Enhanced Brain Tumor Diagnosis with EfficientNetB6: Leveraging Transfer Learning and Edge Detection Techniques

Adnan Hameed; Arsalan Khan; Sohail Ahmad; Sibghat Ullah; Abdul Nasir Khan; Sadiq Nawaz Khan

Authors

Adnan Hameed Department of Computer Science University of Science and technology Bannu, KP, Pakistan.
Arsalan Khan Department of Computer Science University of Science and technology Bannu, KP, Pakistan.
Sohail Ahmad Department of Computer Science University of Science and technology Bannu, KP, Pakistan.
Sibghat Ullah Department of Computer Science University of Science and technology Bannu, KP, Pakistan.
Abdul Nasir Khan Department of Computer Science University of Science and technology Bannu, KP, Pakistan.
Sadiq Nawaz Khan Department of Computer Science University of Science and technology Bannu, KP, Pakistan.

Keywords:

Brain tumor, Medical imaging, Computer-aided diagnosis, EfficientNetB6, CNNs, Transfer learning

Abstract

Correct identification of brain tumors is crucial for determining the subsequent steps in patient management and prognosis. This study introduces a novel approach by mimicking three enhanced deep learning models EfficientNetB0, EfficientNetB6, and ResNet50 on a dataset of 7022 MRI instances, each depicting one of four varieties of brain tumors. The research was conducted using advanced neural network architectures, leveraging transfer learning to improve model performance. Results indicated that EfficientNetB6 achieved the highest testing accuracy at 99.39%, outperforming EfficientNetB0 and ResNet50, which recorded test accuracies of 95% and 97% respectively. Evaluation metrics further highlighted the superior performance of EfficientNetB6, with a precision, recall, and F1 score all at 99%. These findings demonstrate the significant potential of deep learning algorithms in enhancing the diagnostic accuracy of brain tumors, suggesting their implementation in clinical settings could lead to better diagnosis and treatment options.

References

W. Sun, C., Wang, X., Zhang, “Deep learning-based brain tumor classification using convolutional neural network,” J. Med. Imaging Heal. Informatics, vol. 10, no. 1, pp. 209–219, 2020.

L. Zhao, Z., Chen, Y., Liu, “Transfer learning with convolutional neural networks for brain tumor classification,” Front. Neurosci., vol. 15, 2021.

X. Pei, L., Liu, T., Chen, L., Zhang, J., Zhou, “Brain tumor classification via a multimodal data mining framework,” IEEE Access, vol. 8, pp. 106492–106499, 2020.

Y. Shankar, K., Zhang, Y., Liu, “A review of deep learning techniques for brain tumor classification using MRI,” Artif. Intell. Med., vol. 120, pp. 102–192, 2022.

P. Afshar, A. Mohammadi, and K. N. Plataniotis, “Brain Tumor Type Classification via Capsule Networks,” Proc. - Int. Conf. Image Process. ICIP, pp. 3129–3133, Aug. 2018, doi: 10.1109/ICIP.2018.8451379.

H. Chen, J., Liu, W., Yu, “Hybrid neural network for brain tumor classification using CNN and ANN,” IEEE Trans. Neural Networks Learn. Syst., vol. 3, no. 34, pp. 1056–1068, 2023.

H. Dong, G. Yang, F. Liu, Y. Mo, and Y. Guo, “Automatic Brain Tumor Detection and Segmentation Using U-Net Based Fully Convolutional Networks,” Commun. Comput. Inf. Sci., vol. 723, pp. 506–517, 2017, doi: 10.1007/978-3-319-60964-5_44.

P. Roy, S., Menon, N., Raveendran, “Brain tumor classification using VGG-19 architecture with transfer learning,” J. Phys. Conf. Ser., vol. 1767, no. 1, 2021.

S. Kumar, S., Singh, M., Vashisth, “Ensemble learning techniques for brain tumor classification using CNN,” J. Healthc. Eng., 2022.

F. Islam, M., Zhang, Y., Karray, “Brain tumor segmentation and classification from magnetic resonance images: Review of the state-of-the-art methods.,” Annu. Rev. Control, vol. 50, pp. 298–321, 2020.

W. Yang, H., Yu, S., Zhu, “Glioma classification using deep convolutional neural networks,” 2020 IEEE Int. Conf. Bioinforma. Biomed., pp. 1688–1692, 2020.

H. I. Shen, D., Wu, G., Suk, “Deep learning in medical image analysis,” Annu. Rev. Biomed. Eng., vol. 24, pp. 221–251, 2022.

M. J. Wang, G., Li, W., Ourselin, S., Vercauteren, T., Cardoso, “Brain tumor classification using 3D deep learning-based ensemble framework,” Med. Image Anal., vol. 75, pp. 102–305, 2023.