Affiliation:
1. Department of Software, Sangmyung University, Cheonan 31066, Republic of Korea
Abstract
In the domain of radiological diagnostics, accurately detecting and classifying brain tumors from magnetic resonance imaging (MRI) scans presents significant challenges, primarily due to the complex and diverse manifestations of tumors in these scans. In this paper, a convolutional-block-based architecture has been proposed for the detection of multiclass brain tumors using MRI scans. Leveraging the strengths of CNNs, our proposed framework demonstrates robustness and efficiency in distinguishing between different tumor types. Extensive evaluations on three diverse datasets underscore the model’s exceptional diagnostic accuracy, with an average accuracy rate of 97.52%, precision of 97.63%, recall of 97.18%, specificity of 98.32%, and F1-score of 97.36%. These results outperform contemporary methods, including state-of-the-art (SOTA) models such as VGG16, VGG19, MobileNet, EfficientNet, ResNet50, Xception, and DenseNet121. Furthermore, its adaptability across different MRI modalities underlines its potential for broad clinical application, offering a significant advancement in the field of radiological diagnostics and brain tumor detection.
Subject
Electrical and Electronic Engineering,Computer Networks and Communications,Hardware and Architecture,Signal Processing,Control and Systems Engineering
Reference57 articles.
1. Gore, D.V., and Deshpande, V. (2020, January 5–7). Comparative study of various techniques using deep Learning for brain tumor detection. Proceedings of the 2020 International Conference for Emerging Technology (INCET), Belgaum, India.
2. (2022). Gliomas and Its Symptoms and Causes, Johns Hopkins Medicine. Available online: https://www.hopkinsmedicine.org/health/conditions-and-diseases/gliomas.
3. (2022). Pituitary Tumors—Symptoms and Causes, Mayo Clinic. Available online: https://www.hopkinsmedicine.org/health/conditions-and-diseases/pituitary-tumors.
4. (2022). Meningioma, Risk Its Symptoms, Johns Hopkins Medicine. Available online: https://www.hopkinsmedicine.org/health/conditions-and-diseases/meningioma.
5. Rasheed, Z., Ma, Y.K., Ullah, I., Ghadi, Y.Y., Khan, M.Z., Khan, M.A., Abdusalomov, A., Alqahtani, F., and Shehata, A.M. (2023). Brain tumor classification from MRI using image enhancement and convolutional neural network techniques. Brain Sci., 13.