- Research Article
2
- 10.63682/jns.v14i7.5625
Optimised Brain Tumor Detection Using texture-based features and deep learning Algorithm
- May 12, 2025
- Journal of Neonatal Surgery
- Deepa R Bhangi + 1 more +1
Brain Tumor Detection (BTD) using Artificial Intelligence (AI) has gained major attention in the field of medical imaging and diagnostics. AI-based systems, particularly Machine Learning (ML) and Deep Learning (DL) algorithms, offer an advanced and efficient approach to identifying Brain Tumors (BTs) in medical images such as Magnetic Resonance Imaging (MRI) scans. These systems can automatically process and analyze large volumes of imaging data, detecting abnormalities with high accuracy and speed. In this study, the authors proposed 4 ML models (SVM, RF, MLP, and XG-Boost) and 4 DL (Bi-LSTM, Res-Net50, VGG-16, and Inception V3) models. This proposed approach involves data preprocessing step, feature selection, model optimization in a timely manner to improve and maximize prediction of BT. By training AI models on vast datasets, these technologies learn to recognize patterns associated with different types of BTs, including gliomas, meningiomas, and pituitary tumors. By leveraging these algorithms, the research evaluates their performance in terms of accuracy ( ), precision ( ), recall ( ), Specificity ( ) and F1-score ( ). After comparison between the ML and DL model, the proposed DL methods, including Inception V3 achieved highest accuracy (99.04%), precision (98.23%), recall (98.53), (96.73%), and F1-score (97.95%) than the suggested ML models.
Read more