COMPARISON AND PERFORMANCE ANALYSIS OF IMAGE SEGMENTATION ALGORITHMS ON BRAIN TUMOR DETECTION

Öz

Image processing techniques in Clinical Decision Support System (CDSS) are often used. In this study, image processing techniques are used in order to detect a common disease, brain tumor. Brain tumors in magnetic resonance images (MRI) are detected by using image segmentation algorithms. MR images have been taken from state hospitals with official permissions in order to use in the study. Brain tumors in MR images are tried to be detected through the Markov Random Field (MRF), Kapur, Kittler and Otsu algorithms. Algorithms were tested on the specific regions (ROI – Region of Interest) of MR images, separately. In experimental applications, Markov Random Field (MRF) algorithm has given more accurate results than the other algorithms

BEYİN TÜMÖRÜ TESPİTİNDE GÖRÜNTÜ BÖLÜTLEME YÖNTEMLERİNE AİT BAŞARIMLARIN KARŞILAŞTIRILMASI VE ANALİZİ

Öz

Görüntü işleme teknikleri klinik karar destek sistemlerinde (KKDS) sıklıkla kullanılmaktadır. Bu çalışmada çağın önemli bir hastalığı olan beyin tümörlerinin görüntü işleme teknikleri ile tespit görüntülerinden (MRI) yararlanarak beyin tümörünün görüntü segmentasyonu ile tespit edilmesine yönelik bir çalışma gerçekleştirilmiştir. Devlet hastanelerinden MR görüntüleri resmi izinlerle alınmış ve çalışmada kullanılmıştır. Markov Random Field (MRF), Kapur, Kittler ve Otsu algoritmaları ile MR görüntülerindeki tümörlü bölgeler tespit edilmeye çalışılmıştır. Algoritmalar, MR görüntülerinin daha önceden belirlenmiş bölgelerine (ROI – Region of Interest) ayrı ayrı uygulanmıştır. Yapılan deneysel uygulamada Markov Random Field (MRF) algoritmasının beyin tümörü tespitinde diğer algoritmalara oranla daha başarılı sonuçlar verdiği gözlemlenmiştir

Kaynakça

1. Arzu, İ. L. Ç. E., Burcu TOTUR, and Türkan "Evaluation of Patients With Brain Tumors According to International NANDA Nursing Diagnoses: Care Suggestions." Neurological Sciences, 27.2. Journal of Dicle, A., Baksi Şimşek, A., 2010. MD
2. Anderson Beyin Tümörü Semptom Envanteri'nin Güvenilirliği. ve Bauer, S., Wiest, R., Nolte, L. P., & Reyes, M. 2013. A survey of MRI- based medical image analysis for brain tumor studies. Physics in medicine and biology, 58(13), R97.
3. Gordillo, N., Montseny, E., & Sobrevilla, P. (2013). State of the art survey on MRI brain tumor segmentation. Magnetic resonance imaging, 31,8:1426-1438.
4. Fazli, S., Nadirkhanlou, P. 2013. A novel method for automatic segmentation of brain tumors in
5. MRI images, arXiv preprint arXiv, 7573.
6. Gajanayake, G. M. N. R., Roshan Dharshana Yapa, B. Hewawithana. "Comparison of standard image segmentation methods for segmentation of brain tumors from D MR images." Industrial and Information Systems (ICIIS), 2009
7. International Conference on. IEEE. DOI: 1109/ICIINFS.2009.5429848 Kurat, N., Ozkaya N. 2014.
8. Automaticly extracting brain tumor from MR image, Signal Processing and Communications Applications Conference (SIU) on IEEE, 22nd. IEEE, 1109/SIU.2014.6830533

9. Havaei, M., Davy, A., Warde-Farley, D., Biard, A., Courville, A., Bengio, Y., . & Larochelle, H. 2017. Brain tumor segmentation with deep neural networks. Medical image analysis, : 31. DOI: 1016/j.media.2016.05.004
10. Huang, Mengxing, Wenjiao Yu, and Donghai Zhu. 2012. "An improved image segmentation algorithm based on the Otsu method."
11. Software Engineering, Artificial Intelligence, Parallel & Distributed Computing (SNPD), 13th ACIS International Conference 1109/SNPD.2012.26 and on. IEEE. DOI:
12. Zhou, Chenhang, et al. 2015. "A method of Two-Dimensional Otsu image threshold segmentation based
13. Algorithm." Cyber Technology in Automation, Intelligent International Conference on IEEE. DOI: 1109/CYBER.2015.7288151
14. Prema, V., M. Sivasubramanian, and S. Meenakshi. 2016. "Brain cancer feature extraction using otsu's thresholding segmentation." BRAIN 3.
15. Liu, J., Zheng, J., Tang, Q., & Jin, W. Minimum error thresholding segmentation algorithm based on d Mathematical Engineering, 2014. histogram. Problems in
16. Bhandari, Ashish Kumar, et al. "Cuckoo search algorithm and wind driven optimization based study of satellite image segmentation thresholding entropy." Expert Systems with Applications 41.7: 3538-3560. DOI: https://doi.org/10.1016/j.eswa.20 10.059 multilevel Kapur’s
17. Roy, P.K., Bhuiyan, A., Janke A., Desmond P.M., Wong. T.Y. 2015.
18. Automatic white matter lesion segmentation enhanced FLAIR intensity and Markov Computerized Medical Imaging and Graphics, 45: 102-111. DOI: https://doi.org/10.1016/j.compme dimag.2015.08.005 contrast Random Field,
19. Uzunbas, M.G., Chen C., Metaxas D., An efficient conditional random automatic and interactive neuron segmentation, Analysis, 1016/j.media.2015.06.003
20. Kutarnia, J., Pedersen, P. A 2015.
21. Markov random field approach to group-wise mosaicing with application to ultrasound, Medical Image Analysis, : 1016/j.media.2015.05.011
22. Otsu, N., 1975. A threshold selection method from gray-level histograms, Automatica, 11 (285-296), 23-27.
23. Sezgin, M., Sankur, B. 2004. Survey over image thresholding techniques and evalution, Journal of Electronic Imaging, http://dx.doi.org/10.1117/1.1631 DOI:
24. Kapur, J. N., Sahoo, P. K., & Wong, A. K. 1985. A new method for gray- level picture thresholding using the entropy of the histogram, Computer vision, processing, 29,3: 273-285. image
25. Kittler, J., Illingworth, J., 1986.
26. Minimum Error Thresholding, Pattern recognition, 19: 41-47. Kilic, İ. and Kayacan. O. 2012.
27. Physica A: Statistical Mechanics and its Applications, Generalized ICM for image segmentation based on Tsallis statistics, 20, 4899-4908.
28. Zeng, M., Han, T., Meng, Q., Bai, Z., & Liu, Z. 2012. Image thresholding based on edge information analysis,
29. In Image and Signal Processing (CISP)5th International Congress on 1109/CISP.2012.6469984 DOI: FAWCETT, Tom. introduction to ROC analysis.
30. Pattern Recognition Letters, 27,8: 874. https://doi.org/10.1016/j.patrec.2 10.010 An DOI: