QUANTUM BASED BINARY BAT DEEP LEARNING METHOD FOR BRAIN TUMOR CLASSIFICATION IN MRI IMAGES

Abstract

In order to accurately diagnose, treat, and manage a variety of diseases, it is essential to have
medical images that are stored, analyzed, and transmitted in a manner that is both efficient and
dependable. Numerous studies in this sector have concentrated on the utilization of quantum
and quantum-inspired algorithms to boost the performance of traditional medical image
processing procedures. The model that has been proposed is an mix of quantum-based
algorithms and algorithms inspired by nature, and it incorporates the more hopeful aspects of
both types of algorithms. By utilizing the quantum-based binary bat algorithm, also known as q-
BBA, the proposed model has been successful in reducing dimensionality, which refers to
aspects that are not necessary. QBBA achieved superior results than its conventional algorithms.
This was discovered after comparing the performance of QBBA with that of its conventional
methods. The QBBA algorithm emerges as a notable algorithm due to its enhanced noise
immunity. The proposed Quantum-based Binary Bat method has the potential to be applied in
the detection of brain tumors.