2026 International Conference on Networks Computers and Communications (ICNCCom 2026)

A brain tumor is an abnormal growth of cells within the brain or the central spinal canal. Brain cancer is a destructive and life-threatening disease that imposes immense negative effects on patients’ lives. Therefore, the detection of brain tumors at an early stage improves the impact of treatments and increases the patients survival rates. Brain tumor segmentation is the process of precisely isolating and labeling tumor boundaries in medical images, primarily MRI scans. It is crucial for diagnosis and treatment planning. Accurate segmentation of brain tumors from multi-modal MRI scans is critical for diagnosis, treatment planning, and disease monitoring. Tumor heterogeneity and inter-image variability across MRI sequences pose challenging problems to state-of-the-art segmentation models. Brain tumor segmentation with MRI is a challenging task, traditionally relying on manual delineation of regions-of-interest across multiple imaging sequences. However, this data-intensive approach is time-consuming. In this analysis, Adaptive Marine Predators Algorithm with Efficient Net B4-Attention U-net for Improved Brain Tumor Segmentation is presented. The Adaptive Marine Predators Algorithm (AMPA) is an advanced swarm-based metaheuristic technique designed to solve complex optimization problems by mimicking ocean predator hunting behaviors. AMPA is used here for the optimization of learning rate, decoder filter configuration, dropout probability, batch size and loss function weights. This AMPA dynamically adjusts exploitation and exploration phases using fitness guided control strategy, enables better local optima avoidance and faster convergences. This system employs EfficientNet B4 as encoder and U- net based decoder for extracting multi-scale contextual features from brain MRI images. This system performance is measured in terms of DSC, IoU, sensitivity, accuracy, precision, specificity and f1-score. This system improves segmentation accuracy, generalization capability and convergence stability by integrating advanced metaheuristic optimization with EfficientNet-B4-UNet.
 

Brain tumor segmentation, MRI, EfficientNet-B4-UNet, Adaptive Marine Predators Algorithm