MRI Brain Tumor Detection Methods Using Contourlet Transform Based on Time Adaptive Self-Organizing Map

Abstract

The brain is one of the most complex organs in the body, composed of billions of cells that work together to ensure proper functioning. However, when cells divide in a disorderly manner, abnormal growths can occur, forming colonies that can disrupt the normal functioning of the brain and damage healthy cells. Brain tumors can be classified as either benign or low-grade (grade 1 and 2), or malignant or high-grade (grade 3 and 4). In this article, we propose a novel method that uses contourlet transform and time adaptive self-organizing map, optimized by the whale optimization algorithm, in order to distinguish between benign and malignant brain tumors in MRI images. Accurate classification of these images is critical for medical diagnosis and treatment. Our method is compared to other methods used in past research and shows promising results for the precise classification of MRI brain images. Through conducting experiments on different test samples, our system has successfully attained a classification accuracy exceeding 98.5%. Furthermore, it has managed to maintain a satisfactory level of efficiency in terms of run-time.

Keywords

• Brain
• classification
• contourlet transform
• detection
• neural networks
• time adaptive self-organizing map (TASOM)