ENDOSKOPİK GÖRÜNTÜLERİN DEĞERLENDİRİLMESİNDE GÖRÜNTÜ İŞLEME TEMELLİ AKILLI BİR KARAR DESTEK SİSTEMİ

Abstract

Bu çalışmada, kolonoskopik video görüntülerindeki poliplerin yerlerini belirleyen, hekime yardımcı akıllı bir karar destek sistemi sunulmuştur. Sistem, dalgacık dönüşümü eş oluşum matrislerinden çıkarılan öznitelikler ile yapay sinir ağları sınıflandırıcısından oluşmaktadır. Önerilen sistem polip ve normal dokuların bulunduğu bir dizi kolonoskopik video görüntüsüne uygulanmıştır. Elde edilen deneysel sonuçlar özgüllük ve duyarlılık analizi ile değerlendirilmiştir. Kullanılan değerlendirme kriterince gerçekleştirilen bütün uygulamaların sonucunda ortalama % 90.2 duyarlılık ve % 88.7 özgüllük değerleri elde edilmiştir.

Keywords

• Kolonoskopik görüntüler, Polipli doku, Dalgacık dönüşümü, Eş-oluşum matrisleri, Yapay sinir ağları.

AN INTELLIGENT DECISION SUPPORT SYSTEM BASED ON IMAGE PROCESSING FOR EVALUATING OF THE ENDOSCOPIC IMAGES

Abstract

In this study, a decision support system which helps the physician to determine the location of a polyp on the colonoscopic video images is presented. The system is composed of neural network classifier and features extracted from wavelet transform co-occurrence matrices. The proposed methodology is applied to a sequence of colonoscopic video frames which have normal and abnormal formations. The application results are evaluated with respect to the sensitivity and specificity analysis. As a result of the evaluation criterion, 90.2 % sensitivity and 88.7 % specificity values are obtained by using statistical features of the wavelet transform co occurrence matrices and neural networks.

Keywords

• Colonoscopic images, Polyp, Wavelet transform, Co-occurrence matrix, Artificial neural networks.

References

1. Asari, K. V. 2000. “A fast and accurate segmentation technique for the extraction of gastrointestinal lumen from endoscopic images”, Medical Engineering & Physics, Vol. 22, pp. 89-96.
2. Cohen, A., Daubechies, I. and Feauveau, J. C. 1992. Biorthogonal bases of compactly supported wavelets, Commun. Pure Appl. Math. Vol. 45, pp. 485-560.
3. Enderwick, C. and Micheli-Tzanakou, E. 1997. “Classification of mammographic tissue using shape and texture features,” Proc. 19th Annu. Int. Conf. IEEE Engineering Medicine Biology Society, pp. 810-813.
4. Esgiar, A.N., Naguib, R.N.G., Sharif, B.S., Bennett, M.K., Murray, A. 2002. “Fractal analysis in the detection of colonic cancer images”. IEEE Trans Info Technol Biomed; 6: 54-8.
5. Fortin, C. and Ohley, W. 1991. “Automatic segmentation of cardiac images: Texture mapping,” Proc. IEEE 17th Annu. Northeast Bioeng. Conf.
6. Haralick, R.M., Shanmugam, K.K., Dinstein, I. 1973. Texture features for image classification. IEEE Trans. Syst. Man Cyb. 8 (6), 610-621.
7. Houston A. G. and Premkumar, S. B. 1991. “Statistical interpretation of texture for medical applications,” presented at the Biomedical Image Processing and Three Dimensional Microscopy, San Jose, CA..
8. Internet: Tıbbi Onkoloji Derneği, http://www.medonk.org/, Erişim tarihi: 25 Haziran 2006.

9. Internet: Tip 2000. Sağlık Platformu, Kalın barsak (Kolon), rektum ve anüs kanserlrleri, http://www.tip2000.com/tedavi/kolon-rektum/kanser.htm, Erişim tarihi: 26 Haziran 2006.
10. Karkanis, S., Galousi, K. and Maroulis, D. 1999. "Classification of endoscopic images based on texture spectrum", ACAI'99, Workshop on Machine Learning in Medical Applications, Chania, Greece.
11. Karkanis, S.A., Magoulas, G.D., Iakovidis, D.K., Karras, D.A., Maroulis, D.E. 2001. "Evaluation of textural feature extraction schemes for neural network-based interpretation of regions in medical images", IEEE International Conference in Image Processing (ICIP) Proceedings, pp. 281-284, Thessaloniki, Greece.
12. Karkanis, S.A., Iakovidis, D.K., Maroulis, D.E., Karras, D.A. and Tzivras, M. D. 2003. "Computer aided tumor detection in endoscopic video using color wavelet features", IEEE Transactions on Information Technology in Biomedicine, Vol. 7, No. 3.
13. Krishnan, S. M. Yap, C. J., Asari, K. V. and Goh, P. M. Y. 1998. “Neural network based approaches for the classification of colonoscopic images”, Proceedings of the 20th annual international conference of the IEEE Engineering in Medicine and Biology Society, 20: 1678- 1680.
14. Lachmann, F. and Barillot, C. 1992. “Brain tissue classification from MRI data by means of texture analysis,” in Proc. Medical Imaging VI: Image Processing, Vol. 1652. Newport Beach, CA, pp. 72-83.
15. Sujana, H., Swarnamani, S. and Suresh, S. 1996. “Artificial neural Networks for the classification of liver lesions by image texture parameters,” Ultrasound Med. Biol., Vol. 22, pp. 1177-1181.