PAPERS: Medical Image AnalysisNo Access

INTEGRATING GLOBAL AND LOCAL ANALYSIS OF COLOR, TEXTURE AND GEOMETRICAL INFORMATION FOR CATEGORIZING LARYNGEAL IMAGES

Department of Applied Electronics, Kaunas University of Technology, Studentu 50, LT-51368, Kaunas, Lithuania

Corresponding author. Also affiliated with: Intelligent Systems Laboratory, Halmstad University, Box 823, S-30118 Halmstad, Sweden.

Search for more papers by this author

ADAS GELZINIS

Department of Applied Electronics, Kaunas University of Technology, Studentu 50, LT-51368, Kaunas, Lithuania

Search for more papers by this author

MARIJA BACAUSKIENE

Department of Applied Electronics, Kaunas University of Technology, Studentu 50, LT-51368, Kaunas, Lithuania

Search for more papers by this author

, and

VIRGILIJUS ULOZA

Department of Otolaryngology, Kaunas University of Medicine, LT-50009, Kaunas, Lithuania

Search for more papers by this author

https://doi.org/10.1142/S0218001406005228Cited by:9 (Source: Crossref)

Abstract

An approach to integrating the global and local kernel-based automated analysis of vocal fold images aiming to categorize laryngeal diseases is presented in this paper. The problem is treated as an image analysis and recognition task. A committee of support vector machines is employed for performing the categorization of vocal fold images into healthy, diffuse and nodular classes. Analysis of image color distribution, Gabor filtering, cooccurrence matrices, analysis of color edges, image segmentation into homogeneous regions from the image color, texture and geometry view point, analysis of the soft membership of the regions in the decision classes, the kernel principal components based feature extraction are the techniques employed for the global and local analysis of laryngeal images. Bearing in mind the high similarity of the decision classes, the correct classification rate of over 94% obtained when testing the system on 785 vocal fold images is rather encouraging.

Keywords:

References

J. C. Bezdek , Pattern Recognition with Fuzzy Objective Function Algorithms ( Plenum Press , NY , 1981 ) . Crossref, Google Scholar
L. Breiman, Mach. Learn. 24(2), 123 (1996), DOI: 10.1007/BF00058655. Web of Science, Google Scholar
L. Breiman, Mach. Learn. 36, 85 (1999), DOI: 10.1023/A:1007563306331. Crossref, Web of Science, Google Scholar
H. D. Chenget al., Patt. Recogn. 34, 2259 (2001), DOI: 10.1016/S0031-3203(00)00149-7. Crossref, Web of Science, Google Scholar
P. R. Cohen , Empirical Methods for Artificial Intelligence ( MIT Press , Cambridge, MA , 1995 ) . Google Scholar
D. Comaniciu and P. Meer, IEEE Trans. Patt. Anal. Mach. Intell. 24(5), 603 (2002), DOI: 10.1109/34.1000236. Crossref, Web of Science, Google Scholar
F. G. Dikkers and P. G. Nikkels, Ann. Otol. Rhinol. Laryngol. 104(9/1), 698 (1995). Crossref, Web of Science, Google Scholar
Y. Freund and R. E. Schapire, J. Comput. Syst. Sci. 55, 119 (1997), DOI: 10.1006/jcss.1997.1504. Crossref, Web of Science, Google Scholar
M. M. Galloway, Comput. Graph. Imag. Process. 4, 172 (1975). Crossref, Google Scholar
R. M. Haralick, K. Shanmugam and I. Dinstein, IEEE Trans. Syst. Man Cybern. 3(6), 610 (1973). Crossref, Web of Science, Google Scholar
J. F. R. Ilgneret al., Acta Oto-Laryngologica 123(6), 730 (2003), DOI: 10.1080/00016480310000412. Crossref, Web of Science, Google Scholar
D. J. Jobson, Z. Rahaman and G. A. Woodell, IEEE Trans. Imag. Process. 6(3), 451 (1997), DOI: 10.1109/83.557356. Crossref, Web of Science, Google Scholar
O. Kleinsasser , Mikrolaryngoskopie und Endolaryngeale Mikrochirurgie: Technik und Typische Befunde , 3rd edn. ( Schattauer , Stutgart , 1991 ) . Google Scholar
J. C. Lagariaset al., SIAM J. Optim. 9(1), 112 (1998), DOI: 10.1137/S1052623496303470. Crossref, Web of Science, Google Scholar
D. Lindahlet al., J. Nucl. Med. 40, 1 (1999). Web of Science, Google Scholar
M. Ohlsson, Artif. Intell. Med. 30(1), 49 (2004), DOI: 10.1016/S0933-3657(03)00050-2. Crossref, Web of Science, Google Scholar
C. Palm and T. M. Lehmann, Mach. Graph. Vis. 11(2/3), 195 (2002). Google Scholar
P. J. P. Poels, F. I. C. R. S. de Jong and H. K. Schutte, J. Voice 17(3), 425 (2003), DOI: 10.1067/S0892-1997(03)00010-9. Crossref, Web of Science, Google Scholar
Z. Rahman, D. J. Jobson and G. A. Woodell, J. Electron. Imag. 13(1), 100 (2004), DOI: 10.1117/1.1636183. Web of Science, Google Scholar
F. F. J. M. Remacle and G. Friedrich, Euro. Arch. Otorhinolaryngol. 260(1), 1 (2003). Crossref, Web of Science, Google Scholar
C. A. Rosen and T. Murry, The Otolaryngol. Clin. North America 33(9), 1035 (2000). Crossref, Web of Science, Google Scholar
B. Schölkopf, Support vector learning, Ph.D. thesis, Berlin University, Berlin (1997) . Google Scholar
B. Seroussi and J. Bouaud, Artif. Intell. Med. 29(1–2), 153 (2003), DOI: 10.1016/S0933-3657(03)00040-X. Crossref, Web of Science, Google Scholar
J. Shawe-Taylor and N. Cristianini , Kernel Methods for Pattern Analysis ( Cambridge University Press , Cambridge, UK , 2004 ) . Crossref, Google Scholar
P. Taylor, J. Fox and A. T. Pokropek, Med. Imag. Anal. 3(4), 321 (1999), DOI: 10.1016/S1361-8415(99)80027-9. Crossref, Google Scholar
A. Verikaset al., Lecture Notes in Artificial Intelligence 3533, eds. M. Ali and F. Esposito (Springer-Verlag, Heidelberg, 2005) pp. 69–78. Google Scholar
A. Verikaset al., Artif. Intell. Med. 36(1), 71 (2006), DOI: 10.1016/j.artmed.2004.11.001. Crossref, Web of Science, Google Scholar
A. Verikaset al., Patt. Recogn. Lett. 20, 429 (1999), DOI: 10.1016/S0167-8655(99)00012-4. Crossref, Web of Science, Google Scholar
G. Wyszecki and W. S. Stiles , Color Science. Concepts and Methods, Quantitative Data and Formulae , 2nd edn. ( John Wiley , NY , 1982 ) . Google Scholar
S. M. Zeitels , Atlas of phonomicrosurgery and other endolaryngeal procedures for benign and malignant disease ( Singular , San Diego , 2001 ) . Google Scholar
S. Y. Zhu, K. N. Plataniotis and A. N. Venetsanopoulos, Opt. Engin. 38(4), 612 (1999), DOI: 10.1117/1.602105. Web of Science, Google Scholar