A hybrid approach for Alzheimer’s disease diagnosis: image segmentation and deep learning classification

• Published in: Neural computing & applications Vol. 37; no. 19; pp. 13881 - 13899
• Main Author: Bhimavarapu, Usharani
• Format: Journal Article
• Language: English
• Published: London Springer London 01.07.2025; Springer Nature B.V
• Subjects: Accuracy; Algorithms; Alzheimer's disease; Artificial Intelligence; Brain research; Classification; Clustering; Cognitive ability; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Data Mining and Knowledge Discovery; Deep learning; Diagnosis; Disease; Image classification; Image Processing and Computer Vision; Image segmentation; Machine learning; Medical diagnosis; Medical imaging; Memory; Neuroimaging; Original Article; Probability and Statistics in Computer Science; Deep learning; Alzheimer’s disease; Fuzzy C-means; Brain tumors
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-025-11249-8

Alzheimer’s disease is a severe neurodegenerative disease that leads to cognitive decline and memory loss, and hence, the early diagnosis is essential for proper management and care. This study investigates the usage of the improved fuzzy C-means (FCM) algorithm for segmentation of MRI scan and five deep learning models, namely Densenet121, Inception-v3, VGG-19, Xception, and Resnet-50, for image classification. Enhanced fuzzy C-means algorithm helps segment MRI data, while the selected deep learning architectures classify these images for accurate classification. Rigorous processes, including five-fold cross-validation, early stopping, and optimization techniques, were employed to ensure model performance. The results indicated that combining the enhanced fuzzy C-means algorithm with deep learning architectures significantly improved MRI classification accuracy, where Densenet121 and Resnet-50 exhibited the best results. This approach holds promise for enhancing the diagnosis and treatment of Alzheimer’s disease because it increases detection accuracy and reliability, allowing for better patient care.