Brain cyst detection using deep learning models

Abstract

Cysts are common in healthcare and can be associated with various diseases. They can develop in different body parts and contain fluid, semi-solid, or air. Brain cysts are masses that form in the brain, and surgical methods may be used to treat them. The importance of deep learning in medical imaging is steadily growing. This study attempted to detect brain cysts using various architectures, including Random Forest, Unet, AlexNet, and LeNet. The Random Forest algorithm was found to be more successful than the other algorithms. This algorithm is crucial for classification and regression problems as it trains a series of decision trees and consolidates their predictions to create a robust and powerful model. Magnetic resonance imaging was used to detect cysts. The accuracy rates for cyst detection were 79.52%, 89.99%, 90.41%, and 97.26%, respectively. Several models were employed for this purpose, including LeNet, AlexNet, Unet, and the Random Forest algorithm. The accuracy rates for cyst detection were 79.52%, 89.99%, 90.41%, and 97.26%, respectively.