Medical imaging method and system

• US 8,467,583 B2
• Filed: 04/04/2006
• Issued: 06/18/2013
• Est. Priority Date: 04/04/2005
• Status: Active Grant

• Current Assignee: Yissum Research Development Company of the Hebrew University of Jerusalem Ltd. (Hebrew University of Jerusalem)
• Original Assignee: Yissum Research Development Company of the Hebrew University of Jerusalem Ltd. (Hebrew University of Jerusalem)
• Inventors: Smith, Yoav, Czerninski, Rakefet
• Primary Examiner(s): Carter, Aaron W
• Application Number:
  US11/910,271
• Publication Number:
  US 20080260218A1
• Time in Patent Office: 2,632 Days
• Field of Search: 600/306, 128/922, 382/128, 382/167, 382/165, 382/118, 382/14
• 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 5/0088 for oral or dental tissue
• CPC Class Codes: A61B 5/1034 by means of colour cards
• CPC Class Codes: A61B 5/411 Detecting or monitoring allergy or intolerance reactions to an allergenic agent or substance
• 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 5/4547 Evaluating teeth
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/30088 Skin; Dermal
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/90 Determination of colour characteristics

Abstract

A computerized method and system for detection and quantification of changes in color on skin or internal tissue or organs within the human body. Digital images of the skin or tissue containing an area of interest are analyzed using the software of the invention, based on at least one channel of the LAB color system. The invention calculates the intensity and distribution of color present within the predetermined area of interest, and results in display of at least one color information attribute. The invention allows color calibration of the image to be performed in relation to a reference label having predetermined colors which surrounds the area of interest, prior to the analysis. The invention allows a threshold analysis to be performed, which graphically depicts the size and location of areas exhibiting significant change in color, which is a determinant factor in medical diagnosis.

Claims

1. A method for computerized analysis of particular color changes of specific clinical nature for all types of medical analysis pertaining to color, present in one image originating from at least one lesion in human body tissue, comprising:

a) placing a matching reference label having a plurality of reference colors, in the vicinity of every analyzed lesion, said reference label having a window cut in it and placed so as to surround the corresponding lesion size and shape associated with an area of interest (AOI) therein;

b) capturing a color image including every analyzed lesion and the corresponding reference label along with human tissue encompassing said reference label, wherein said image is a digital image or is converted into a digital image;

c) performing color calibration of the image using the LAB color system, said calibration comprising reading the color intensity value of at least one reference color from the reference label in the image, comparing said value to the true predetermined color intensity value of said reference color, and optionally correcting the digital data of the image in at least one channel within the LAB color system, for color distortion;

d) selecting the borders of said AOI within the image;

c) calculating the intensity and distribution of color within said area of interest in relation to said reference label using at least one channel of the LAB system, to give at least one color information attribute within a clinically relevant range; and

f) displaying said at least one color information attribute upon display means;

wherein at least steps (c) and (e) are performed by a processing means allowing color calibration and allowing calculation and display of said at least one color information attribute.

2. The method of claim 1 wherein an evaluation of the intensities of said reference colors on all sides of said window provides a clear indication of the level of homogeneity of illumination during said image capture activity.

3. The method of claim 1, wherein the calculation performed in step (e) for determining said at least one color information attribute is selected from at least one of the following:

a cumsum value, a threshold analysis, a histogram of a single LAB channel, the average color value measured in a predetermined LAB channel, the median color value of a predetermined LAB channel, the minimum color value measured in a predetermined LAB color channel, and the maximum color value measured in a predetermined LAB color channel.

4. The method of claim 3, wherein said cumsum value is a weighted average of the color intensity in an area of interest, for calculating the most predominant color in said area of interest.

5. The method of claim 3, wherein said threshold analysis is comprised of selecting a value of color intensity, and providing an indication within said image, of pixels above or equal to said value of color intensity.

6. The method of claim 1, further comprising the steps of performing a calculation relating to the size and shape of the area of interest, and displaying the result of said calculation on display means;

said calculation selected from at least one of the group consisting of;

calculating the size, calculating the relative magnification, calculating the equivalent diameter, and calculating the length of the major axis.

7. The method of claim 1, further comprising the step of staining said every analyzed lesion, prior to step (a) of placement of the reference label.

8. The method of claim 1, wherein said analysis is performed on at least two images, and said calculated color information attributes of both of said images are displayed visually adjacent to one another, said two images representing images taken over time from a similar area of a single person, or said two images representing two different areas of interest of a single person.

9. The method of claim 1, wherein said images are received from a distant location, and are transmitted in a format having digital image information contained within, to a central diagnostic center capable of performing color calibration, and capable of calculating said at least one color information attribute and of interpreting its relevance.

10. The method of claim 1, further allowing mathematical comparison of said at least one calculated color information attribute, to a database of color information attributes determined from images captured from a plurality of people.

11. The method of claim 1 for use in instances in which the intensity of the color is related to progression or regression of a medical condition.

12. The method of claim 11, wherein said medical condition is selected from:

micro-organismic infection, inflammation, benign neoplasms, malignant neoplasms, reactive lesions, autoimmune diseases, vesiculoulcerative lesions, allergic reactions, dermatoses, congenital deformities, ulcerations, granulomatous disease and nutritional deficiencies.

13. The method of claim 12, wherein said neoplasm is selected from erythroplakia, leukoplakia, leukemia, and white lesions;

and wherein said micro-organismic infection is selected from herpetic infection, candidiasis, mucomycosis, leishmaniasis, abscesses, gingivitis, apotheosis, diffused infections; and

wherein said autoimmune disease is selected from psoriasis, contact stomatitis, Lichen Planus, Pemphigus, wherein said granulomatous disease is selected from Melkersson-Rosental syndrome.

21. The method of claim 1, wherein said tissue of the human body is selected from:

the mouth, the lips or the teeth.

22. The method of claim 1 wherein said tissue of the human body is selected from:

the epidermis, the epithelium of the oral cavity, the gastrointestinal tract or the female reproductive tract.

14. A system for computerized analysis of particular color changes of specific clinical nature for all types of medical analysis pertaining to color present in one image originating from at least one lesion in human body tissue, comprising:

a. a digital camera, or scanning means for converting image information into digital image information;

b. a reference label having a plurality of reference colors, said reference label having a window cut in it and being placed so as to surround an area of interest (AOI) in said lesion image,

wherein said lesion image includes human tissue encompassing said reference label;

c. calculation means for calculating the size and shape of said lesion; and

d. processing means comprising a memory device, a driver and display means, wherein said processing means is in communication with said memory device, and is configured to;

i. perform color calibration of the image using the LAB color system, said calibration comprising reading the color intensity value of at least one reference color from the reference label in the image, comparing said value to the true predetermined color intensity value of said reference color, and optionally correcting the digital data of the image in at least one channel within the LAB color system, for color distortion;

ii. calculate the intensity and distribution of color within an area of interest using at least one channel of the LAB system, to give at least one color information attribute within a clinically relevant range; and

iii. display said at least one color information attribute upon said display means.

15. The system of claim 14, wherein said calculation performed to give said at least one color information attribute, is selected from at least one of the following:

a cumsum value, a threshold analysis, a histogram of a single LAB channel, the average color value measured in a predetermined LAB channel, the median color value of a predetermined LAB channel, the minimum color value measured in a predetermined LAB color channel, and the maximum color value measured in a predetermined LAB color channel.

16. The system of claim 14, wherein said processing means is further configured to perform automatic detection of the reference colors upon said reference label.

17. The system of claim 14, wherein the LAB values of the reference colors on said reference label are L=100, L=0, A=50, A=0, B=50, B=0.

18. The system of claim 14, further comprising communication interface means allowing access to a communication system, allowing receipt of images from a distant location, said images being transmitted in a format having digital image information contained within, wherein said communication interface means enables transmission of a medical diagnosis to said distant location.

19. A non-transitory computer readable storage medium comprising software capable of:

a) performing color calibration of an image using the LAB color system, said calibration comprising reading the color intensity value of at least one reference color from a reference label present in an image, comparing said value to the true predetermined color intensity value of said reference color, and optionally correcting the digital data of the image in at least one channel within the LAB color system, for color distortion;

b) calculating the intensity and distribution of color within a predetermined area of interest (AOI) within said image, wherein said reference label has a window cut in it and is placed so as to surround said AOI so that said reference label is in close proximity to said image, using at least one channel of the LAB system, to give at least one color information attribute within a clinically relevant range,

wherein said image includes a region encompassing said reference label; and

c) directing display of said at least one color information attribute upon display means.

20. The non-transitory computer readable storage medium according to claim 19, wherein said calculation performed to give said at least one color information attribute is selected from at least one of the following:

a cumsum value, a threshold analysis, a histogram of a single LAB channel, the average color value measured in a predetermined LAB channel, the median of a predetermined LAB channel, the minimum color value measured in a predetermined LAB color channel, and the maximum color value measured in a predetermined LAB color channel.