Optical Biopsy Method for Breast Cancer Diagnosis Based on Artificial Neural Network Classification οf Fluorescence Landscape Data

• Authors: T. Dramićanin , I. Zeković , B. Dimitrijević , S. Ribar , M. Dramićanin
• Languages of publication: EN

Abstracts

EN

Supervised self-organizing map, a type of artificial neural network, is applied for classification of human breast tissue samples utilizing data obtained from fluorescence landscape measurements. Female breast tissue samples were taken soon after the surgical resection, identified and stored at -80°C until fluorescence measurements. From fluorescence landscapes obtained in UV-VIS region spectral features showing statistically significant differences between malignant and normal samples are identified and further quantified to serve as a training input to neural network. Additional set of samples was used as a test group input to trained network in order to evaluate performance of proposed optical biopsy method. Classification sensitivity of 83.9% and specificity of 88.9% are found.

Keywords

EN

87.64.kv; 84.35.+i; 87.19.xj; 33.50.-j

Discipline

• 33.50.-j: Fluorescence and phosphorescence; radiationless transitions, quenching (intersystem crossing, internal conversion)(for energy transfer, see also section 34; for biophysical applications, see 87.64.kv)
• 84.35.+i: Neural networks(for optical neural networks, see 42.79.Ta; see also 07.05.Mh Neural networks, fuzzy logic, artificial intelligence in computers in experimental physics; 87.18.Sn in biological complexity)
• 87.19.xj: Cancer
• 87.64.kv: Fluorescence

• Publisher: Institute of Physics, Polish Academy of Sciences
• Journal: Acta Physica Polonica A
• Year: 2009
• Volume: 116
• Issue: 4
• Pages: 690-692

Dates

published

2009-10

Contributors

author

T. Dramićanin

• Institute of Nuclear Sciences "Vinča", University of Belgrade, 11001 Belgrade, Serbia

author

I. Zeković

• Institute of Nuclear Sciences "Vinča", University of Belgrade, 11001 Belgrade, Serbia

author

B. Dimitrijević

• Institute of Nuclear Sciences "Vinča", University of Belgrade, 11001 Belgrade, Serbia

author

S. Ribar

• Faculty of Mechanical Engineering, University of Belgrade, Kraljice Marije 16, 11120 Belgrade, Serbia

author

M. Dramićanin

• Institute of Nuclear Sciences "Vinča", University of Belgrade, 11001 Belgrade, Serbia

References

• 1. http://www.komen.org/bci (accessed 2009)
• 2. R.R. Alfano, G.C. Tang, A. Pradhan, W. Lam, D.S.J. Choy, E. Opher, IEEE J. Quantum Electron. 23, 1806 (1987)
• 3. T. Dramićanin, M.D. Dramićanin, V. Jokanović, D. Nikolić-Vukosavljević, B. Dimitrijević, Photochem. Photobiol. 81, 1554 (2005)
• 4. K.T. Schomacker, J.K. Frisoli, C.C. Compton, T.J. Flotte, J.M. Richter, N.S. Nishioka, T.F. Deutsch, Lasers Surg. Med. 12, 63 (1992)
• 5. S.D. Kamath, K.K. Mahato, J. Biomed. Opt. 12, 14028 (2007)
• 6. H.J.C.M. Sterenborg, M. Motamedi, R.F. Wagner, M. Duvic, S. Thomsen, S.L. Jacques, Lasers Med. Sci. 9, 191 (1994)
• 7. T. Kohonen, Self-Organizing Maps, 3rd ed., Springer, Berlin 2001
• 8. T. Kohonen, Computer 21, 11 (1988)
• 9. H. Motulsky, Intuitive Biostatistics, Oxford University Press, New York 1995

Identifiers

DOI

10.12693/APhysPolA.116.690