Ses Tellerinde Oluşan Nodüllere Ait Şekilsel Özelliklerin Görüntü İşleme Teknikleriyle Otomatik Olarak Belirlenmesi
Abstract
Gelişen teknolojik altyapı sayesinde medikal görüntüleme cihazları, ses tellerinin yapısal bozulmalarını ve titreşimlerini kolaylıkla incelemektedir Ancak ses telleri üzerinde oluşan nodül, polip gibi benzer patolojik bulgu gösteren lezyonların teşhisi bazen zor olmaktadır. Bu amaçla, yapılan çalışmada ses telleri üzerinde bulunan nodüller görüntü işleme teknikleri kullanılarak, otomatik olarak bölütlenmiş ve bu nodüllere ait alan, çevre, gibi şekilsel özelliklerin de çıkarımına yönelik bir yazılım geliştirilmiştir. Oluşturulan yazılım sayesinde, histogram tabanlı önişleme ve gradyan tabanlı görüntü işleme teknikleriyle nodüller bölütlenmiştir. Daha sonra uzman doktor tarafından elle belirlenen nodüller ile otomatik bölütlenen nodüller çakıştırılmış ve ZSI benzerlik indeksi ile yazılımın başarısı test edilmiştir. 0,71 ile 0,.89 arasında ZSI değerleri elde edilmiştir. Literatürde 0.7 ve üzeri değerler başarılı olarak kabul edilmektedir.
Keywords
References
- Hansen, J. H.,Gavidia-Ceballos, L. ve Kaiser, J. F., (1998). “A nonlinearoperator-based speech feature analysis method with application to vocal fold pathology assessment”, Biomedical Engineering, IEEE Transactions on, 45(3): 300-313
- Ilgner, J. F., Palm, C., Schutz, A. G., Spitzer, K., Westhofen, M. ve Lehmann, T. M., (2003). “Colour texture analysis for quantitative laryngoscopy”, Acta Otolaryngologıca, 123(6): 730-734.
- Lohscheller, J., Toy, H., Rosanowski, F., Eysholdt, U. ve Döllinger, M., (2007). “Clinically evaluated procedure for the reconstruction of vocal fold vibrations from endoscopic digital high-speed videos”, Medical image analysis, 11(4) : 400-413.
- Türkmen H.İ., Karsligil M.E., Koçak İ., “Classification Of Vocal Fold Nodules And Cysts Based On Vascular Defects Of Vocal Folds”, MLSP 2013, Southampton, United Kingdom
- Verikas, A., Gelzinis, A., Bacauskiene, M. ve Uloza, V., (2006). “Towards a computer-aided diagnosis system for vocal cord diseases”, Artificial Intelligence in Medicine, 36(1): 71-84
- Yan, Y., Ahmad, K., Kunduk, M. ve Bless, D., (2005). “Analysis of vocal-fold vibrations from high-speed laryngeal images using a Hilbert transform-based methodology”, Journal of voice, 19(2): 161-175.
- Zijdenbos, A. P., Dawant, B. M., Margolin, R. A. and Palmer, A. C., “Morphometric analysis of white matter lesions in MR images: Method and validation”, IEEE Trans Med Imag. 13:716–24, 1994
Automatic Determination of the Morphometric Properties of Nodules in the Vocal Cord by Image Processing Techniques
Abstract
Thanks to the developing technological infrastructure, medical imaging devices are easily examining the structural distortions and vibrations of vocal tractors. However, it is sometimes difficult to diagnose lesions with similar pathologic findings, such as nodules, polyps. For this purpose, in the study, the nodules on the vocal cord were automatically segmented using image processing techniques and a software developed for extracting the morphological properties of these nodules such as area, perimeter etc. Through the software, the nodules are segmented by histogram-based preprocessing and gradient-based image processing techniques. Then the nodules manually identified by the specialist doctor and the automatically segmented nodules were superimposed and the success of the software with the ZSI similarity index has been tested. ZSI values obtained are between 0.71 and 0.89. In the literature, the values higher than 0.7 are a considered as successful.
Keywords
References
- Hansen, J. H.,Gavidia-Ceballos, L. ve Kaiser, J. F., (1998). “A nonlinearoperator-based speech feature analysis method with application to vocal fold pathology assessment”, Biomedical Engineering, IEEE Transactions on, 45(3): 300-313
- Ilgner, J. F., Palm, C., Schutz, A. G., Spitzer, K., Westhofen, M. ve Lehmann, T. M., (2003). “Colour texture analysis for quantitative laryngoscopy”, Acta Otolaryngologıca, 123(6): 730-734.
- Lohscheller, J., Toy, H., Rosanowski, F., Eysholdt, U. ve Döllinger, M., (2007). “Clinically evaluated procedure for the reconstruction of vocal fold vibrations from endoscopic digital high-speed videos”, Medical image analysis, 11(4) : 400-413.
- Türkmen H.İ., Karsligil M.E., Koçak İ., “Classification Of Vocal Fold Nodules And Cysts Based On Vascular Defects Of Vocal Folds”, MLSP 2013, Southampton, United Kingdom
- Verikas, A., Gelzinis, A., Bacauskiene, M. ve Uloza, V., (2006). “Towards a computer-aided diagnosis system for vocal cord diseases”, Artificial Intelligence in Medicine, 36(1): 71-84
- Yan, Y., Ahmad, K., Kunduk, M. ve Bless, D., (2005). “Analysis of vocal-fold vibrations from high-speed laryngeal images using a Hilbert transform-based methodology”, Journal of voice, 19(2): 161-175.
- Zijdenbos, A. P., Dawant, B. M., Margolin, R. A. and Palmer, A. C., “Morphometric analysis of white matter lesions in MR images: Method and validation”, IEEE Trans Med Imag. 13:716–24, 1994
Details
| Subjects | Electrical Engineering |
|---|---|
| Journal Section | Research Articles |
| Authors | |
| Publication Date | December 27, 2017 |
| Submission Date | November 6, 2017 |
| Published in Issue | Year 2017 |