Evrişimli Sinir Ağları Kullanarak Beyin Tümörü Sınıflandırması

Year 2024, Volume: 04 Issue: 02, 176 - 183, 31.12.2024

Firuze Damla Eryılmaz Baran Meric Cetin

Abstract

Bu çalışmada, evrişimli sinir ağlarına dayalı olarak beyin MRI görüntülerinden beyin tümörünün erken teşhisini kolaylaştıran üç farklı derin öğrenme çerçevesi tasarlanmıştır. Beyin tümörü sınıflandırmasını yapabilmek için ResNet50, VGG16 ve InceptionV3 gibi literatürde çokça kullanılan mimariler tercih edilmiştir. Deneyler için hem orjinal MRI görüntüleri hem de çeşitli manipülasyon teknikleri ile oluşturulan sentetik veriler kullanılmıştır. İkili beyin tümörü sınıflandırma sürecine ek olarak, tasarlanan üç evrişimli sinir ağı modelinde iki farklı aktivasyon fonksiyonunun kullanımdaki etkisi de araştırılmıştır. Yapılan deneylere ait performans ölçütleri doğruluk, F-skor, kesinlik, hassasiyet ve hata oranı metrikleri ile sunulmuştur. Simülasyon sonuçlarında, evrişimli sinir ağının son katmanındaki aktivasyon fonksiyonunun seçimine göre sırasıyla InceptionV3 modeli için ortalama %96,75 doğruluk oranı ve ResNet50 modeli için ortalama %97,75 doğruluk oranı elde edilmiştir.

Keywords

CNN, Beyin tümorü, sınıflandırma, resnet50, vgg16, inceptionv3.

Project Number

ICES2024 bildirisidir

Brain Tumor Classification Using Convolutional Neural Networks

Abstract

In this paper, three different deep learning frameworks were designed based on convolutional neural networks that facilitate the early diagnosis of brain tumors from brain MRI images. In order to classify brain tumors, several architectures that are widely used in the literature such as ResNet50, VGG16 and InceptionV3 have been preferred. Both the original MRI images and synthetic images generated by various manipulation techniques were used for the experiments. In addition to the binary brain tumor classification process, the effect of two different activation functions on the use of the designed three-convolutional neural network model was also investigated. Performance measures of the experiments have been presented with accuracy, F-score, precision, precision and error rate metrics. In the simulation results, according to the selection of the activation function in the last layer of the convolutional neural network, an average \%96.75 accuracy rate for the InceptionV3 model and an average of \%97.75 accuracy rate for the ResNet50 model were obtained, respectively.

Keywords

CNN, Brain Tumor, Classification, ResNet50, VGG16, InceptionV3.

Project Number

ICES2024 bildirisidir

References

• [1] J. Amin et al., “Brain tumor detection: A Long Short-term Memory (LSTM)-based Learning Model.” Neural Computing and Applications, vol. 32, no. 20, pp. 15965-15973, 2020.
• [2] A. Saleh, R. Sukaik, S. S. Abu-Naser, “Brain Tumor Classification Using Deep Learning.” International Conference on Assistive and Rehabilitation Technologies., pp. 131-136, 2020.
• [3] H. A. Khan et al., “Brain Tumor Classification in MRI Image Using Convolutional Neural Network.” Math. Biosci. Eng, 17, pp. 6203, 2020.
• [4] T. Sadad et al., “Brain Tumor Detection and Multi-Classification Using Advanced Deep Learning Techniques. Microscopy Research and Technique.” vol. 84, no. 6, pp. 1296-1308, 2021.
• [5] P. Saxena, A. Maheshwari, S. Maheshwari, “Predictive Modeling of Brain Tumor: A Deep Learning Approach.” Innovations in Computational Intelligence and Computer Vision. pp. 275-285, 2021.
• [6] H. Mohsen et al., “Classification Using Deep Learning Neural Networks for Brain Tumors.”Future Computing and Informatics Journal, vol. 3, no. 1, pp. 68-71, 2018.
• [7] F. Citak et al., “Machine Learning in Grading of Gliomas Based on Multi-parametric Magnetic Resonance Imaging at 3t. Computers in Biology and Medicine, 99, pp. 154-160, 2018.
• [8] S. Deepak and P. Ameer, “Brain Tumor Classification Using Deep CNN Features via Transfer Learning.” Computers in Biology and Medicine, 111, pp. 103345, 2019.
• [9] K. Vaidhya, S. Thirunavukkarasu, V. Alex, and G. Krishnamurthi, “Multi-modal Brain Tumor Segmentation Using Stacked Denoising Autoencoders.” BrainLes. Springer, pp. 181-194, 2015.
• [10] A. Rehman, S. Naz, M. I. Razzak, F. Akram and M. Imran, “A Deep Learning-based Framework for Automatic Brain Tumors Classification Using Transfer Learning.” Circuits, Systems, and Signal Processing, vol. 39, no. 2, pp. 757-775, 2020.
• [11] V. Romeo et al., “ Prediction of Tumor Grade and Nodal Status in Oropharyngeal and Oral Cavity Squamous-cell Carcinoma Using a Radiomic Approach. Anticancer Research, vol. 40, no.1, pp. 271-280, 2020.
• [12] K. He, X. Zhang, S. Ren and J. Sun, “Deep Residual Learning for Image Recognition.” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770-778, 2016.
• [13] K. Simonyan and A. Zisserman, “Very Deep Convolutional Networks for Large-scale Image Recognition.” ArXiv Preprint arXiv:1409.1556, 2014.
• [14] C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens and Z. Wojna, “Rethinking the Inception Architecture for Computer Vision.” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818-2826, 2016.
• [15] H. Kutlu and E. Avcı, “A Novel Method for Classifying Liver and Brain Tumors Using Convolutional Neural Networks, Discrete Wavelet Transform and Long Short-term Memory Networks.” Sensors, vol. 19, no. 9, pp. 1992, 2019.