Abstract
Brain tumors present a significant challenge in medical diagnostics due to their complexity and variability. This research investigates the application of deep learning to classify different types of brain tumors, aiming to enhance diagnostic accuracy and efficiency. The proposed ensemble method leverages a hybrid model that combines fine-tuned pre-trained DenseNet121 and EfficientNet-B0 models, omitting their respective top layers. By integrating the strengths of both networks through additional fully connected layers, classification performance is significantly improved. The proposed ensemble method achieves an accuracy of 99.67% on the Figshare Dataset-I and 99.39% on the Kaggle Dataset-II.
| Original language | English |
|---|---|
| Pages (from-to) | 95-100 |
| Number of pages | 6 |
| Journal | Proceedings of the IEEE Conference on Systems, Process and Control, ICSPC |
| Issue number | 2024 |
| DOIs | |
| Publication status | Published - 2024 |
| Event | 12th IEEE Conference on Systems, Process and Control, ICSPC 2024 - Malacca, Malaysia Duration: 7 Dec 2024 → … |
Keywords
- Brain Tumor
- Deep Learning
- Ensemble Learning
- Pre-Trained Model
- Transfer Learning
ASJC Scopus subject areas
- Artificial Intelligence
- Computer Science Applications
- Information Systems
- Information Systems and Management
- Safety, Risk, Reliability and Quality
- Control and Optimization
- Modelling and Simulation
- Education