EfficientNet-Based Transfer Learning for Accurate MRI Brain Tumor Classification
Poster No:
1136
Submission Type:
Abstract Submission
Authors:
Saeed Alqahtani1
Institutions:
1Najran University, najran, najran
First Author:
Introduction:
Background: Accurate brain tumor classification using MRI images is vital for early diagnosis and effective treatment planning. Although deep learning methods have shown potential, achieving high accuracy and ensuring model generalization across diverse datasets remains a challenge.
Problem: Existing automated approaches face difficulties with complex feature extraction and limited generalization, especially when working with datasets of varying sizes. Furthermore, many methods lack comprehensive performance validation using multiple evaluation metrics.
Aim: This study aims to develop and validate a transfer learning-based deep learning model for multi-class brain tumor classification. The proposed model strives to deliver consistent accuracy, reliability, and performance across datasets of varying sizes.
Problem: Existing automated approaches face difficulties with complex feature extraction and limited generalization, especially when working with datasets of varying sizes. Furthermore, many methods lack comprehensive performance validation using multiple evaluation metrics.
Aim: This study aims to develop and validate a transfer learning-based deep learning model for multi-class brain tumor classification. The proposed model strives to deliver consistent accuracy, reliability, and performance across datasets of varying sizes.
Methods:
We introduce Deep-EFNet, an innovative architecture built upon EfficientNetB0 with transfer learning. The model harnesses the robust feature extraction capabilities of EfficientNetB0, enhanced with strategic modifications to boost performance. These include batch normalization for stable training, dropout and L2 regularization to mitigate overfitting, and a hierarchical dense layer structure for enhanced feature representation. To ensure thorough validation, the model was evaluated on two distinct datasets comprising 3,064 and 7,023 MRI images, respectively, covering four classes of brain tumors.
Results:
The experimental evaluation of Deep-EFNet showcased outstanding performance across multiple metrics and datasets. The model achieved an accuracy of 95% on the 3K-DS dataset (3,064 images) and further improved to 98% on the larger Dataset 2 (7,023 images). These results were reinforced by exceptional ROC curve scores, reaching a perfect 1.00 for all classes in Dataset 2 and demonstrating similarly strong performance on 3K-DS, with 0.99 for class 0 and 1.00 for the other classes. Comprehensive validation using precision, recall, F1-scores, confusion matrices, and calibration curves confirmed the model's robustness and consistent performance across all evaluation metrics.
Conclusions:
Deep-EFNet achieves state-of-the-art performance in brain tumor classification, outperforming existing methods in both accuracy and reliability. Its consistent results across datasets of varying sizes highlight strong generalization capabilities, positioning it as a promising tool for clinical applications in brain tumor diagnosis.
Modeling and Analysis Methods:
Classification and Predictive Modeling 1
Methods Development 2
Other Methods
Keywords:
Experimental Design
Machine Learning
Modeling
MRI
Statistical Methods
1|2Indicates the priority used for review
·ROC curves for 3K-DS with AUC values showcasing high classification performance
·ROC curves for 7K-DS with AUC values showcasing high classification performance
Abstract Information
By submitting your proposal, you grant permission for the Organization for Human Brain Mapping (OHBM) to distribute your work in any format, including video, audio print and electronic text through OHBM OnDemand, social media channels, the OHBM website, or other electronic publications and media.
The Open Science Special Interest Group (OSSIG) is introducing a reproducibility challenge for OHBM 2025. This new initiative aims to enhance the reproducibility of scientific results and foster collaborations between labs. Teams will consist of a “source” party and a “reproducing” party, and will be evaluated on the success of their replication, the openness of the source work, and additional deliverables. Click here for more information. Propose your OHBM abstract(s) as source work for future OHBM meetings by selecting one of the following options:
Please indicate below if your study was a "resting state" or "task-activation” study.
Healthy subjects only or patients (note that patient studies may also involve healthy subjects):
Was this research conducted in the United States?
Were any human subjects research approved by the relevant Institutional Review Board or ethics panel? NOTE: Any human subjects studies without IRB approval will be automatically rejected.
Were any animal research approved by the relevant IACUC or other animal research panel? NOTE: Any animal studies without IACUC approval will be automatically rejected.
Please indicate which methods were used in your research:
For human MRI, what field strength scanner do you use?
Which processing packages did you use for your study?
Provide references using APA citation style.
Gyawali, S., Sharma, P., & Mahapatra, A. (2019). Meningioma and psychiatric symptoms: An individual patient data analysis. Asian Journal of Psychiatry, 42, 94–103.
Ostrom, Q. T., Price, M., Neff, C., Cioffi, G., Waite, K. A., Kruchko, C., & Barnholtz-Sloan, J. S. (2022). CBTRUS statistical report: Primary brain and other central nervous system tumors diagnosed in the United States in 2015–2019. Neuro-Oncology, 24, v1–v95.
Asiri, A. A., Shaf, A., Ali, T., Shakeel, U., Irfan, M., Mehdar, K. M., Halawani, H. T., Alghamdi, A. H., Alshamrani, A. F. A., & Alqhtani, S. M. (2023). Exploring the power of deep learning: Fine-tuned vision transformer for accurate and efficient brain tumor detection in MRI scans. Diagnostics, 13, 2094.
Pereira, S., Pinto, A., Alves, V., & Silva, C. A. (2016). Brain tumor segmentation using convolutional neural networks in MRI images. IEEE Transactions on Medical Imaging, 35, 1240–1251.
Cha, S. (2006). Update on brain tumor imaging: From anatomy to physiology. American Journal of Neuroradiology, 27, 475–487.
Ge, C., Gu, I. Y. H., Jakola, A. S., & Yang, J. (2020). Enlarged training dataset by pairwise GANs for molecular-based brain tumor classification. IEEE Access, 8, 22560–22570.
Somasundaram, S., & Gobinath, R. (2019). Current trends on deep learning models for brain tumor segmentation and detection–A review. In Proceedings of the 2019 International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COMITCon) (pp. 217–221).
Parsons, D. W., Jones, S., Zhang, X., Lin, J. C. H., Leary, R. J., Angenendt, P., Mankoo, P., Carter, H., Siu, I. M., Gallia, G. L., et al. (2008). An integrated genomic analysis of human glioblastoma multiforme. Science, 321, 1807–1812.
Eckel-Passow, J. E., Lachance, D. H., Molinaro, A. M., Walsh, K. M., Decker, P. A., Sicotte, H., Pekmezci, M., Rice, T., Kosel, M. L., Smirnov, I. V., et al. (2015). Glioma groups based on 1p/19q, IDH, and TERT promoter mutations in tumors. New England Journal of Medicine, 372, 2499–2508.