Abstract
A Brain Tumor (BT), further known as an intracranial tumor, is a mass of abnormal tissue whose cells multiply and procreate uncontrolled and appear unaffected by those mechanisms that control normal cells, and it causes many people's deaths each year. BT is frequently detected using Magnetic Resonance Imaging (MRI) procedures. One of the greatest common techniques for segmenting medical images is Multilevel Thresholding (MT). MT received the researchers ' attention because of its simplicity, ease of use, and accuracy. Consequently, this paper uses the most recent Zebra Optimization Algorithm (ZOA) to deal with the MT problems of MRI images. The ZOA's performance has been evaluated on 10 MRI images with threshold levels up to 10 and evaluated against five different algorithms: Sine Cosine Algorithm (SCA), Arithmetic Optimization Algorithm (AOA), Flower Pollination Algorithm (FPA), Reptile Search Algorithm (RSA), and Marine Predators Algorithm (MPA). The experimental results, which included numerous performance metrics such as Mean Square Error (MSE), Peak Signal-To-Noise Ratio (PSNR), Feature Similarity Index Metric (FSIM), Normalized Correlation Coefficient (NCC), and fitness values, totally show that the ZOA outperforms all other algorithms based on Kapur's entropy for all the applied measures.