Affiliation:
1. Skyline University College
2. Rabdan Academy
3. United Arab Emirates University
4. Zarqa University
5. Applied Science Private University
6. Weill Cornell Medicine-Qatar
Abstract
Abstract
Brain Magnetic Resonance Imaging (MRI) plays a critical role in medical research and clinical applications, ranging from quantifying tissue volume, facilitating surgical simulations, assisting in treatment planning, enabling brain mapping, aiding in disease diagnosis, and evaluating therapeutic efficacy. This study introduces a novel method for MRI brain segmentation, which harnesses the power of a hybrid approach combining Artificial Bee Colony (ABC) algorithm with Fuzzy C-Means (FCM) clustering. Our approach leverages the exploration capability of the ABC algorithm, with an improved global best guidance (IABC), to optimally initialize the cluster centroid values of the FCM, thus enhancing the segmentation outputs. Comparative evaluation of the proposed method, denoted as IABC-FCM, conducted on a diverse set of MRI brain images, reveals its superior performance. The results indicate the potential of this hybrid approach as a robust tool for improved MRI brain segmentation tasks.
Publisher
Research Square Platform LLC
Reference41 articles.
1. A hybrid harmony search algorithm for MRI brain segmentation;Alia O;Evolutionary Intelligence,2011
2. MRI brain segmentation via hybrid firefly search algorithm;Alomoush W;Journal of Theoretical & Applied Information Technology,2014
3. A hybrid biogeography-based optimization and fuzzy C-means algorithm for image segmentation;Zhang M;Soft computing,2019
4. A scalable framework for segmenting magnetic resonance images;Hore P;Journal of signal processing systems,2009
5. Fuzzy C-mean based brain MRI segmentation algorithms;Balafar M;Artificial Intelligence Review,2014