Classification of Brain Tumors in MRI Images

• Andressa G. Moreira UFC
• Stefane A. dos Santos UFC
• Michele F. de Oliveira UFC
• Iális C. de Paula Júnior UFC
• Débora F. de Assis UFC

DOI: https://doi.org/10.5753/sbcas.2024.2396

Abstract

Brain cancer is characterized by the development of malignant tumors. Therefore, early detection is crucial for patient survival. Advances in Artificial Intelligence (AI) have improved medical image analysis. However, classifying projects is still a challenging task. In this study, the transfer learning technique is used to classify the types of tumors into Meningioma, Glioma, Pituitary lesions and cases without tumor, based on magnetic resonance images. For this, the AlexNet, DenseNet201, EfficientNetB7, MobileNetV2 and ResNet50 architectures are used. The EfficientNetB7 network obtained the most promising results, reaching 97.68% for test accuracy.

References

Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamaría, J., Fadhel, M. A., Al-Amidie, M., and Farhan, L. (2021). Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. Journal of big Data, 8:1–74.

Asif, S., Yi, W., Ain, Q. U., Hou, J., Yi, T., and Si, J. (2022). Improving effectiveness of different deep transfer learning-based models for detecting brain tumors from mr images. IEEE Access, 10:34716–34730.

Bhuvaji, S., Kadam, A., Bhumkar, P., Dedge, S., and Kanchan, S. (2020). Brain Tumor Classification (MRI) [Dataset]. Kaggle. [link]. Acesso em 01 de março de 2024.

Bindu, J. H. and Devi, M. U. (2024). Classification of Brain Tumor Images using Segmentation and Transfer Learning. In 2024 5th International Conference on Mobile Computing and Sustainable Informatics (ICMCSI), pages 225–232.

Bow, S.-T. (2002). Pattern Recognition and Image Preprocessing. Marcel Dekker, Inc., USA, 2nd edition.

Brown, M. B. and Forsythe, A. B. (1974). Robust tests for the equality of variances. Journal of the American statistical association, 69(346):364–367.

Chakrabarty, N. (2017). Brain MRI Images for Brain Tumor Detection [Dataset]. Kaggle. [link]. Acesso em 01 de março de 2024.

Cheng, J. (2017). Brain Tumor Dataset. [link]. Acesso em 01 de março de 2024.

Chlap, P., Min, H., Vandenberg, N., Dowling, J., Holloway, L., and Haworth, A. (2021). A review of medical image data augmentation techniques for deep learning applications. Journal of Medical Imaging and Radiation Oncology, 65(5):545–563.

El-Assiouti, O. S., Hamed, G., El-Saadawy, H., Ebied, H. M., and Khattab, D. (2023). Regioninpaint, cutoff and regionmix: Introducing novel augmentation techniques for enhancing the generalization of brain tumor identification. IEEE Access, 11:83232–83250.

Friedman, M. (1937). The use of ranks to avoid the assumption of normality implicit in the analysis of variance. Journal of the american statistical association, 32(200):675–701.

He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 770–778.

Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K. Q. (2017). Densely Connected Convolutional Networks. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 2261–2269.

Instituto Nacional de Câncer (INCA) (2022). Câncer do sistema nervoso central. [link]. Acesso em 01 de março de 2024.

Islam, M. A., Noshin, S. A., Islam, M. R., Razy, M. F., Antara, S., Reza, M. T., and Parvez, M. Z. (2023). A low parametric cnn based solution to efficiently detect brain tumor cells from ultrasound scans. In 2023 IEEE 13th Annual Computing and Communication Workshop and Conference (CCWC), pages 1152–1158.

Kaya, Y. and Gürsoy, E. (2023). A mobilenet-based cnn model with a novel fine-tuning mechanism for covid-19 infection detection. Soft Computing, 27(9):5521–5535.

Krizhevsky, A., Sutskever, I., and Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 25.

Nemenyi, P. B. (1963). Distribution-free multiple comparisons. Princeton University.

Ottom, M. A., Rahman, H. A., and Dinov, I. D. (2022). Znet: Deep learning approach for 2d mri brain tumor segmentation. IEEE Journal of Translational Engineering in Health and Medicine, 10:1–8.

Padmapriya, S. and Devi, M. G. (2024). Computer-Aided Diagnostic System for Brain Tumor Classification using Explainable AI. In 2024 IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI), volume 2, pages 1–6.

Patare, Y., Yadav, S., Pingale, R., and S, K. (2024). Brain Tumor Detection Using Deep Learning(CNN). In 2024 International Conference on Emerging Smart Computing and Informatics (ESCI), pages 1–5.

Raj, J. R. F., Vijayalakshmi, K., Priya, S. K., and Appathurai, A. (2024). Brain tumor segmentation based on kernel fuzzy c-means and penguin search optimization algorithm. Signal, Image and Video Processing, 18(2):1793–1802.

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, pages 4510–4520.

Shapiro, S. S. and Wilk, M. B. (1965). An analysis of variance test for normality (complete samples). Biometrika, 52(3-4):591–611.

Srivastava, A., Khare, A., and Kushwaha, A. (2023). Brain tumor classification using deep learning framework. In 2023 International Conference on Intelligent Systems, Advanced Computing and Communication (ISACC), pages 1–4.

Tan, M. and Le, Q. (2019). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. In International conference on machine learning, pages 6105–6114. PMLR.

Tomasi, C. and Manduchi, R. (1998). Bilateral filtering for gray and color images. In Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271), pages 839–846.

Zuiderveld, K. (1994). Contrast limited adaptive histogram equalization. In Graphics gems IV, pages 474–485.