Beyin Tümörü Varlığının Geleneksel Derin Öğrenme Tekniği Kullanılarak Tespiti ve MR Görüntülerinde K-Means Segmentasyonu Kullanılarak Kesin Tümör Konumlarının Belirlenmesi

Year 2020, Volume: 1 Issue: 2, 91 - 97, 31.12.2020

Muhammed Oguz Tas , Semih Ergin

Abstract

Beyin dokusunda bulunan hücrelerin anormal bir şekilde büyümesi ile beyinde tümörler meydana gelmektedir. Beyinde bulunan tümörlerin büyük bir miktarı kanserli olduğu için, tümörlü beyin hasta kişinin ölümüne kadar sonuçlar doğurabilir. Beyin tümörlerinin görüntülenmesinde yaygın olarak MR görüntüleme araç olarak kullanılmaktadır. MR görüntüleri, görüntünün doku, karşıtlık, parlaklık ve sınır bilgilerini kullanarak hastalıklı bölgeler ile sağlıklı bölgeleri ayırabilmektedir. Bu sayede, beyin tümörünün şekli, konumu, büyüklüğü, alanı bulunarak hastalığın tedavi sürecinin planlaması yapılabilmektedir. Bu çalışmada, derin öğrenme yardımı ile MR görüntülerinde beyin tümörünün tespit edilmesi ve K-means ile bölütlenmesi işlemi yapılmaktadır. Çalışma sonucunda beyin tümörünün tespit edilmesinde elde edilen doğruluk oranı %84.45, hassasiyet %95.04 olarak bulunmuştur. Çalışma ile, tam otomatik bir beyin tümörü tespit etme ve bölütleme önerilerek, tümörlü bölgenin doğru bir şekilde çıkarılması amaçlanmıştır.

Keywords

manyetik rezonans görüntüleme, beyin tümör tanıma, beyin tümör bölütleme, derin öğrenme, k-means

Detection of the Brain Tumor Existance Using a Traditional Deep Learning Technique and Determination of Exact Tumor Locations Using K-Means Segmentation in MR Images

Abstract

Tumors occur in the brain as the cells in the brain tissue grow abnormally. Since a large amount of tumors in the brain are cancerous, it can have consequences until the death of the sick person. MR imaging is widely used as a means of imaging brain tumors. MR images can distinguish diseased areas and healthy areas using the image's texture, contrast, brightness and boundary information. In this way, planning of the treatment process of the disease can be made by finding the shape, location, size and area of the brain tumor. In this study, the detection of the brain tumor in MR images by using deep learning and the segmentation with K-means are performed. As a result of the study, the accuracy obtained in detecting of the brain tumor is 84.45%, and the sensitivity is 95.04%. The study proposed detection and segmentation of the brain tumor and, extracting the tumor area automatically.

Keywords

magnetic resonance imaging, brain tumor detection, brain tumor segmentation, deep learning, k-means

References

• Akkus, Z., Ali, I., Sedlar, J., Kline, T. L., Agrawal, J. P., Parney, I. F., ... Erickson, B. J. (2016). Predicting 1p19q chromosomal deletion of low-grade gliomas from MR images using deep learning. arXiv preprint arXiv:1611.06939.
• Arunkumar, N., Mohammed, M. A., Ghani, M. K. A., Ibrahim, D. A., Abdulhay, E., Ramirez-Gonzalez, G., … Albuquerque, V. H. C. (2019). K-means clustering and neural network for object detecting and identifying abnormality of brain tumor. Soft Computing, 23(19), 9083-9096.
• Bahadure, N. B., Ray, A. K., Thethi, H. P. (2017). Image analysis for MRI based brain tumor detection and feature extraction using biologically inspired BWT and SVM. International journal of biomedical imaging, 2017,1-12, https://doi.org/10.1155/2017/9749108 1-12.
• Bobotov, Z. and Bene, W. S. (2016). Segmentation of Brain Tumors from Magnetic Resonance Images using Adaptive Thresholding and Graph Cut Algorithm. In The 20th Central European Seminar on Computer Graphics, April 24-27, Slovakia.
• Cabria, I. and Gondra, I. (2017). MRI segmentation fusion for brain tumor detection. Information Fusion, 36, 1-9.
• Damodharan, S. and Raghavan, D. (2015). Combining Tissue Segmentation and Neural Network for Brain Tumor Detection. International Arab Journal of Information Technology (IAJIT), 12(1), 42-52.
• Dong, H., Yang, G., Liu, F., Mo, Y., Guo, Y. (2017). Automatic brain tumor detection and segmentation using U-Net based fully convolutional networks. In annual conference on medical image understanding and analysis, pp. 506-517. July 11–13, UK.
• Gurusamy, R. and Subramaniam, V. (2017). A machine learning approach for MRI brain tumor classification. Computers, Materials & Continua, 53(2), 91-108.
• 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, 35, 18-31.
• Hussain, S., Anwar, S. M., Majid, M. (2017). Brain tumor segmentation using cascaded deep convolutional neural network. In 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 1998-2001, 11-15 July, South Korea.
• Iqbal, S., Ghani, M. U., Saba, T., Rehman, A. (2018). Brain tumor segmentation in multi‐spectral MRI using convolutional neural networks (CNN). Microscopy research and technique, 81(4), 419-427.
• Kaggle. 2019. Internet: https://www.kaggle.com/navoneel/brain-mri-images-for-brain-tumor-detection
• Kaya, I. E., Pehlivanlı, A. Ç., Sekizkardeş, E. G., Ibrikci, T. (2017). PCA based clustering for brain tumor segmentation of T1w MRI images. Computer methods and programs in biomedicine, 140, 19-28.
• Khan, M. A., Lali, I. U., Rehman, A., Ishaq, M., Sharif, M., Saba, T., … Akram, T. (2019). Brain tumor detection and classification: A framework of marker‐based watershed algorithm and multilevel priority features selection. Microscopy research and technique, 82(6), 909-922.
• Menze B., Jakab A., Bauer S., Kalpathy-Cramer J., Farahani K., Kirby J., … Leemput K.V. (2015). The Multimodal brain tumor image segmentation benchmark (brats). IEEE Trans Med Imaging, 34(10):1993-2024.
• Nazir, M., Khan, M. A., Saba, T., Rehman, A. (2019). Brain Tumor Detection from MRI images using Multi-level Wavelets. In 2019 International Conference on Computer and Information Sciences (ICCIS), pp. 1-5, 3-4 April, Saudi Arabia.
• Pereira, S., Pinto, A., Alves, V., Silva, C. A. (2016). Brain tumor segmentation using convolutional neural networks in MRI images. IEEE transactions on medical imaging, 35(5), 1240-1251.
• Ronneberger, O., Fischer, P., Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention, pp. 234-241, October 5-9, Germany.
• Saouli, R., Akil, M., Kachouri, R. (2018). Fully automatic brain tumor segmentation using end-to-end incremental deep neural networks in MRI images. Computer methods and programs in biomedicine, 166, 39-49.
• Soltaninejad, M., Yang, G., Lambrou, T., Allinson, N., Jones, T. L., Barrick, T. R., ... Ye, X. (2018). Supervised learning based multimodal MRI brain tumour segmentation using texture features from supervoxels. Computer methods and programs in biomedicine, 157, 69-84.
• Soltaninejad, M., Zhang, L., Lambrou, T., Yang, G., Allinson, N., Ye, X. (2019). MRI brain tumor segmentation using random forests and fully convolutional networks. arXiv preprint arXiv:1909.06337.
• Thaha, M. M., Kumar, K. P. M., Murugan, B. S., Dhanasekeran, S., Vijayakarthick, P., Selvi, A. S. (2019). Brain tumor segmentation using convolutional neural networks in MRI images. Journal of medical systems, 43(9), 294.
• The Whole Brain Atlas. 2019. Internet: http://www.med.harvard.edu/AANLIB/home.html