Artificial Intelligence Method for Detecting Brain Cancer using Advanced Intelligent Algorithms

Because of the gravity of this condition, the development of trustworthy detection tools for brain cancer is an absolute need. The K-Nearest Neighbors (KNN) algorithm and the genetic algorithm are only two examples of the machine learning algorithms that have been deployed in recent years to identify brain cancer in scans. Other examples include the neural network algorithm and the ensemble learning algorithm. This study proposes a combination of KNN algorithm with the genetic algorithm in order to identify cases of brain cancer based only on MRI scans. In order to preprocess the MRI images, the median filter is used, and after that, the genetic algorithm is utilized for the purposes of feature extraction as well as feature selection. The KNN algorithm is then used to determine whether or not the photos of the brain indicate cancerous or normal tissue. The photographs of the brain are then classed accordingly. This, in turn, is beneficial to the feature extraction and feature selection phases. These repercussions may be positive or negative. This strategy provides a solid groundwork for the development of efficient diagnostic tools, and it is also applicable to a variety of other medical imaging applications.