Manuscript received September 5, 2024; revised October 11, 2024; accepted November 19, 2024; published February 27, 2025.

Abstract—Brain tumors pose significant diagnostic and therapeutic challenges and are associated with high rates of illness and death. Magnetic Resonance Imaging provides detailed images of the brain’s structure, making it an essential tool for identifying abnormalities, including tumors. However, accurately categorizing different types of tumors still poses a considerable difficulty. Recent advancements in deep learning, particularly Convolutional Neural Networks (CNNs), have shown promising results in the precise classification of brain tumors via MRI data processing. Nevertheless, the effectiveness of CNNs might be constrained by the magnitude and intricacy of the dataset. This study illustrates the application of Hybrid Quantum- Classical Convolutional Neural Network (HQC-CNN) and DenseNet121 model on the brain tumor classes namely meningioma glioma, and pituitary tumors. The experimental results indicate that the models attained accuracies of 88% and 94% in categorizing brain tumor images, respectively, with the HQC-CNN model and DenseNet121.

Keywords—quantum convolutional neural networks, classical convolutional neural networks, quantum hybridclassical, densenet121, quantum computing, brain tumor, Magnetic Resonance Imaging (MRI)

Cite: Anandhavalli Muniasamy, Salma A. S. Alquhtani, Afnan H. Alshehri, Arshiya Begum, and Asfia Sabahath, "Investigating Hybrid Quantum-Assisted Classical and Deep Learning Model for MRI Brain Tumor Classification," Journal of Image and Graphics, Vol. 13, No. 1, pp. 123-129, 2025.

Copyright © 2025 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC-BY-4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.