Medical Image Processing

• US 20100158330A1
• Filed: 09/12/2006
• Published: 06/24/2010
• Est. Priority Date: 09/12/2005
• Status: Active Grant

• Current Assignee: DVP Technologies Ltd.
• Original Assignee: DVP Technologies Ltd.
• Inventors: Lavi, Eitan, Guissin, Avraham Rami
• Granted Patent: US 8,472,682 B2
• Time in Patent Office: Days
• US Class Current: 382/128
• CPC Class Codes: A61B 5/0077 Devices for viewing the surface of the body, e.g. camera, magnifying lens
• CPC Class Codes: A61B 5/1032 Determining colour for diagnostic purposes measuring colour in general G01J3/46
• CPC Class Codes: A61B 5/444 Evaluating skin marks, e.g. mole, nevi, tumour, scar
• CPC Class Codes: A61B 5/445 Evaluating skin irritation or skin trauma, e.g. rash, eczema, wound, bed sore
• CPC Class Codes: A61B 5/725 using specific filters therefor, e.g. Kalman or adaptive filters A61B5/316 take precedence
• CPC Class Codes: G06T 2207/10068 Endoscopic image
• CPC Class Codes: G06T 2207/20012 Locally adaptive
• CPC Class Codes: G06T 2207/30028 Colon; Small intestine
• CPC Class Codes: G06T 2207/30088 Skin; Dermal
• CPC Class Codes: G06T 2207/30092 Stomach; Gastric
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/90 Determination of colour characteristics
• CPC Class Codes: G06V 10/56 relating to colour
• CPC Class Codes: G06V 2201/03 Recognition of patterns in medical or anatomical images
• CPC Class Codes: G06V 40/103 Static body considered as a whole, e.g. static pedestrian or occupant recognition

Abstract

A method of image processing, including:

• (a) calculating at least one pixel color feature (PCF) value for each pixel in a color medical image to generate a set of PCF data; and
• (b) filtering the PCF data with at least one spatial adaptive bandpass filter (ABPF) to sort the pixels into physiologically significant regions;
  • wherein the at least one PCF value for at least one pixel depends on at least 2 color components of the medical image.

Claims

1. A method of image processing, the method comprising:

(a) calculating at least one pixel color feature (PCF) value for each pixel in a color medical image to generate a set of PCF data; and

(b) filtering the PCF data with at least one spatial adaptive bandpass filter (ABPF) to sort the pixels into physiologically significant regions;

wherein the at least one PCF value for at least one pixel depends on at least 2 color components of the medical image.

2. A method according to claim 1 wherein the PCF is solely a function of color components of the medical image.

3. A method according to claim 1 wherein the PCF is solely a function of color components of a pixel for which the PCF value is calculated.

4. A method according to claim 1 wherein the PCF is based on a ratio of the at least 2 color components.

5. A method according to claim 1, wherein calculating comprises calculating a color feature which matches a human visual ability.

6. A method according to claim 1, wherein calculating comprises calculating a color feature which matches a spectra of a tissue absorbance of interest.

7. A method of image processing according to claim 1, wherein practice of the method alters color Saturation and substantially preserves Hue of the image.

8. A method according to claim 1, wherein filtering comprises modifying a color of at least one pixel.

9. A method according to claim 1, wherein filtering comprises maintaining the color of substantially all the pixels in the image.

10. A method according to claim 9, comprising correcting the image after said filtering to maintain a color of said pixels.

11. A method according to claim 9, comprising limiting modification of said image to within saturation of at least one of a representation of said image and a display of said image.

12. A method according to claim 9, comprising separately filtering each color component of said image.

13. A method according to claim 1, wherein filtering comprises filtering with a plurality of bandpass filters.

14. A method according to claim 13, comprising combining the results of said filters.

15. A method of image processing according to claim 1, wherein the spatial adaptive bandpass filter defines edges of regions.

16. A method of image processing according to claim 1, wherein filtering comprises thresholding of spatial adaptive bandpass filter results.

17. A method of image processing according to claim 1, wherein the spatial adaptive bandpass filter defines regions without a priori size criteria.

18. A method of image processing according to claim 1, wherein filtering emphasizes at least one region of the image to indicate an amount of oxyhemoglobin.

19. A method of image processing according to claim 1, wherein filtering emphasizes at least one region to indicate an amount of deoxyhemoglobin.

20. A method of image processing according to claim 1, wherein the medical image is an endoscopic image.

21. A method of image processing according to claim 1, wherein the image is acquired using broadband light.

22. A method of image processing according to claim 1 wherein the image is acquired using narrowband light.

23. A method of image processing according to claim 1, wherein the PCF includes at least one term indicating a difference between color components.

24. A method of image processing according to claim 23, wherein the difference between color components is a difference between color components of the medical image.

25. A method of image processing according to claim 1, wherein the PCF functions as a spectral filter which emphasizes red in the image.

26. A method of image processing according to claim 1, wherein the PCF functions as a spectral filter which emphasizes blue in the image.

27. A method of image processing according to claim 1, wherein the PCF includes a normalization component.

28. A method of image processing according to claim 1, wherein the PCF functions as a spectral filter which evaluates similarity to at least one difference in a hemoglobin absorbance spectra.

29. A method of image processing according to claim 28, wherein the PCF functions as a spectral filter which evaluates similarity to at least two differences in a hemoglobin absorbance spectra.

30. A method of image processing according to claim 1, comprising repeating (a) and (b) at least two levels of sensitivity.

31. A method of image processing according to claim 30, comprising repeating (a) and (b) at least three levels of sensitivity.

32. A method of image processing according to claim 1, comprising repeating (a) and (b) at least two types of filtering result, one matched to human vision and one matched to tissue spectra.

33. A method of image processing according to claim 1, comprising repeating (a) on a result of (b).

34. A method of image processing according to claim 1, comprising applying (a) and (b) as a single combined filter.

35. A method of image processing, the method comprising:

(a) capturing a medical image using broadband light;

(b) calculating at least one pixel color feature (PCF) value for each pixel in a color medical image to generate a set of PCF data; and

(c) filtering the PCF data with at least one spatial filter to sort the pixels into physiologically significant regions.

36-55. -55. (canceled)

56. A method of image processing, the method comprising:

(a) capturing a color medical image using white light; and

(b) calculating at least two pixel color feature (PCF) values for each pixel in the image to generate a first set and a second set of PCF data;

(c) separately applying spatial filters to the first set of PCF data and the second set of PCF data; and

(d) combining the result of the separate applying.

57-63. -63. (canceled)

64. A method of image processing, the method comprising:

(a) acquiring an image with white light

(b) applying a first pixel color feature (PCF) to each pixel in the image to generate a first set of PCF data indicative of a first color characteristic;

(c) applying a second pixel color feature (PCF) to each pixel in the image to generate a second set of PCF data indicative of a second color characteristic; and

(d) sorting pixels into regions based upon comparison of each of the two sets of PCF data to reference values based upon a reference absorbance spectra.

65-69. -69. (canceled)

70. An apparatus for enhancement of a color medical image, the apparatus comprising:

(a) an input port adapted to receive a color medical image as digital data;

(b) filtration circuitry adapted to apply at least one spectral processing filter to each of a plurality of image pixels to evaluate a color feature of each pixel;

(c) sorting circuitry adapted to define at least one image region by applying an adaptive bandpass spatial filter to the enhanced color features of the pixels.

71-74. -74. (canceled)