US6081612A — Systems and methods for the multispectral imaging…

Claim 1

Independent Claim 218 words

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.

Claim 2

Independent Claim 218 words

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.

Claim 3

Dependent Claim 73 words

The method of claim 1, wherein the at least one statistical measure is calculated separately within either of a border region and an interior region of the digital image, wherein: the border region encompasses the envelope of circles of fixed radius centered on the boundary of the segmentation mask; and the inside region comprises all points of the image that are within the segmentation mask boundary but not included in the border region.

Claim 4

Dependent Claim 104 words

The method of claim 2, wherein the computing step comprises estimating at an individual level at least one value which is a statistical measure of texture of the portion of the region of interest within the border region and interior region, chosen from the group consisting of: the number of wavelet maxima per unit area; the ratio of the mean coefficient magnitude to the absolute deviation of the coefficient magnitudes from the mean value; the ratio of the mean coefficient magnitude to the standard deviation of the coefficient magnitudes; and the skewness of the coefficient magnitudes, normalized to the cube of the standard deviation.

Claim 5

Dependent Claim 38 words

The method of claim 1, further comprising estimating either of the degree of change of a statistic of the wavelet coefficient distribution with the increment of wavelet level, and the degree of deviation of such change from linearity.

Claim 6

Dependent Claim 26 words

The method of claim 2, further comprising estimating the average rate of change, with respect to level, of the number of wavelet maxima per unit area.

Claim 7

Dependent Claim 28 words

The method of claim 1, further comprising comparing the estimated texture values to the threshold derived from statistical analysis of a multiscale wavelet transformation of the digital image.

Claim 8

Dependent Claim 19 words

The method of claim 1, wherein the estimating and characterizing steps are conducted without the intervention of an operator.

Claim 9

Dependent Claim 17 words

The method of claim 1, wherein the segmenting step is conducted without the intervention of an operator.

Claim 10

Dependent Claim 19 words

The method of claim 1, wherein the illuminating step further comprises illuminating a region of interest including a burn.

Claim 11

Dependent Claim 24 words

The method of claim 9, wherein the characterizing step comprises characterizing the condition of the burn with respect to the condition of normal skin.

Claim 12

Dependent Claim 19 words

The method of claim 1, wherein the illuminating step further comprises illuminating a region of interest including a wound.

Claim 13

Dependent Claim 24 words

The method of claim 11, wherein the characterizing step comprises characterizing the condition of the wound with respect to the condition of normal skin.

Claim 14

Dependent Claim 55 words

The method of claim 1, further comprising: photographing the region of interest with a color camera to form color photographic slides; and illuminating the color photographic slides with light in each spectral band; wherein the digital imaging step comprises digitally imaging the illuminated color photographic slides of the region of interest with a digital camera.

Claim 15

Dependent Claim 37 words

The method of claim 1, wherein the computing step further comprises estimating a value which is a function of the asymmetry of the segmented image in each spectral band, for two principal axis of the segmented image.

Claim 16

Dependent Claim 20 words

The method of claim 1, wherein the computing step further comprises computing the intensity moment with a binary intensity distribution.

Claim 17

Dependent Claim 52 words

The method of claim 1, wherein the computing step further comprises estimating at least one value which is a function of the blotchiness of the segmented digital image, the estimated blotchiness value being defined through statistical properties of the spatial distribution of topographic regions of the digital images at each spectral band.

Claim 18

Dependent Claim 26 words

The method of claim 16, wherein the computing step further comprises determining the centroids of topographic regions of the segmented digital image at each spectral band.

Claim 19

Dependent Claim 47 words

The method of claim 1, wherein the computing step comprises estimating a value which is a statistical measure of the deviation of the border of the region of interest from the border of an ellipse of the same area, aspect ratio, and orientation as the segmentation mask.

Claim 20

Dependent Claim 36 words

The method of claim 1, wherein the computing step comprises estimating a statistical measure of the gradient values of the intensity of the digital images across the border of the segmented images, at each spectral band.

Claim 21

Dependent Claim 32 words

The method of claim 1, wherein the computing step comprises estimating values based on the ratio of standard deviation of the areas of dermal papillae to their mean within the segmentation mask.

Claim 22

Dependent Claim 28 words

The method of claim 1, wherein the computing step comprises estimating values of the average and standard deviation of the thickness of rete ridges within the segmentation mask.

Claim 23

Dependent Claim 21 words

The method of claim 1, wherein the characterizing step comprises distinguishing multiple times between melanoma and several types of benign lesion.

Claim 24

Dependent Claim 46 words

The method of claim 1, wherein the condition of the region of interest to be characterized is the presence of a melanoma and the processor compares a weighted combination of parameter values against a threshold value for melanoma and different types of benign lesions, multiple times.

Claim 25

Dependent Claim 43 words

The method of claim 1, wherein the segmentation mask is generated from a digital image in a spectral band in which the amount of light re-emitted by skin is less within skin having an abnormal condition than within skin having a normal condition.

Claim 26

Dependent Claim 26 words

The method of claim 1, wherein the segmenting step further comprises segmenting the digital images by generating a segmentation mask in more than one spectral band.

Claim 27

Dependent Claim 88 words

The method of claim 1, wherein prior to the computing step, the digital image is first segmented to locate the region of interest in the image, and said computing step further comprises: locating N topographic regions of the segmented image, wherein the nth such topographic regions is the locus of all pixels whose intensities line between I(n-1) and I(n), for n=1, 2, . . . , N; and calculating at least one quantity that represents a statistical property of the spatial distribution of pixels within a topographic region.

Claim 28

Dependent Claim 74 words

The method of claim 26, wherein the at least one quantity is chosen from the group consisting of: the means of the distances of all the pixels in a topographic region from the intensity centroid of the segmented image; the standard deviation of said distances; and the ratio of the area of a polygon defined by the intensity centroids of at least three different topographic regions to the total area of the segmented image.

Claim 29

Dependent Claim 119 words

The method of claim 1, wherein, in any spectral band, the digital image is segmented to locate the region of interest and the computing step further comprises: locating the principal axes of computing an orientation angle in the segmented image; rotating the segmented digital image such that the principal axes are parallel to the image axes; computing the difference in intensity between each pair of pixels with locations that are mirror images with respect to a principal axis; summing up the absolute values of intensity differences; calculating asymmetry values for each principal axis by normalizing the sum of intensity differences by the total intensity in the segmented images; and summing the estimated asymmetry values for the two principal axes.

Claim 30

Dependent Claim 14 words

The method of claim 28, wherein the digital image is the binary segmentation mask.

Claim 31

Dependent Claim 84 words

The method of claim 1, wherein, in any spectral band, the digital image is segmented to located the region of interest and the computing step further comprises: locating N topographic regions of the segmented image, wherein the n th such topographic region is the locus of all pixels whose intensities lie between I(n-1) and I(n), for n=1, 2, . . . , N; and calculating at least one quantity that represents a statistical property of the spatial distribution of pixels within a topographic region.

Claim 32

Dependent Claim 35 words

The method of claim 30, wherein the calculated quantity depends on the mean and standard deviation of the distances of all the pixels in a topographic region from the intensity centroid of the segmented image.

Claim 33

Dependent Claim 38 words

The method of claim 31, wherein the calculated quantity is the ratio of the area of a polygon defined by the intensity centroids of at least three different topographic regions to the total area of the segmented image.

Claim 34

Dependent Claim 51 words

The method of claim 1, wherein the characterizing step comprises the logical union {`AND`} of the outputs of several intermediate distinguishing steps, wherein each such step distinguishes between a particular condition of a region of interest of the biological tissue and a different alternative condition of the same region of interest.

Claim 35

Dependent Claim 29 words

The method of claim 1, wherein the segmentation mask is generated from a digital image in that spectral band in which the resulting segmentation mask has the largest area.

Claim 36

Independent Claim 180 words

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.

Claim 37

Independent Claim 180 words

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.

Claim 38

Dependent Claim 17 words

The system of claim 35, further comprising means for suppressing specular reflections from the region of interest.

Claim 39

Dependent Claim 70 words

The system of claim 36, wherein the processor estimates the statistical measures separately within either of a border region and an interior region of the digital image the border region encompasses the envelope of circles of fixed radius centered on the boundary of the segmentation mask; and the inside region comprises all points of the image that are within the segmentation mask boundary but not included in the border region.

Claim 40

Dependent Claim 102 words

The system of claim 37, wherein the processor estimates at an individual level at least one value which is a statistical measure of texture of the portion of the region of interest within the border region and interior region, chosen from the group consisting of: the number of wavelet maxima per unit area; the ratio of the mean coefficient magnitude to the absolute deviation of the coefficient magnitudes from the mean value; the ratio of the mean coefficient magnitude to the standard deviation of the coefficient magnitudes; and the skewness of the coefficient magnitudes, normalized to the cube of the standard deviation.

Claim 41

Dependent Claim 39 words

The system of claim 38, wherein the processor further estimates either of the degree of change of a statistic of the wavelet coefficient distribution with increment of wavelet level, and the degree of deviation of such change from linearity.

Claim 42

Dependent Claim 28 words

The system of claim 38, wherein the processor further estimates the average rate of change, with respect to level, of the number of wavelet maxima per unit area.

Claim 43

Dependent Claim 48 words

The system of claim 35, wherein the camera records monochromatic images and the illumination means comprises: a tungsten halogen light source with feedback to stabilize the intensity in each wavelength band; means for sequentially filtering the light; and an optical fiber ring illuminator to distribute the filtered light.

Claim 44

Dependent Claim 21 words

The system of claim 41, further comprising a feedback loop for stabilizing the intensity of the light source by the processor.

Claim 45

Dependent Claim 60 words

The system of claim 42, further comprising a material of stable reflectance for being illuminated by the light source, wherein the feedback loop includes the monitoring by the processor, of the intensity of light reflected from the material by the processor and the adjustment of the intensity of the light source if the monitored intensity varies from a desired value.

Claim 46

Dependent Claim 18 words

The system of claim 43, wherein the power, voltage or current supplied to the light source is monitored.

Claim 47

Dependent Claim 15 words

The system of claim 35, wherein the source of illumination is at least one laser.

Claim 48

Independent Claim 113 words

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.

Claim 49

Independent Claim 113 words

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.

Claim 50

Dependent Claim 83 words

The method of claim 46, wherein the at least one statistical measure is generated separately within one of either of a border region and an interior region of a feature of the image, wherein: the border region encompasses the envelope of circles of fixed radius centered on the boundary of a segmentation mask of the feature of the image; and the interior region comprises all points of the image that are within the segmentation mask boundary but not included in the border region.

Claim 51

Dependent Claim 112 words

The method of claim 47, wherein the generating step comprises generating at an individual level at least one value which is a statistical measure of texture of the portion of the region of interest within the border region and interior region, chosen from the group consisting of: the number of wavelet maxima per unit area; the ratio of the mean of the coefficient magnitudes to the absolute deviation of the coefficient magnitudes from the mean value; the ratio of the mean of the coefficient magnitudes to the standard deviation of the coefficient magnitudes; and the skewness of the coefficient magnitudes, normalized to the cube of the standard deviation of the coefficient magnitudes.

Claim 52

Dependent Claim 18 words

The method of claim 46, wherein the region of interest of a biological tissue is a skin lesion.

Claim 53

Dependent Claim 17 words

The method of claim 46, wherein the region of interest of a biological tissue is a wound.

Claim 54

Dependent Claim 17 words

The method of claim 46, wherein the region of interest of a biological tissue is a burn.

Claim 55

Dependent Claim 26 words

The method of claim 46 wherein the digital image of the biological tissue is an image acquired with light in the ultraviolet to blue spectral band.

Claim 56

Dependent Claim 111 words

The method of claim 52 wherein: the region of interest of a biological tissue is a skin lesion; and prior to the computing step, the digital image in any spectral band is first segmented to locate the region of interest in the image, and wherein said computing step further comprises calculating at least one quantity chosen from the group consisting of: the average of the area of dermal papillae within the segmentation mask; the standard deviation of the area of dermal papillae within the segmentation mask; average of the thickness of rete ridges within the segmentation mask; and the standard deviation of the thickness of rete ridges within the segmentation mask.

Claim 57

Dependent Claim 63 words

The method of claim 52 wherein: the region of interest of a biological tissue is a skin lesion; and prior to the computing step, the digital image in any spectral band is first segmented by means of a segmentation mask, said mask being generated from the digital image acquired in that spectral band for which the imaged skin lesion has the largest area.

Claim 58

Dependent Claim 21 words

The method of claim 46 wherein an image is acquired by a digital camera in a least one infrared spectral band.

Claim 59

Dependent Claim 30 words

The method of claim 46 wherein the images are acquired in different spectral bands in the visible region by digitizing color slides of the region of interest of the tissue.

Claim 60

Dependent Claim 129 words

The method of claim 46, wherein the computing step comprises calculating at least one quantity which is a statistical measure of texture in a portion of the region of interest, wherein the measure is chosen from the group consisting of: the number of wavelet maxima per unit area; the ratio of the mean magnitude of the wavelet maxima coefficients to the absolute deviation of the coefficient magnitudes with respect to the mean magnitude; the ratio of the mean magnitude of the wavelet maxima coefficients to the standard deviation of the coefficient magnitudes; and the skewness of the coefficient magnitudes, normalized to the cube of the standard deviation; wherein said portion of the region of interest comprises either of a border subregion and a subregion interior to said border subregion.

Claim 61

Dependent Claim 39 words

The method of claim 57, further comprising calculating either of the degree of change of a statistic of the wavelet maxima coefficient distribution upon an increment of wavelet level, and the degree of deviation of such change from linearity.

Claim 62

Dependent Claim 26 words

The method of claim 57, further comprising calculating the average rate of change, with respect to level, of the number of wavelet maxima per unit area.

Claim 63

Dependent Claim 49 words

The method of claim 46, further comprising comparing each of the computed quantities to a threshold, which threshold is predetermined through statistical analysis of multiscale wavelet maxima representations of a training set of digital images of similar biological tissue, for which the condition of the tissue is independently known.

Claim 64

Dependent Claim 126 words

The method of claim 46, wherein prior to the computing step, the digital image is first segmented to locate the region of interest in the image, and said computing step further comprises: determining the principal axis of the segmented image; rotating the principal axes of the segmented image until they are oriented parallel to the coordinate axes of the image; computing the differences in intensity between each pair of pixels whose locations, with respect to a principal axis, are mirror images of each other; summing the absolute values of said intensity differences; calculating asymmetry values with respect to each principal axis, by normalizing the said sum to the total intensity in the segmented images; and adding together the asymmetry values calculated for the two principal axes.

Claim 65

Dependent Claim 27 words

The method of claim 61, wherein prior to the "determining" step, the intensities in the digital image are replaced by the binary values of the segmentation mask.

Claim 66

Dependent Claim 97 words

The method of claim 46, wherein prior to the computing step, the digital image is first segmented to locate the region of interest in the image, and said computing step further comprises: calculating at least one quantity chosen from the group consisting of: a statistical measure of the deviation of the border of the region of interest from the border of an ellipse having the same area, aspect ratio, and orientation as the segmentation mask; and a statistical measure of the gradients of the intensity values of the digital image across the border of the segmented image.

Claim 67

Dependent Claim 53 words

The method of claim 46 wherein the characterizing step comprises the logical combination of the outputs of several intermediate distinguishing steps, wherein each distinguishing step distinguishes between a particular condition of a region of interest of the biological tissue and a different one of several alternative conditions of the same region of interest.

Claim 68

Dependent Claim 25 words

The method of claim 46, wherein the digital images are formed by digitizing a color slide of the region of interest in different spectral bands.

Claim 69

Dependent Claim 21 words

The method of claim 46, wherein the region of interest of a biological tissue is a pigmented region suspected of melanoma.

Annuity Stage	Window Opens	Payment Deadline	Surcharge Period Until	Estimated Fee	Status
3.5 Years (Year 4)	2003-06-27	2003-12-27	2004-06-27	$2000.00	Window Closed / Lapsed
7.5 Years (Year 8)	2007-06-27	2007-12-27	2008-06-27	$3760.00	Window Closed / Lapsed
11.5 Years (Year 12)	2011-06-27	2011-12-27	2012-06-27	$7700.00	Window Closed / Lapsed

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

Abstract

Inventors

Bibliographic Details

Claims Analysis

References Cited (Backward Citations)

USPTO Annuity & Maintenance Windows

Assigned Categories & Tags

Assign Category Tag