medigraphic.com

2006, Number 2

<< Back Next >>

Rev Mex Ing Biomed 2006; 27 (2)

Evaluation of healthy and infected cervical tissue using a LIFS system and a back-propagation neural network

Castillo AA, De La Rosa VJM, Calva CPA, Franco LEB, Torres MR, Álvarez DR, De La Rosa GG, Romero GMB

Language: English
References: 15
Page: 68-73
PDF size: 187.50 Kb.


ABSTRACT

Laser Induced Fluorescence Spectroscopy (LIFS) is a technique that has been recently used to detect in vivo or in vitro cancer. The LIFS system has been used to analyze cervical tissue samples for histological evaluation. Because the fluorescence spectra are position and inter-probe dependent (albeit they were equally classified by histological evaluation) the relationship that exists in the data is complex. So, a back-propagation Artificial Neural Network is used to detect the relationships contained within them. The validation of the system was done with 5 different proves and a 100% classification coincidence between the neural network classification and a normal histological one was obtained. The LIFS-System works with a N2 laser of 5 μJ pulse energy (tFWHM = 3.8 ns at 337.1 nm wavelength) and spectra from 350 to 650 nm were processed and evaluated in a PC.


REFERENCES

  1. Secretaría de Salud. México. Epidemiología 2006; 1(23): 1-7.

  2. Lazcano-Ponce E, Herrero R, Muñoz N, Cruz A, Shah KVK, Alonso P, Hernández P, Salmerón J, Hernández M. Epidemiology of HPV infection among Mexican women with normal cervical cytology. International Journal of Cancer 2001; 91(3): 412-420.

  3. International Agency for Research on Cancer, Globocan 2002 database. http://www-dep.iarc.fr/GLOBOCAN/table2.asp?cancer=142®ion=99&sex=2&sort=1.

  4. Tumer K, Ramanujam N, Ghosh J, Richards-Kortum R. Ensembles of radial basis function networks for spectroscopic detection of cervical precancer. IEEE Transactions of Biomedical Engineering 1998; 45(8): 953-961.

  5. Mitchell MF. Accuracy of colposcopy. Clinical consultations in obstetrics and gynecology. 1994; 6(1): 70-73.

  6. Majumder SK, Kumar R, Gosh NP, Gupta PK. Cancer diagnosis using N2 laser excited autofluorescence spectroscopy of formalin-fixed human tissue” Conference Proceedings of Photonics 2004. http://eel.inst.ac.ir/Sadr/Papers/bio4.pdf

  7. Briokner CJ, Follen M, Boiko I, Galvan J, Thomsen S, Malpica A, Suzuki S, Lotan R, Richards-Kortum R. Autofluorescence patterns in short-term cultures of normal cervical tissue. Photochemistry and Photobiology 2000; 71(6): 730-736.

  8. De la Rosa J, Bautista FJ. Optical properties of paper at 337.1 nm. Revista Mexicana de Física 2005; 51(1): 110-113.

  9. Fang Q, Papaioannou T, Jo JA, Vaitha R, Shastry RK, Marcu L. Time-domain laser-induced fluorescence spectroscopy apparatus for clinical diagnostics. Review of Scientific Instruments 2004; 75(1): 151-162.

  10. Glassman WS, Liu CH, Tang GC, Lubicz S, Alfano RR. Ultraviolet excited fluorescence spectra from non-malignant and malignant tissues of the gynecological tract. Lasers in the Life Sciences 1992; 5(1-2): 49-58.

  11. Batuello TJ, Crawford ED. Artificial neural networks in prostate cancer. Lab. Medica International 2001; 18(3): 10-11.

  12. Bishop CM. Neural networks for pattern recognition, Oxford University Press Inc., New York, 1995.

  13. Hagan M, Demuth H, Beale M. Neural network design, PWS, Publishing Company, Boston, 1996.

  14. Rojas R. Neural networks, a systematic introduction. Springer, Berlin, 1996.

  15. Álvarez R, Franco EB, Torres R. Sistema auxiliar para el diagnóstico de carcinoma epidermoide invasor en tejido cérvix empleando tecnología láser. Trabajo terminal No. 633, ESCOM-IPN, 2005.




2020     |     www.medigraphic.com