MindSight: Revolutionizing Brain Tumor Diagnosis with Deep Learning

• Main Authors: Gandham, Rushita, Manambakam, Keerthi Reddy, Nannapaneni, Navyasri, Enduri, Murali Krishna, Hajarathaiah, Koduru, Anamalamudi, Satish
• Format: Conference Proceeding
• Language: English
• Subjects: Brain modeling; Brain Tumor Detection; Computational Efficiency; Computational modeling; Deep learning; EfficientNetB3; Magnetic resonance imaging; Measurement; MobileNetV3; ResNet50; Training; Transfer learning; VGG16
• ISSN: 2473-5655
• DOI: 10.1109/CSNT60213.2024.10545790

Brain tumors, characterized by abnormal cell growth, pose a substantial health challenge with non-cancerous (benign) and cancerous (malignant) categories. India witnesses the diagnosis of approximately 40,000 fresh instances of brain tumors annually. The rarity and diversity of tumor types make predicting survival rates challenging. Efficient identification of cerebral abnormalities is essential for the timely and effective management of neurological conditions. Exploring the application of deep learning, this study investigates brain tumor detection using a curated dataset of Magnetic Resonance Images (MRI). Utilizing this dataset, brain tumor detection is advanced through the application of diverse models, including EfficientNetB3, ResNet50, MobileNetV3, and VGG16. The study prioritizes dataset preprocessing, emphasizing data augmentation. Diverse brain tumor images contribute to model training, incorporating transfer learning from pre-trained models on extensive datasets for discerning intricate patterns in medical images. Efficiency evaluation considers computational resources, training time, and complexity. Quantitative metrics F1 score, accuracy, recall, and precision are employed to gauge model performance in classifying the tumor and non-tumor regions. In the conducted study, VGG16 demonstrated the best performance compared to all other models.