Reflectance imaging and analysis for evaluating tissue pigmentation

• US 8,498,460 B2
• Filed: 02/22/2011
• Issued: 07/30/2013
• Est. Priority Date: 02/22/2010
• Status: Active Grant

• Current Assignee: Canfield Scientific Incorporated
• Original Assignee: Canfield Scientific Incorporated
• Inventors: Patwardhan, Sachin V.
• Primary Examiner(s): Fitzpatrick, Atiba O
• Application Number:
  US13/032,341
• Publication Number:
  US 20110206254A1
• Time in Patent Office: 889 Days
• Field of Search: 382128-134, 128920-925, 356 39- 49, 600407-414, 600424-426, 345581-618
• 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 5/441 Skin evaluation, e.g. for skin disorder diagnosis
• 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

Abstract

Methods and apparatus are described that provide the ability to estimate the diffuse reflection component of an image of tissue such as skin captured without cross-polarization. It is thereby possible to estimate skin pigmentation information from an image of skin captured conventionally, such as, for example, a total reflection image, obtained in a conventional manner by shining white light on the skin and capturing the reflected light. The image may also be a partially diffuse reflection image, such as a low quality cross-polarized image. The diffuse reflection component of a captured image can then be further processed to obtain Red and Brown pigmentation images, useful for indicating the distribution of hemoglobin and melanin, the primary chromophores of skin. Additionally, a standard captured image of skin can be analyzed to obtain an estimate of the surface reflection component of the reflected light. The surface reflection component can then be used to generate a surface reflection image, useful for showing the distribution of light on the skin and to highlight superficial features such as wrinkles, fine lines, folds, pores, texture, and visible spots.

Claims

1. A computer implemented method of processing a reflection image of tissue comprising:

performing a training procedure, including determining a first transformation;

estimating at least one of a diffuse reflection component and a surface reflection component of the reflection image, including applying the first transformation to the reflection image;

generating an image of at least one of the diffuse reflection component and the surface reflection component of the reflection image; and

performing a further operation on the image including at least one of storing, processing and displaying the image,

wherein performing the training procedure includes determining parameters for generating the image of the at least one of the diffuse reflection component and the surface reflection component.

2. The method of claim 1, wherein the first transformation is determined in accordance with an independent component analysis (ICA).

3. The method of claim 1, wherein:

performing a training procedure includes determining a second transformation, and

the step of estimating includes applying the second transformation to the diffuse reflection component.

4. The method of claim 3, wherein performing the training procedure includes determining parameters for generating a pigmentation image.

5. The method of claim 1, wherein the reflection image is a total reflection image, a polarized image, or a partially polarized image.

6. The method of claim 1, wherein the reflection image includes a Red/Green/Blue (RGB) image.

7. The method of claim 1, wherein the reflection image is an N-dimensional channel space image, where N≧

2.

9. The method of claim 1, wherein the first transformation is a function of at least one of a skin type and an imaging apparatus used to capture the reflection image.

11. The method of claim 1, wherein the parameters include at least one of scaling, quantization, and color translation parameters.

12. The method of claim 3, wherein the parameters include at least one of scaling, quantization, and color translation parameters.

13. The method of claim 12, wherein the color translation parameters include parameters for translating the pigmentation image into at least one of a Red, Brown, and Yellow image.

14. The method of claim 1 comprising:

estimating data of at least one pigmentation from the diffuse reflection component of the reflection image; and

generating a pigmentation image from the data of the at least one pigmentation.

15. The method of claim 14, wherein the data of the at least one pigmentation is indicative of at least one of hemoglobin, melanin, and bilirubin.

16. The method of claim 14, wherein estimating data of the at least one pigmentation includes performing at least one of a color-space transformation, a principle component analysis (PCA), an independent component analysis (ICA), and a Red/Brown/X transformation.

17. The method of claim 14 comprising:

performing a further operation on the pigmentation image including at least one of storing, processing and displaying the pigmentation image.

18. The method of claim 17 comprising:

adding shading information to the pigmentation image.

19. The method of claim 1, wherein the reflection image includes N images, each image representing a color-space channel, where N≧

2.

8. A computer implemented method of processing a reflection image of tissue comprising:

performing a training procedure, including determining a first transformation;

estimating at least one of a diffuse reflection component and a surface reflection component of the reflection image, including applying the first transformation to the reflection image;

generating an image of at least one of the diffuse reflection component and the surface reflection component of the reflection image; and

performing a further operation on the image including at least one of storing, processing and displaying the image,

wherein performing the training procedure includes;

forming at least one measurement array from pixels of a plurality of training images; and

processing the at least one measurement array to account for at least one characteristic of an imaging apparatus used to capture the plurality of training images, wherein the at least one characteristic includes at least one of a wavelength-dependent output of an illumination source of the imaging apparatus, a wavelength-dependent response of a detector of the imaging apparatus, an illumination and detection configuration of the imaging apparatus, and a wavelength-dependent refractive index of air and skin.

10. A computer implemented method of processing a reflection image of tissue comprising:

performing a training procedure, including determining a first transformation;

estimating at least one of a diffuse reflection component and a surface reflection component of the reflection image, including applying the first transformation to the reflection image;

generating an image of at least one of the diffuse reflection component and the surface reflection component of the reflection image; and

performing a further operation on the image including at least one of storing, processing and displaying the image,

wherein the first transformation is a function of at least one of a skin type and an imaging apparatus used to capture the reflection image.