International Journal of Computer and Information Technology

Open Access Open Access  Restricted Access Subscription Access

Analysis of the Convolutional Neural Network Model in Detecting Brain Tumor


Affiliations
1 Department of Mathematics Howard University Washington DC, United States
2 Department of Mathematics Defiance College Defiance OH, United States
 

Detecting brain tumors is an active area of research in brain image processing. This paper proposes a methodology to segment and classify brain tumors using magnetic resonance images (MRI). Convolutional Neural Networks (CNN) are one of the effective detection methods and have been employed for tumor segmentation. We optimized the total number of layers and epochs in the model. First, we run the CNN with 1000 epochs to see its best-optimized number. Then we consider six models, increasing the number of layers from one to six. It allows seeing the overfitting according to the number of layers.

Keywords

component; Convolutional Neural Network, Brain Tumor, Data Augmentation.
User
Notifications
Font Size

  • S. Bakas, H. Akbari, A. Sotiras, M. Bilello, M. Rozycki, J. S. Kirby, J. B.Freymann, K. Farahani, and C. Davatzikos, “Advancing the cancer genomeatlas glioma mri collections with expert segmentation labels and radiomicfeatures,”Scientific data, vol. 4, no. 1, pp. 1–13, 2017.

  • M. Prastawa, E. Bullitt, S. Ho, and G. Gerig, “A brain tumor segmentationframework based on outlier detection,”Medical image analysis, vol. 8, no. 3,pp. 275–283, 2004.

  • A. Jalalifar, H. Soliman, M. Ruschin, A. Sahgal, and A. Sadeghi-Naini,“A brain tumor segmentation framework based on outlier detection usingone-class support vector machine,” in2020 42nd Annual International Conerence of the IEEE Engineering in Medicine & Biology Society (EMBC).IEEE, 2020, pp. 1067–1070.

  • L. Harper, F. Barkhof, P. Scheltens, J. M. Schott, and N. C. Fox, “An algo-rithmic approach to structural imaging in dementia,”Journal of Neurology,Neurosurgery & Psychiatry, vol. 85, no. 6, pp. 692–698, 2014.

  • G. B. Frisoni, N. C. Fox, C. R. Jack, P. Scheltens, and P. M. Thompson,“The clinical use of structural mri in alzheimer disease,”Nature ReviewsNeurology, vol. 6, no. 2, pp. 67–77, 2010.

  • R. C. Petersen, P. Aisen, L. A. Beckett, M. Donohue, A. Gamst, D. J.Harvey, C. Jack, W. Jagust, L. Shaw, A. Togaet al., “Alzheimer’s dis-ease neuroimaging initiative (adni): clinical characterization,”Neurology,vol. 74, no. 3, pp. 201–209, 2010.

  • S. Qiu, P. S. Joshi, M. I. Miller, C. Xue, X. Zhou, C. Karjadi, G. H. Chang,A. S. Joshi, B. Dwyer, S. Zhuet al., “Development and validation of an in-terpretable deep learning framework for alzheimer’s disease classification,”Brain, vol. 143, no. 6, pp. 1920–1933, 2020.

  • C. A. Charu,Neural Networks and Deep Learning: A Textbook. Spinger,2018.

  • L. Alzubaidi, J. Zhang, A. J. Humaidi, A. Al-Dujaili, Y. Duan, O. Al-Shamma, J. Santamaŕ ıa, M. A. Fadhel, M. Al-Amidie, and L. Farhan,“Review of deep learning: Concepts, cnn architectures, challenges, appli-cations, future directions,”Journal of big Data, vol. 8, no. 1, pp. 1–74,2021.

  • S. Afaq and S. Rao, “Significance of epochs on training a neural network,”International Journal of Scientific and Technology Research, vol. 19, no. 6,pp. 485–488, 2020.

  • S. Irsheidat and R. Duwairi, “Brain tumor detection using artificial convo-lutional neural networks,” in2020 11th International Conference on Infor-mation and Communication Systems (ICICS), 2020, pp. 197–203.


Abstract Views: 94

PDF Views: 68




  • Analysis of the Convolutional Neural Network Model in Detecting Brain Tumor

Abstract Views: 94  |  PDF Views: 68

Authors

Destiny Rankins
Department of Mathematics Howard University Washington DC, United States
Yeona Kang
Department of Mathematics Howard University Washington DC, United States
Dewayne A. Dixon
Department of Mathematics Howard University Washington DC, United States
Seonguk Kim
Department of Mathematics Defiance College Defiance OH, United States

Abstract


Detecting brain tumors is an active area of research in brain image processing. This paper proposes a methodology to segment and classify brain tumors using magnetic resonance images (MRI). Convolutional Neural Networks (CNN) are one of the effective detection methods and have been employed for tumor segmentation. We optimized the total number of layers and epochs in the model. First, we run the CNN with 1000 epochs to see its best-optimized number. Then we consider six models, increasing the number of layers from one to six. It allows seeing the overfitting according to the number of layers.

Keywords


component; Convolutional Neural Network, Brain Tumor, Data Augmentation.

References