Support Vector Machine on Fluorescence Landscapes for Breast Cancer Diagnostics

Excitation-emission matrices (EEM) and total synchronous fluorescence spectra (SFS) of normal and malignant breast tissue specimens are measured in UV–VIS spectral region to serve as data inputs in development of Support Vector Machine (SVM) based breast cancer diagnostics tool. Various input data combinations are tested for classification accuracy using SVM prediction against histopathology findings to discover the best combination regarding diagnostics sensitivity and specificity. It is shown that with EEM data SVM provided 67 % sensitivity and 62 % specificity diagnostics. With SFS data SVM provided 100 % sensitivity and specificity for a several input data combinations. Among these combinations those that require minimal data inputs are identified.

[1]  Massimiliano Pontil,et al.  Support Vector Machines for 3D Object Recognition , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Dong-Chul Park,et al.  Centroid neural network for unsupervised competitive learning , 2000, IEEE Trans. Neural Networks Learn. Syst..

[3]  Tuan Vo-Dinh.  Principle of synchronous luminescence (SL) technique for biomedical diagnostics , 2000, Photonics West - Biomedical Optics.

[4]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[5]  Karthik Vishwanath,et al.  Fluorescence Spectroscopy In Vivo , 2011 .

[6]  Bernard F. Buxton,et al.  Drug Design by Machine Learning: Support Vector Machines for Pharmaceutical Data Analysis , 2001, Comput. Chem..

[7]  Singaravelu Ganesan,et al.  Characterization of cervical normal and abnormal tissues by synchronous luminescence spectroscopy , 2002, SPIE BiOS.

[8]  S. K. Majumdar,et al.  Synchronous luminescence spectroscopy of human breast tissues , 1998, Photonics West - Biomedical Optics.

[9]  B. Chance,et al.  Kinetics of mitochondrial flavoprotein and pyridine nucleotide in perfused heart , 1972 .

[10]  T. Vo‐Dinh,et al.  Multicomponent analysis by synchronous luminescence spectrometry. , 1978, Analytical chemistry.

[11]  Patrick Haffner,et al.  Support vector machines for histogram-based image classification , 1999, IEEE Trans. Neural Networks.

[12]  Nirmala Ramanujam,et al.  FLUORESCENCE SPECTROSCOPY IN VIVO 1 Fluorescence Spectroscopy In Vivo , 2000 .

[13]  S Nioka,et al.  In vivo study of tissue oxygen metabolism using optical and nuclear magnetic resonance spectroscopies. , 1989, Annual review of physiology.

[14]  N. Ramanujam,et al.  Diagnosis of Breast Cancer Using Optical Spectroscopy , 2003 .

[15]  D. Choy,et al.  Fluorescence spectra from cancerous and normal human breast and lung tissues , 1987, Annual Meeting Optical Society of America.

[16]  Roberto Lenarduzzi,et al.  Development of a synchronous fluorescence imaging system and data analysis methods. , 2007, Optics express.

[17]  T. Vo‐Dinh.  Fluorescence Spectroscopy for Biomedical Diagnostics , 2003 .

[18]  Hualou Liang,et al.  Detection of delayed gastric emptying from electrogastrograms with support vector machine , 2001, IEEE Transactions on Biomedical Engineering.

[19]  Martin T. Hagan,et al.  Neural network design , 1995 .

[20]  J. Mercer.  Functions of positive and negative type, and their connection with the theory of integral equations , 1909 .

[21]  Jung-Hsien Chiang,et al.  Neural and Fuzzy Methods in Handwriting Recognition , 1997, Computer.

[22]  Miroslav D. Dramićanin,et al.  Three-dimensional Total Synchronous Luminescence Spectroscopy Criteria for Discrimination Between Normal and Malignant Breast Tissues , 2005, Photochemistry and photobiology.

[23]  S. Madhuri,et al.  Native Fluorescence Spectroscopy of Blood Plasma in the Characterization of Oral Malignancy¶ , 2003 .

[24]  S. L. Jacques,et al.  In vivo fluorescence spectroscopy and imaging of human skin tumours , 1994, Lasers in Medical Science.

[25]  Chris H. Q. Ding,et al.  Multi-class protein fold recognition using support vector machines and neural networks , 2001, Bioinform..

[26]  Ovidiu Ivanciuc,et al.  Applications of Support Vector Machines in Chemistry , 2007 .

[27]  W. F. Bynum,et al.  Facts of life , 1989, Nature.

[28]  T J Flotte,et al.  Ultraviolet laser‐induced fluorescence of colonic tissue: Basic biology and diagnostic potential , 1992, Lasers in surgery and medicine.

[29]  Miroslav D. Dramićanin,et al.  Discrimination Between Normal and Malignant Breast Tissues by Synchronous Luminescence Spectroscopy , 2006 .

[30]  N. Ramanujam,et al.  Autofluorescence Spectroscopy of Normal and Malignant Human Breast Cell Lines¶ , 2003, Photochemistry and photobiology.

[31]  K. K. Mahato,et al.  Optical pathology using oral tissue fluorescence spectra: classification by principal component analysis and k-means nearest neighbor analysis. , 2007, Journal of biomedical optics.

[32]  Tatjana Dramićanin,et al.  Application of Supervised Self-Organizing Maps in Breast Cancer Diagnosis by Total Synchronous Fluorescence Spectroscopy , 2011, Applied spectroscopy.