A Novel Method for Categorizing Brain Tumors using the Hybrid ALO-ELM Model

Abstract

Brain tumors, like many other disorders, can cause brain injury through the formation of clots. The MRI picture clearly shows the brain tumor. Healthy brain tissue and brain tumor tissue seem quite similar under the microscope, making it easy to confuse the two. The brain tumor must be properly diagnosed. When assessing brain tumors, segmentation is the gold standard. Brain tumor segmentation is conducted to get around this difficulty by isolating tumor tissue from normal brain tissue, edematous brain tissue, and cerebrospinal fluid. However, this cannot be accomplished until the MRI picture has been median filtered to preserve its edges. An iterative thresholding approach is required to extract the greatest area from the tumor segmentation. After using the watershed method to separate the brain from the rest of the head, the cropping procedure is used to remove any remaining skull tissue. After ALO has improved the settings of ELM, a brain tumor detection system based on the ALO-ELM combination will have been created by identifying the input nodes, hidden layer nodes, and output nodes. The technique outperforms both the ALO and ELM models, with an accuracy of around 98.8%.