Answers are grounded in this paper and cite their sources.
Background/Objectives: Multiple Sclerosis (MS) is a chronic neurodegenerative disease affecting the central nervous system and significantly reducing the quality of life. Early detection of the disease is critical for slowing its progression and developing appropriate treatment plans. In recent years, artificial intelligence and deep learning methods have begun to play a significant role in clinical decision support systems, particularly due to their high accuracy rates in the analysis of Magnetic Resonance (MR) images. Methods: In this study, a hybrid model was developed for the automatic classification of MS. Two different architectures were used for feature extraction in the developed model. These architectures were selected from among the most successful architectures out of 10 different Convolutional Neural Network (CNN) and Vision Transformer (ViT) architectures. Six different classifiers were used to classify the feature maps obtained in the proposed model and pre-trained models. The application of the VOTE operation in the final stage of the proposed model improved its performance. Results: The proposed model yielded competitive results compared to similar studies in the literature and the CNN and ViT architectures used in this study. The accuracy rate achieved with the proposed hybrid model was 97.28%. Conclusions: These results indicate that the proposed model has the potential to support computer-aided MS detection and may provide a useful framework for clinical decision support systems.
No takes yet. Share an insight, caveat, or question.
ÇIPLAK et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: