Accurate tissue injury assessment

• US 6,411,907 B1
• Filed: 06/29/1999
• Issued: 06/25/2002
• Est. Priority Date: 07/25/1997
• Status: Expired due to Term

• Current Assignee: Physical Optics Corporation
• Original Assignee: Intelligent Optical Systems, Inc.
• Inventors: Wang, Allan, Fiesler, Emile, Lu, Taiwei, Lieberman, Robert A.
• Primary Examiner(s): Hilten, John S.
• Assistant Examiner(s): Washburn, Douglas N
• Application Number:
  US09/342,303
• Time in Patent Office: 1,092 Days
• Field of Search: 702/28, 702/172, 128/654, 128/664, 128/665
• US Class Current: 702/28
• CPC Class Codes: A61B 5/0059 using light, e.g. diagnosis by transillumination, diascopy, fluorescence A61B5/0093, A61B5/1455, A61B5/02416 and A61B5/0261 take precedence
• CPC Class Codes: A61B 5/411 Detecting or monitoring allergy or intolerance reactions to an allergenic agent or substance
• CPC Class Codes: A61B 5/445 Evaluating skin irritation or skin trauma, e.g. rash, eczema, wound, bed sore
• CPC Class Codes: A61B 5/7232 involving compression of the physiological signal, e.g. to extend the signal recording period
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: G01J 3/02 Details
• CPC Class Codes: G01J 3/0218 using optical fibers
• CPC Class Codes: G01J 3/0272 Handheld
• CPC Class Codes: G01J 3/28 Investigating the spectrum using colour filters G01J3/51
• CPC Class Codes: G01N 2021/3155 Measuring in two spectral ranges, e.g. UV and visible
• CPC Class Codes: G01N 21/31 Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry G01N21/72 takes precedence
• CPC Class Codes: G01N 21/359 using near infrared light
• CPC Class Codes: G01N 2201/1296 using neural networks
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: Y10S 706/924 Medical

Abstract

Systems and methods using a spectrometer system for real-time automatic evaluation of tissue injury are described. A method of assessing an injury to tissue comprises reflecting an electromagnetic signal from the tissue to produce a reflected electromagnetic signal; producing spectral data pertaining to the intensities of individual wavelengths of the reflected electromagnetic signal; analyzing the spectral data to obtain a set of results; and providing an indication of the nature of the injury to the tissue based upon the set of results.

Claims

1. A method of assessing an injury to tissue comprising:

(A) reflecting an electromagnetic signal from said tissue to produce a reflected electromagnetic signal;

(B) producing spectral data pertaining to the intensities of individual wavelengths of said reflected electromagnetic signal;

(C) compressing said spectral data to produce compressed spectral data;

said compressing step being performed before a processing step such that, during said processing step, compressed spectral data is processed;

(D) analyzing said spectral data to obtain a set of results; and

(E) providing an indication of the nature of said injury to said tissue based upon said set of results.

2. The method according to claim 1, wherein said analyzing step is performed using a system of equations having the form:

$\begin{array}{c}\left\{\begin{array}{c}{y}_1=f_1^2<br><br>\left[\underset{j}{\sum <br><br>}<br><br>c_{\mathrm{j1}}^2<br><br>f_1^1<br><br>\left[\underset{i}{\sum <br><br>}<br><br>c_{\mathrm{ij}}^1<br><br>s_i\right]\right]\\ \mathrm{⋮<br><br>}\\ y_k=f_k^2<br><br>\left[\underset{j}{\sum <br><br>}<br><br>c_{\mathrm{jk}}^2<br><br>f_k^1<br><br>\left[\underset{i}{\sum <br><br>}<br><br>c_{\mathrm{ij}}^1<br><br>s_i\right]\right]\end{array}\right\}\end{array}$

where the functions ƒ

_kⁿ are single-valued functions, c_ijⁿ and c_jkⁿ are coefficients from a matrix, and y₁ . . . y_k are the outputs of analyzing step and are proportional to the probability that the tissue injury is of class k.

3. The method according to claim 2, wherein said coefficients are fixed.

4. A method of assessing an injury to tissue comprising:

(A) generating a first electromagnetic signal;

then

(B) reflecting said first electromagnetic signal from said tissue to produce a second electromagnetic signal;

then

(C) transmitting said second electromagnetic signal to a spectrometer;

then

(D) producing spectral data pertaining to said second electromagnetic signal using said spectrometer, said spectral data including information pertaining to the intensities of individual wavelengths of said second electromagnetic signal;

then

(E) compressing said spectral data to produce compressed spectral data;

said compressing step being performed before a processing step such that, during said processing step, compressed spectral data is processed;

(F) analyzing said spectral data to obtain a set of results, said set of results indicating the nature of said injury to said tissue; and

(G) providing an indication of the nature of said injury to said tissue based upon said set of results.

5. The method according to claim 4, wherein said analyzing step is performed using a system of equations having the form:

$\begin{array}{c}\left\{\begin{array}{c}{y}_1=f_1^2<br><br>\left[\underset{j}{\sum <br><br>}<br><br>c_{\mathrm{j1}}^2<br><br>f_1^1<br><br>\left[\underset{i}{\sum <br><br>}<br><br>c_{\mathrm{ij}}^1<br><br>s_i\right]\right]\\ \mathrm{⋮<br><br>}\\ y_k=f_k^2<br><br>\left[\underset{j}{\sum <br><br>}<br><br>c_{\mathrm{jk}}^2<br><br>f_k^1<br><br>\left[\underset{i}{\sum <br><br>}<br><br>c_{\mathrm{ij}}^1<br><br>s_i\right]\right]\end{array}\right\}\end{array}$

where the functions ƒ

_kⁿ are single-valued functions, c_ijⁿ and c_jkⁿ are coefficients from a matrix, and y₁ . . . y_k are the outputs of said analysis step and are proportional to the probability that the tissue injury is of class k.

6. The method according to claim 4, further comprising compressing said spectral data to produce compressed spectral data, said compressing step including transforming said spectral data to a representation in which said spectral data is represented using a plurality of coefficients, the total number of said coefficients being relatively small as compared to the total number of wavelengths for which intensity information is produced during the producing step (D), each of said coefficients corresponding to one of a plurality of orthogonal eigen-spectra of the transformation, and said compressing step being performed before said processing step.

7. An apparatus for assessing an injury to a tissue, comprising:

an electromagnetic signal generator;

an optical fiber connected to said electromagnetic signal generator;

a fiber optic probe connected to said optical fiber;

a broad band spectrometer connected to said fiber optic probe; and

a computer connected to said broad band spectrometer, said computer analyzing data from said broad band spectrometer to produce a plurality of outputs, each of said plurality of outputs corresponding to a tissue injury category; and

wherein said computer includes a principle component analyzer of broad band spectral data obtained from said broad band spectrometer; and

wherein said computer produces a set of results at said plurality of outputs, said set of results indicating the nature of said injury to said tissue.

8. The apparatus according to claim 7, wherein the result at each of said plurality of outputs indicates the probability that said injury to said tissue is in said tissue injury category that corresponds to the respective output.

9. The apparatus according to claim 7, wherein said computer includes:

an autoscaling processor;

a singular value decomposition analyzer coupled to said autoscaling processor; and

a classifier coupled to said singular value decomposition analyzer.

10. The apparatus according to claim 7, further comprising a sample enclosure.

11. The apparatus according to claim 7, further comprising a positioner operatively connected to said fiber optic probe.

12. The apparatus according to claim 7, wherein one of said plurality of outputs corresponds to a full thickness burn injury and another of said plurality of outputs corresponds to a partial thickness burn injury.

13. A method of assessing an injury to tissue, the method comprising:

reflecting an electromagnetic signal off said tissue to produce a reflected electromagnetic signal;

measuring the intensities of individual wavelengths of said reflected electromagnetic signal to produce spectrum data;

compressing said spectrum data and extracting features from said spectrum data, including the step of extracting a set of orthogonal feature vectors to represent said spectrum data; and

classifying said set of orthogonal feature vectors, including the step of producing a set of results at a plurality of outputs, each of said outputs corresponding to a tissue injury category, and said set of results indicating the nature of said injury to said tissue.

14. The method according to claim 13, wherein a first one of said plurality of outputs corresponds to a full thickness burn injury and a second one of said plurality of outputs corresponds to a partial thickness burn injury.

15. The method according to claim 14, wherein the result at said first one of said plurality of outputs indicates the probability that said tissue injury is a full thickness burn injury and wherein the result at said second one of said plurality of outputs indicates the probability that said tissue injury is a partial thickness burn injury.