Multi-excitation diagnostic system and methods for classification of tissue

Abstract

Methods and systems for in vivo classification of tissue are disclosed. The tissue is irradiated with light from multiple light sources and light scattered and fluoresced from the tissue is received. Distinct emissions of the sample are identified from the received light. An excitation-emission matrix is generated ( 1002 ). On-diagonal and off-diagonal components of the excitation-emission matrix are identified ( 1004, 1006, 1008 ). Spectroscopic measures are derived from the excitation-emission matrix ( 1014 ), and are compared to a database of known spectra ( 1016 ) permitting the tissue to be classified as benign or malignant ( 1018 ). An optical biopsy needle or an optical probe may be used to contemporaneously classify and sample tissue for pathological confirmation of diagnosis.

1 - 29 . (canceled) 
     
     
         30 . A method of training a diagnostic software system network to differentiate between benign and malignant tissue, the method comprising
 acquiring a plurality of spectra for distinct positions of the tissue;   instructing a statistical analysis module to search for differentiating features of the spectra;   producing tissue specimens of the tissue that correspond to the distinct positions;   comparing the differentiating features of the spectra determined by the statistical analysis module with pathological observations of the produced tissue specimens; and   providing feedback to the statistical analysis module based upon correlations between the pathological observations and the differentiating features.   
     
     
         31 . The method of  claim 30 , wherein the acquiring operation further comprises:
 illuminating the tissue with an incident broadband light source;   illuminating the tissue with at least one bandwidth-limited incident light source in the UV and near UV spectrum; and   collecting reflected and emitted light from the tissue.   
     
     
         32 . The method of  claim 30 , wherein wavelengths of the plurality of spectra are in a range of about 200-2000 nm. 
     
     
         33 . The method of  claim 30  wherein the statistical analysis module comprises an artificial neural network module. 
     
     
         34 . The method of  claim 30  wherein the statistical analysis module comprises a support vector machine. 
     
     
         35 . The method of  claim 30 , wherein the plurality of spectra comprises a fluorescence emission spectrum caused by an excitation signal and the fluorescence emission spectrum is indicative of at least one molecular component level within the tissue. 
     
     
         36 . The method of  claim 35  wherein the molecular component level comprises at least one of a level of tryptophan. 
     
     
         37 . The method of  claim 35  wherein the molecular component level comprises at least one of a level of collagen. 
     
     
         38 . The method of  claim 35  wherein the molecular component level comprises at least one of a level of NADH. 
     
     
         39 . The method of  claim 35 , wherein wavelengths of the plurality of spectra are in a range of about 200-2000 nm. 
     
     
         40 . The system of  claim 39 , wherein the plurality of spectra are analyzed by diffuse reflectance spectroscopy. 
     
     
         41 . The method of  claim 39  wherein the comparing comprises differentiating between benign and malignant tissue and/or differentiating between a plurality of disease grades. 
     
     
         42 . The method of  claim 30  further comprising:
 providing an optical biopsy needle device comprising an elongate biopsy needle having a distal end with a distal tip, said distal end configured to biopsy tissue spaced proximally from the distal tip, said device having a fiber optic bundle comprising at least one transmitter fiber for transmitting radiation to the distal tip and at least one receiver fiber for transmitting radiation from the distal tip, wherein the fiber optic bundle including the transmitter fiber and including the receiver fiber extends within the biopsy needle and wherein the fiber optic bundle including the transmitter fiber and including the receiver fiber each terminate at the distal tip of the biopsy needle such that the transmitter fiber transmits radiation to the tissue adjacent the distal tip and such that the receiver fiber transmits radiation from the tissue adjacent the distal tip; 
 connecting the fiber optic bundle of the optical biopsy needle device to a spectral analysis device; 
 positioning the distal tip of the biopsy needle adjacent to or within the tissue; 
 obtaining a spectral response associated with a distinct position of the tissue spaced proximally from the distal tip; and 
 evaluating the spectral response with the spectral analysis device and the statistical analysis module to determine whether the tissue is benign or malignant. 
 
     
     
         43 . The method of  claim 42  further comprising actuating the biopsy needle device to obtain a portion of tissue spaced proximally from the distal tip at the distinct position and removing the portion of the tissue if the tissue is determined to be malignant. 
     
     
         44 . The method of  claim 42  further comprising delivering a therapeutic treatment to tissue at the distinct position determined to be malignant. 
     
     
         45 . The method of  claim 42 , wherein the statistical analysis module comprises an artificial neural network module trained to differentiate between benign and malignant tissue to determine a morphology of each distinct position and wherein the evaluating operation further comprises analyzing the spectral response within the artificial neural network module. 
     
     
         46 . The method of  claim 42 , wherein the statistical analysis module comprises a support vector machine trained to differentiate between benign and malignant tissue to determine a morphology of each distinct position and wherein the evaluating operation further comprises analyzing the spectral response within the support vector machine. 
     
     
         47 . The method of  claim 42  wherein the obtaining operation further comprises:
 transmitting an excitation signal through the at least one transmitter fiber; and 
 receiving a fluorescence emission signal through the at least one receiver fiber. 
 
     
     
         48 . The method of  claim 47  wherein the evaluating operation determines whether the fluorescence emission signal is indicative of an abnormal level of an endogenous fluorophore in the tissue. 
     
     
         49 . The method of  claim 48 , wherein the tissue is prostatic tissue and the evaluating operation determines whether the fluorescence emission signal is indicative of at least one molecular component level within the tissue. 
     
     
         50 . A system for training a diagnostic software system network to differentiate between benign and malignant tissue and/or to differentiate between a plurality of disease grades, the system comprising:
 a spectral analysis device configured for acquiring a plurality of spectra for distinct positions of the tissue;   a memory storing a statistical analysis module; and   a processor configured for executing the statistical analysis module and configured for:
 instructing the statistical analysis module to search for differentiating features of the spectra; 
 comparing the differentiating features of the spectra determined by the statistical analysis module with pathological observations of the produced tissue specimens; and 
 providing feedback to the statistical analysis module based upon correlations between the pathological observations and the differentiating features. 
   
     
     
         51 . The system of  claim 50 , wherein the spectral analysis device is configured for:
 illuminating the tissue with an incident broadband light source;   illuminating the tissue with at least one bandwidth-limited incident light source in the UV and near UV spectrum; and   collecting reflected and emitted light from the tissue.   
     
     
         52 . The system of  claim 50 , wherein the spectral analysis device is configured for acquiring the plurality of spectra having wavelengths in a range of about 200-2000 nm. 
     
     
         53 . The system of  claim 50  wherein the statistical analysis module comprises an artificial neural network module. 
     
     
         54 . The system of  claim 50  wherein the statistical analysis module comprises a support vector machine. 
     
     
         55 . The system, of  claim 50 , wherein the plurality of spectra comprises a fluorescence emission spectrum caused by an excitation signal and the fluorescence emission spectrum is indicative of at least one molecular component level within the tissue. 
     
     
         56 . The system of  claim 55  wherein the molecular component level comprises at least one of a level of tryptophan. 
     
     
         57 . The system of  claim 55  wherein the molecular component level comprises at least one of a level of collagen. 
     
     
         58 . The system of  claim 55  wherein the molecular component level comprises at least one of a level of NADH. 
     
     
         59 . The system of  claim 50 , wherein the spectral analysis device is configured for acquiring the plurality of spectra having wavelengths in a range of about 200-2000 nm. 
     
     
         60 . The system of  claim 59 , wherein the comparing comprises analyzing the plurality of acquired spectra by diffuse reflectance spectroscopy. 
     
     
         61 . The system of  claim 59  wherein the comparing comprises differentiating between benign and malignant tissue and/or differentiating between a plurality of disease grades.