Brain tumor diagnostics with application of hybrid fuzzy convolutional neural networks
DOI:
https://doi.org/10.20535/SRIT.2308-8893.2020.1.06Keywords:
medical diagnostics, brain tumor classification, ANFIS, CNN, hybrid networkAbstract
The problem of classification of brain tumors on medical images is considered. For its solution hybrid CNN-ANFIS is developed in which convolutional neural network VGG-16 and ResNetV2_50 are used as feature extractors while ANFIS is used as the classifier. Training algorithms of ANFIS were implemented. The experimental investigations of the suggested hybrid network on the standard dataset Brain MRI images for brain tumor detection were carried out and comparison with known results was performed.References
Dong H. Automatic Brain Tumor Detection and Segmentation Using U-Net Based Fully Convolutional Networks / H. Dong, G. Yang, F. Liu et al. — 2017.
Arya P. A Survey on Brain Tumor Detection and Segmentation from Magnetic Resonance Image / P. Arya, A.K. Malviya. — 2019.
Zhang Y. One-class kernel subspace ensemble for medical image classification / Y. Zhang, B. Zhang, F. Coenen et al. // EURASIP Journal on Advances in Signal Processing. —2014. — Vol. 2014, N 17. — P. 1–13.
Sundar R. Brain Tumor Detection and Segmentation by Intensity Adjustment / R. Sundar. — 2017.
Singh A. Classifying Biological Images Using Pre-trained CNNs / A. Singh, H. Mansourifar, H. Bilgrami et al. — Available at: https://docs.google.com/document/d/1H7xVK7nwXcv11CYh7hl5F6pM0m218FQloAXQODP-Hsg/ edit?usp=sharing.
Bengio Y. Representation learning:A review and new perspectives / Y. Bengio, A. Courville, P. Vincent // IEEE Transactions on Pattern Analysis and Machine Intelligence. — 2013. — Vol. 35. — P. 1798–1828.
LeCun Y. Deep learning / Y. LeCun, Y. Bengio, G. Hinton // Nature. — 2015. — Vol. 521. — P. 436–444.
Krizhevsky A. Imagenet classification with deep convolutional neural networks / A. Krizhevsky, I. Sutskever, G.E. Hinton // Advances in Neural Information Processing Systems. — 2012. — 25. — P. 1097–1105.
Zaychenko Yu. Medical images of breast tumors diagnostics with application of hybrid CNN–FNN network / Yu. Zaychenko, G. Hamidov, I. Varga // Systemni doslidzhennja ta informatsijni tekhnolohiyi. — 2018. — № 4. — S.37–47.
Zgurovsky M. The Fundamentals of Computational Intelligence: System Approach / M. Zgurovsky, Yu. Zaychenko // Springer International Publishing AG, Switzerland. — 2016. — 308 p.
Brain MRI Images for Brain Tumor Detection. — Available at: https://www.kaggle.com/navoneel/brain-mri-images-for-brain-tumor-detection.
Understanding loss functions: Hinge loss. — Available at: https://medium.com/ analytics-vidhya/understanding-loss-functions-hinge-loss-a0ff112b40a1
Decoupled weight decay regularization. — Available at: https://arxiv.org/pdf/1711.05101.pdf
A Closer Look at Deep Learning Heuristics: Learning rate restarts, Warmup and Distillation. — Available at: https://arxiv.org/abs/1810.13243
On the Difficulty of Warm-Starting Neural Network Training. — Available at: https://arxiv.org/pdf/1910.08475.pdf
