Reflectance imaging and analysis for evaluating tissue pigmentation

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.

What is claimed: 
     
       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 
 estimating data of at least one pigmentation from the diffuse reflection component of the reflection image; 
 generating a pigmentation image from the data of the at least one pigmentation; and 
 performing a further operation on the pigmentation image including at least one of storing, processing and or displaying the pigmentation image, 
 wherein performing the training procedure includes determining parameters for generating the image of the at least one of estimating 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 the 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. 
     
     
       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 
 estimating data of at least one pigmentation from the diffuse reflection component of the reflection image; 
 generating a pigmentation image from the data of the at least one pigmentation; and 
 performing a further operation on the pigmentation image including at least one of storing, processing and or displaying the pigmentation 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 or a wavelength-dependent refractive index of air and skin. 
 
 
     
     
       9. The method of  claim 1 , wherein the first transformation is a function of at least one of a skin type and or an imaging apparatus used to capture the reflection image. 
     
     
       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 
 estimating data of at least one pigmentation from the diffuse reflection component of the reflection image; 
 generating a pigmentation image from the data of the at least one pigmentation; and 
 performing a further operation on the pigmentation image including at least one of storing, processing and or displaying the pigmentation image, 
 wherein the first transformation is a function of at least one of a skin type and or 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 or 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 a surface reflection component of the reflection image, including applying the first transformation to the reflection image, wherein performing the training procedure includes determining parameters for estimating the surface reflection component; and 
 generating a pigmentation image from the data of the at least one pigmentation an image of at least one of the diffuse reflection component or the surface reflection component of the reflection image. 
 
     
     
       15. The method of claim  14  1, wherein the data of the at least one pigmentation is indicative of at least one of hemoglobin, melanin, and or bilirubin. 
     
     
       16. The method of claim  14  1, 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 or a Red/Brown/X transformation. 
     
     
       17. The method of claim  14  1 comprising:
 performing a further operation on the pigmentation image including at least one of storing, processing and or displaying the pigmentation image. 
 
     
     
       18. The method of claim  17  1 comprising:
 adding shading information to the pigmentation image. 
 
     
     
       19. The method of  claim 1 , wherein the reflection image includes an N-dimensional color channel image or N images, each image representing a color-space color channel, where N≥2. 
     
     
       20. The method of claim 1, wherein generating the pigmentation image includes translating the data of the at least one pigmentation into at least one of a Red, Brown, or Yellow pseudo-colored image. 
     
     
       21. A computer implemented method of processing a reflection image of tissue comprising:
 estimating data of at least one pigmentation from the reflection image, including applying a transformation determined in a training procedure to the reflection image;   generating a pigmentation image from the data of the at least one pigmentation; and   performing a further operation on the pigmentation image including at least one of storing, processing or displaying the pigmentation image.   
     
     
       22. The method of claim 21, wherein the reflection image is a total reflection image, a polarized image, or a partially polarized image. 
     
     
       23. The method of claim 21, wherein the reflection image includes a Red/Green/Blue (RGB) image. 
     
     
       24. The method of claim 21, wherein the reflection image includes an N-dimensional color channel image or N images, each image representing a color channel, where N≥2. 
     
     
       25. The method of claim 21, wherein the data of the at least one pigmentation is indicative of at least one of hemoglobin, melanin, and bilirubin. 
     
     
       26. The method of claim 21, wherein the transformation is determined in accordance with at least one of a color-space transformation, a principle component analysis (PCA), an independent component analysis (ICA), or a Red/Brown/X transformation. 
     
     
       27. The method of claim 21 comprising:
 adding shading information to the pigmentation image.   
     
     
       28. The method of claim 21, wherein parameters for generating the pigmentation image include at least one of scaling, quantization, or color translation parameters. 
     
     
       29. The method of claim 28, wherein the color translation parameters include parameters for translating the data of the at least one pigmentation into at least one of a Red, Brown, or Yellow pseudo-colored image. 
     
     
       30. The method of claim 21, wherein 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, or a wavelength-dependent refractive index of air and skin.   
     
     
       31. The method of claim 21, wherein the transformation is a function of at least one of a skin type or an imaging apparatus used to capture the reflection image. 
     
     
       32. The method of claim 21 comprising:
 estimating at least one of a diffuse reflection component or a surface reflection component of the reflection image, including applying another transformation to the reflection image;   generating an image of at least one of the diffuse reflection component or the surface reflection component of the reflection image; and   performing a further operation on the image of the at least one of the diffuse reflection component or the surface reflection component of the reflection image, including at least one of storing, processing or displaying the image of the at least one of the diffuse reflection component or the surface reflection component of the reflection image.   
     
     
       33. Apparatus for processing a reflection image of tissue comprising:
 a storage device for storing instructions; and   a processor configured to process the instructions to:
 estimate data of at least one pigmentation from the reflection image, including applying a transformation determined in a training procedure to the reflection image; 
 generate a pigmentation image from the data of the at least one pigmentation; and 
 perform a further operation on the pigmentation image including at least one of storing, processing or displaying the pigmentation image. 
   
     
     
       34. The apparatus of claim 33, wherein the reflection image is a total reflection image, a polarized image, or a partially polarized image. 
     
     
       35. The apparatus of claim 33, wherein the reflection image includes a Red/Green/Blue (RGB) image. 
     
     
       36. The apparatus of claim 33, wherein the reflection image includes an N-dimensional color channel image or N images, each image representing a color channel, where N≥2. 
     
     
       37. The apparatus of claim 33, wherein the data of the at least one pigmentation is indicative of at least one of hemoglobin, melanin, or bilirubin. 
     
     
       38. The apparatus of claim 33, wherein the transformation is determined in accordance with at least one of a color-space transformation, a principle component analysis (PCA), an independent component analysis (ICA), or a Red/Brown/X transformation. 
     
     
       39. The apparatus of claim 33, wherein parameters for generating the pigmentation image include at least one of scaling, quantization, or color translation parameters. 
     
     
       40. The apparatus of claim 39, wherein the color translation parameters include parameters for translating the data of the at least one pigmentation into at least one of a Red, Brown, or Yellow pseudo-colored image. 
     
     
       41. The apparatus of claim 33, wherein the transformation is a function of at least one of a skin type or an imaging apparatus used to capture the reflection image. 
     
     
       42. The apparatus of claim 33 wherein the processor is configured to process instructions to:
 estimate at least one of a diffuse reflection component and a surface reflection component of the reflection image, including applying another transformation to the reflection image;   generate an image of at least one of the diffuse reflection component and the surface reflection component of the reflection image; and   perform a further operation on the image including at least one of storing, processing or displaying the image.   
     
     
       43. The apparatus of claim 33 comprising an image capture device, wherein the reflection image of tissue is captured by the image capture device. 
     
     
       44. A non-transitory computer-readable storage medium having stored thereon a computer program for processing a reflection image of tissue, the computer program comprising instructions for causing a computer to:
 estimate data of at least one pigmentation from the reflection image, including applying a transformation determined in a training procedure to the reflection image;   generate a pigmentation image from the data of the at least one pigmentation; and   perform a further operation on the pigmentation image including at least one of storing, processing or displaying the pigmentation image.   
     
     
       45. The storage medium of claim 44, wherein the transformation is a function of at least one of a skin type or an imaging apparatus used to capture the reflection image.