Automated brain tumor recognition using equilibrium optimizer with deep learning approach on MRI images

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Deep Learning

Background:

• Brain tumors (BT) pose significant health risks due to their location.
• Artificial intelligence (AI), including deep learning (DL) and machine learning (ML), offers advanced tools for disease diagnosis and treatment.
• AI analyzes brain Magnetic Resonance Imaging (MRI) to identify and categorize tumors, aiding medical professionals in diagnosis and treatment planning.

Purpose of the Study:

• To develop and validate a novel AI technique for accurate brain tumor recognition in MRI images.
• To enhance the early detection and classification of brain tumors using deep learning and optimization algorithms.

Main Methods:

• The Brain Tumor Recognition using an Equilibrium Optimizer with a Deep Learning Approach (BTR-EODLA) technique was employed.
• Median filtering (MF) was used for noise reduction in MRI images.
• Squeeze-excitation ResNet (SE-ResNet50) extracted features, optimized by the Equilibrium Optimizer (EO), and a stacked autoencoder (SAE) performed tumor detection.

Main Results:

• The BTR-EODLA technique demonstrated high performance in brain tumor recognition.
• Experimental validation showed a superior accuracy of 98.78% compared to existing models.
• The method effectively identifies the presence of brain tumors in MRI scans.

Conclusions:

• The BTR-EODLA technique offers a highly accurate and effective solution for brain tumor detection using AI and deep learning on MRI data.
• This AI-driven approach has the potential to significantly improve diagnostic accuracy and patient management in neuro-oncology.