

9. The method of claim 1, wherein spatially registering the first and second medical images includes at least one of translating, rotating, shearing and scaling at least one of the first and second medical images.

10. The method of claim 1, wherein each of the first and second medical images includes a target portion and a remainder portion and wherein spatially registering the first and second medical images includes segmenting the target portion and the remainder portion of each of the first and second medical images.

11. The method of claim 1, wherein each of the first and second medical images includes a target portion and a remainder portion and wherein spatially registering the first and second medical images includes cropping each of the first and second medical images to contain only the target portion that is in both the first and second medical images.

12. The method of claim 11, wherein the at least one pixel value histogram is generated based on pixel values of only the cropped first and second medical images.

13. The method of claim 1, wherein spatially registering the first and second medical images includes optimization of an entropy correlation coefficient of the first and second medical images.

14. A method for registering a first medical image to a second medical image, comprising the steps of:

generating a joint pixel value histogram using pixel values of the first and second medical images;

selecting a parametric transform function from a plurality of predetermined parametric transform functions, the selecting being based on a first medical image acquisition method for the first medical image and a second medical image acquisition method for the second medical image; and

statistically fitting parameters of the selected parametric transform function to the joint pixel value histogram, the statistically fitting determines values of the parameters.

15. The method of claim 14, further comprising:

generating a lookup table using the selected parametric transform function and the values of the fitted parameters; and

applying the lookup table to the pixel values of the first medical image to generate a third medical image, the third medical image being transformed from the first medical image and registered to the second medical image.

16. The method of claim 14, further comprising the steps of:

performing computer aided detection process for comparing the second and third medical images; and

displaying the second and third medical images with results of said computer aided detection process.

17. The method of claim 14, wherein the plurality of predetermined parametric transform functions are one-dimensional monotonic functions.

18. The method of claim 14, wherein each of the first and second medical image is selected from a digitized analog image and a digitally acquired image and wherein the plurality of predetermined parametric transform functions includes:

(1) a function for registering a digitized analog image to another digitized analog image, (2) a function for registering a digitally acquired image to another digitally acquired image, (3) a function for registering a digitally acquired image to a digitized analog image, and (4) a function for registering a digitized analog image to a digitally acquired image.

19. The method of claim 14, wherein each of the plurality of predetermined parametric transform functions models image acquisition parameters, the image acquisition parameters being at least one of incident radiation intensity, exposure time, film characteristic curve for an analog image, digitizer characteristic for digitizing an analog image, and digital detector response for a digitally acquired image.

20. The method of claim 14, wherein each of the first and second medical images is a mammogram, and wherein each of the plurality of predetermined parametric transform functions models image acquisition parameters, the image acquisition parameters being at least one of breast thickness, incident radiation intensity, exposure time, film characteristic curve for an analog image, digitizer characteristic for digitizing an analog image, and digital detector response for a digitally acquired image.

21. The method of claim 14, further comprising spatially registering the first medical image and the second medical image relative to each other.

22. The method of claim 21, wherein spatially registering the first and second medical images includes at least one of translating, rotating, shearing and scaling at least one of the first and second medical images.

23. The method of claim 21, wherein each of the first and second medical images includes a target portion and a remainder portion and wherein spatially registering the first and second medical images includes segmenting the target portion and the remainder portion of each of the first and second medical images.

24. The method of claim 21, wherein each of the first and second medical images includes a target portion and a remainder portion and wherein spatially registering the first and second medical images includes cropping each of the first and second medical images to contain only the target portion that is in both the first and second medical images.

25. The method of claim 24, wherein the joint pixel value histogram is generated based on pixel values of only the cropped first and second medical images.

26. The method of claim 21, wherein spatially registering the first and second medical images includes optimization of an entropy correlation coefficient of the medical images.

27. A system for registering a first medical image to a second medical image, comprising:

an input for receiving data for the first and second medical images; and

a processor configured to generate a joint pixel value histogram using pixel values of the first and second medical images, select a parametric transform function from a plurality of predetermined parametric transform functions based on a first image acquisition method for the first medical image and a second image acquisition method for the second medical image, and statistically fit parameters of the selected parametric transform function to the joint histogram to determine the values of the parameters.

28. The system of claim 27, wherein the processor is further configured to generate a lookup table using the selected parametric transform function and the values of the fitted parameters and to apply the lookup table to the pixel values of the first medical image to generate a third medical image, the third medical image being transformed from the first medical image and registered to the second medical image.

29. The system of claim 27, wherein the processor is further configured to perform a computer aided detection process for comparing the second and third medical images, the system further comprising:

a display for displaying the second and third medical images with results of the computer aided detection process.

30. The system of claim 27, wherein the plurality of predetermined parametric transform functions are one-dimensional monotonic functions.

31. The system of claim 27, wherein each of the first and second medical images is selected from a digitized analog image and a digitally acquired image and wherein the plurality of predetermined parametric transform functions includes:

(1) a function for registering a digitized analog image to another digitized analog image, (2) a function for registering a digitally acquired image to another digitally acquired image, (3) a function for registering a digitally acquired image to a digitized analog image, and (4) a function for registering a digitized analog image to a digitally acquired image.

32. The system of claim 27, wherein each of the plurality of predetermined parametric transform functions models image acquisition parameters, the image acquisition parameters being at least one of incident radiation intensity, exposure time, film characteristic curve for an analog image, digitizer characteristic for digitizing an analog image, and digital detector response for a digitally acquired image.

33. The system of claim 27, wherein the processor is further configured to spatially register the first medical image and the second medical image relative to each other.

34. The system of claim 33, wherein the processor is further configured to spatially register the first and second medical images by at least one of translating, rotating, shearing and scaling at least one of the first and second medical images.

35. The system of claim 33, wherein each of the first and second medical image includes a target portion and a remainder portion and wherein the processor spatially registers the first and second medical images by segmenting the target portion and the remainder portion of each of the first and second medical images.

36. The system of claim 33, wherein each of the first and second medical images includes a target portion and a remainder portion and wherein the processor is further configured to crop each of the first and second medical images to contain only the target portion that is in both the first and second medical images.

37. The system of claim 36, wherein the processor is further configured to generated the joint pixel value histogram based on pixel values of only the cropped first and second medical images.

38. The system of claim 33, wherein the processor is further configured to spatially register the first and second medical images by optimizing an entropy correlation coefficient of the first and second medical images.

39. A computer program product for directing a computing apparatus to automatically register a first medical image and a second medical image, comprising:

computer code for generating a joint pixel value histogram using pixel values of the first and second medical images;

computer code for selecting a parametric transform function from a plurality of predetermined parametric transform functions, the selecting being based on a first image acquisition method for the first medical image and a second image acquisition method for the second medical image; and

computer code for statistically fitting parameters of the selected parametric transform function to the joint pixel value histogram, the statistically fitting determines values of the parameters.

40. A computer program product for directing a computing apparatus to automatically register a first medical image and a second medical image, comprising:

computer code for spatially registering the first medical image and the second medical image relative to each other;

computer code for generating at least one pixel value histogram based on pixel values of the first and second medical images;

computer code for generating a lookup table based on the at least one pixel value histogram, a first image acquisition method for the first medical image and a second image acquisition method for the second medical image; and

computer code for applying the lookup table to the pixel values of the first medical image to generate a third medical image, the third medical image being transformed from the first medical image and registered to the second medical image.