US 6,081,612 A · Systems and methods for the multispectral imaging and characterization of skin tissue

Abstract

Systems and methods for the multispectral imaging of skin tissue enables automatic characterization of the condition of a region of interest of the skin, based on direct digital imaging of the region of interest or the digitization of color photographic slides of the region of interest, illuminated by appropriately filtered light. Preferably, a digital image at a low spectral band is automatically segmented and that segmented mask is used to segment the other images by a digital processor. Parameters are estimated through wavelet maxima representations. Parameters related to the texture, asymmetry, blotchiness and border irregularities are also automatically estimated. The region of interest is automatically characterized by the digital processor, based on those parameters. The region of interest may include a skin lesion, in which case the present invention enables the characterization of the lesion as malignant or benign. The region of interest may also include wounds or burns.

Claims66

Dependent claims

A method of characterizing the condition of a region of interest of skin, wherein the absorption and scattering of light in different spectral bands by the region of interest is a function of the condition of the skin, the method comprising:

illuminating a portion of the skin including the region of interest by light in at least three spectral bands;
digitally imaging a portion of the skin including the region of interest at the at least three spectral bands with the light re-emitted by the portion of the skin to generate digital images comprising digital signals whose values are a function of the condition of the region of interest of the skin;
and
providing the digital images to a processor, wherein the processor:
segments the digital images by generating a segmentation mask defining the boundary of the region of interest from a digital image in any one of the at least three spectral bands;
computes at least one rotationally and translationally invariant statistical measure of coefficient distributions of the multiscale wavelet maxima representations of the digital images in each spectral band, which are functions of the texture of the region of interest determined by the segmentation mask;
characterizes the condition of the skin based on the estimated values;
and
outputs the characterization of the condition of the skin.

6 more elements

A system for characterizing the condition of a region of interest of skin, comprising:

a source of illumination of light in at least three spectral bands;
a camera for acquiring digital images of the region of interest based on the light re-emitted from the illuminated region of interest at each of the spectral bands, the digital image comprising digital signals whose values are a function of the condition of the region of interest;
memory for storing the digital images provided by the camera;
a digital processor programmed to perform the steps of:
segmenting the digital images stored in memory by generating a segmentation mask from a digital image in any one of the at least three spectral bands;
computing at least one rotationally and translationally invariant statistical measure of coefficient distributions for the multiscale wavelet maxima representations of the digital images in each spectral band, which are functions of the texture of the region of interest determined by the segmentation mask;
characterizing the condition of the skin based on the estimated values;
outputting the characterization of the region of interest.

5 more elements

A method of characterizing the condition of a region of interest of biological tissue, wherein the absorption and scattering of light in different spectral bands by the region of interest is a function of the condition of the tissue, the method comprising:

computing at least one rotationally and translationally invariant statistical measure of coefficient distributions of the multiscale wavelet maxima representations of at least three digital images of the region of interest, the at least three digital images formed by light of at least three wavelength bands, the statistical measure being a function of the texture of the region of interest;
and
characterizing the condition of the tissue based on the generated measure.

Dependencies are inferred from the claim text.

Systems and methods for the multispectral imaging and characterization of skin tissue

Life of this patent

Systems and methods for the multispectral imaging and characterization of skin tissue

Life of this patent

Abstract

Claims66