BEYİN MR GÖRÜNTÜLERİNDEN mRMR TABANLI BEYİN TÜMÖRLERİNİN SINIFLANDIRMASI

Year 2022, Issue: 006, 1 - 9, 31.12.2022

Burak Tasci

Abstract

Beyin tümörleri nedeniyle ölen kişilerin sayısı gün geçtikçe artmaktadır. Beyin tümörünün tedavi planlamasında ve tedavi sonucunun değerlendirilmesinde erken teşhis çok önemlidir. Beyin tümörü olan bir hastanın, hastalığının erken teşhis edilmesi sayesinde doğru tedavi yöntemleri uygulanarak hayatta kalma ihtimali artabilir. Manyetik rezonans (MR) görüntüleme beyin tümörlerinin tanı ve teşhisinde önemli bir role sahiptir. Bununla birlikte, MR görüntüleri kullanarak beyin tümörlerini sınıflandırması beyin yapısının karmaşıklığı ve içindeki dokuların iç içe geçmesi nedeniyle zordur. Bu çalışma, DenseNet201 ön eğitimli modelinin avg_pool ve fc1000 katmalarından elde edilen 2920 özniteliğin 500 adeti mRMR algoritması kullanılarak seçilmiştir. Öznitelik seçimi yapılmadan %95.00 doğruluk, mRMR öznitelik seçimi yapılarak %95.76 doğruluk elde edilmiştir

Keywords

MR görüntüleri, sınıflandırma, beyin tümörü, DVM, K-EYK, mRMR

Thanks

Yazarın teşekkür edeceği herhangi bir kişi ve ya kuruluş bulunmamaktadır.

CLASSIFICATION OF mRMR-BASED BRAIN TUMORS from BRAIN MR IMAGES

Abstract

The number of persons who pass away from brain tumors continues to rise on a daily basis. The planning of treatment and the assessment of the treatment's effectiveness are both significantly aided by an early detection of a brain tumor. A person with a brain tumor may have a better chance of living if the disease is found and treated early and in the right way. Imaging with magnetic resonance, sometimes known as MR imaging, plays an essential part in the detection and diagnosis of brain cancers. However, due to the intricate nature of the brain's structure and the interconnectedness of its tissues, classification of brain tumors using MR imaging can be a challenging endeavor. In this study, 500 of 2920 features obtained from avg_pool and fc1000 layers of DenseNet201 pre-trained model were selected using mRMR algorithm. 95.00% accuracy was obtained without feature selection, and 95.76% accuracy was obtained by mRMR feature selection.

Keywords

MR images, classification, brain tumor, SVM, kNN, mRMR

References

• [1] Abiwinanda, N., Hanif, M., Hesaputra, S. T., Handayani, A., and Mengko, T. R. (2019). Brain tumor classification using convolutional neural network. In World congress on medical physics and biomedical engineering 2018. Springer, Singapore. 183-189.
• [2] Seetha, J., and Raja, S. S. (2018). Brain tumor classification using convolutional neural networks. Biomedical and Pharmacology Journal, 11(3), 1457.
• [3] Lakshmi, M. J., and Nagaraja Rao, S. (2022). Brain tumor magnetic resonance image classification: a deep learning approach. Soft Computing, 1-9.
• [4] Veeramuthu, A., Meenakshi, S., Mathivanan, G., Kotecha, K., Saini, J. R., Vijayakumar, V., and Subramaniyaswamy, V. (2022). MRI brain tumor image classification using a combined feature and image-based classifier. Frontiers in Psychology, 13.
• [5] Li, M., Kuang, L., Xu, S., and Sha, Z. (2019). Brain tumor detection based on multimodal information fusion and convolutional neural network. IEEE Access, 7, 180134-180146.
• [6] Singh, A. (2015, February). Detection of brain tumor in MRI images, using combination of fuzzy c-means and SVM. In 2015 2nd international conference on signal processing and integrated networks (SPIN) , IEEE. 98-102.
• [7] Praveen, G. B., and Agrawal, A. (2015, November). Hybrid approach for brain tumor detection and classification in magnetic resonance images. In 2015 Communication, Control and Intelligent Systems (CCIS), IEEE. 162-166.
• [8] Thirumurugan, P., Ramkumar, D., Batri, K., and Siva Sundhara Raja, D. (2016). Automated detection of glioblastoma tumor in brain magnetic imaging using ANFIS classifier. International Journal of Imaging Systems and Technology, 26(2), 151-156.
• [9] Chen, X., and Konukoglu, E. (2018). Unsupervised detection of lesions in brain MRI using constrained adversarial auto-encoders. arXiv preprint arXiv:1806.04972.
• [10] Chen, X., Pawlowski, N., Rajchl, M., Glocker, B., and Konukoglu, E. (2018). Deep generative models in the real-world: an open challenge from medical imaging. arXiv preprint arXiv:1806.05452.
• [11] (2022, 19.06.2022). Brain Tumor MRI Image Classification (https://www.kaggle.com/datasets/iashiqul/brain-tumor-mri-image-classification).
• [12] Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., and Fergus, R. (2013). Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199.
• [13] Redmon, J., and Farhadi, A. (2017). YOLO9000: better, faster, stronger. In Proceedings of the IEEE conference on computer vision and pattern recognition, 7263-7271.
• [14] Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition, 2818-2826.
• [15] Zoph, B., Vasudevan, V., Shlens, J., and Le, Q. V. (2018). Learning transferable architectures for scalable image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition , 8697-8710.
• [16] Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
• [17] He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, 770-778.
• [18] Szegedy, C., Ioffe, S., Vanhoucke, V., and Alemi, A. A. (2017, February). Inception-v4, inception-resnet and the impact of residual connections on learning. In Thirty-first AAAI conference on artificial intelligence.
• [19] Krizhevsky, A., Sutskever, I., and Hinton, G. E. (2017). Imagenet classification with deep convolutional neural networks. Communications of the ACM, 60(6), 84-90.
• [20] Zhang, X., Zhou, X., Lin, M., and Sun, J. (2018). Shufflenet: An extremely efficient convolutional neural network for mobile devices. In Proceedings of the IEEE conference on computer vision and pattern recognition, 6848-6856.
• [21] Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition , 1251-1258.
• [22] Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L. C. (2018). Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE conference on computer vision and pattern recognition, 4510-4520.
• [23] Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, 4700-4708.
• [24] Iandola, F. N., Han, S., Moskewicz, M. W., Ashraf, K., Dally, W. J., and Keutzer, K. (2016). SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size. arXiv preprint arXiv:1602.07360.
• [25] Tan, M., and Le, Q. (2019, May). Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning, PMLR. 6105-6114.
• [26] Ghassemi, N., Shoeibi, A., and Rouhani, M. (2020). Deep neural network with generative adversarial networks pre-training for brain tumor classification based on MR images. Biomedical Signal Processing and Control, 57, 101678.
• [27] Citak-Er, F., Firat, Z., Kovanlikaya, I., Ture, U., and Ozturk-Isik, E. (2018). Machine-learning in grading of gliomas based on multi-parametric magnetic resonance imaging at 3T. Computers in biology and medicine, 99, 154-160.
• [28] Shahzadi, I., Tang, T. B., Meriadeau, F., and Quyyum, A. (2018, December). CNN-LSTM: cascaded framework for brain tumour classification. In 2018 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES), IEEE. 633-637.