Abstract

This study proposes a structured, multi-phase framework to enhance medical image classification accuracy through early detection and precise classification of Azheimer’s disease using MRI scans. Initially, image preprocessing using gaussian filtering and normalization is applied to suppress noise and standardize intensity levels. The proposed Deep Intuitionistic Fuzzy Clustering (DIFC) method effectively models uncertainty and vagueness inherent in medical imaging by incorporating membership, non-membership, and hesitation degrees, thereby achieving superior segmentation performance compared to traditional fuzzy clustering approaches. The Sea Lion Optimization Algorithm (SLOA) is employed to fine-tune clustering parameters, ensuring faster convergence and improved segmentation stability. Subsequently, textual, convolutional, and statistical features extracted from the segmented regions are optimized by Deep Maxout Network (DMN) using SLOA for multi-stage AD classification. Experimental results demonstrate that the proposed DIFC-SLOA-DMN framework achieves high accuracy, sensitivity, and specificity, validating its effectiveness as a robust and reliable computer-aided diagnostic system for early Alzheimer’s disease detection and progression analysis.

References

• Alzheimer’s Disease 5-Class Dataset (ADNI), available at: https://www.kaggle.com/madhucharan/alzheimersdisease 5classdatasetadni, accessed July 2021.
• S. Afzal, M. Maqsood, F. Nazir, U. Khan, F. Aadil, K. M. Awan, I. Mehmood, and O. Y. Song, “A data augmentationbased framework to handle class imbalance problem for Alzheimer’s stage detection,” IEEE Access, vol. 7, pp. 115528–115539, 2019.
• J. B. Bae et al., “Identification of Alzheimer’s disease using a convolutional neural network model based on T1-weighted magnetic resonance imaging,” Scientific Reports, vol. 10, no. 1, p. 22252, 2020.
• J. Ramya, B. U. Maheswari, M. P. Rajakumar, and R. Sonia, “Alzheimer’s disease segmentation and classification on MRI brain images using enhanced expectation maximization adaptive histogram (EEM-AH) and machine learning,” Information Technology and Control, vol. 51, no. 4, pp. 786–800, 2022.
• K. De Silva and H. Kunz, “Prediction of Alzheimer’s disease from magnetic resonance imaging using a convolutional neural network,” Intelligence-Based Medicine, vol. 7, p. 100091, 2023.
• C. Feng et al., “Deep learning framework for AD diagnosis via 3D-CNN and FSBi-LSTM,” IEEE Access, vol. 7, pp. 63605–63618, 2019.
• P. Forouzannezhad et al., “A deep neural network approach for early diagnosis of mild cognitive impairment using multiple features,” in Proc. IEEE ICMLA, 2018, pp. 1341–1346.
• S. Ribariˇc, “Detecting early cognitive decline in Alzheimer’s disease with brain synaptic structural and functional evaluation,” Biomedicines, vol. 11, no. 2, p. 355, 2023.
• H. Huang et al., “Voxel-based morphometry and a deep learning model for the diagnosis of early Alzheimer’s disease based on cerebral gray matter changes,” Cerebral Cortex, vol. 33, no. 3, pp. 754–763, 2023.
• M. Xu et al., “Preliminary study on early diagnosis of Alzheimer’s disease in APP/PS1 transgenic mice using multimodal magnetic resonance imaging,” Frontiers in Aging Neuroscience, vol. 16, p. 1326394, 2024.
• S. Aghajanian et al., “Longitudinal structural MRI-based deep learning and radiomics features for predicting Alzheimer’s disease progression,” Alzheimer’s Research & Therapy, vol. 17, no. 1, pp. 1–13, 2025.
• D. Mungra et al., “PRATIT: A CNN-based emotion recognition system using histogram equalization and data augmentation,” Multimedia Tools and Applications, vol. 79, no. 3, pp. 2285–2307, 2020.
• B. M. Nguyen et al., “An improved sea lion optimization for workload elasticity prediction with neural networks,” International Journal of Computational Intelligence Systems, vol. 15, no. 1, p. 90, 2022.
• R. Liu et al., “Large margin and local structure preservation sparse representation classifier for Alzheimer’s MRI classification,” Frontiers in Aging Neuroscience, vol. 14, p. 916020, 2022.
• V. Adarsh et al., “Multimodal classification of Alzheimer’s disease and mild cognitive impairment using custom MKSCDDL kernel over CNN with transparent decisionmaking,” Scientific Reports, vol. 14, no. 1, p. 1774, 2024.
• F. Segovia et al., “Multivariate analysis of dual-point amyloid PET intended to assist the diagnosis of Alzheimer’s disease,” Neurocomputing, vol. 417, pp. 1–9, 2020.
• K. Shankar et al., “Alzheimer detection using Group Grey Wolf Optimization based features with convolutional classifier,” Computers & Electrical Engineering, vol. 77, pp. 230– 243, 2019.
• S. Sudha et al., “Segmentation of RoI in medical images using CNN: A comparative study,” in Proc. IEEE TENCON, 2019, pp. 767–771.
• T. S. Sindhu, N. Kumaratharan, and P. Anandan, “Hybrid optimized deep fuzzy clustering-based segmentation and Deep Maxout Network for Alzheimer’s disease classification,” Biomedical Signal Processing and Control, vol. 93, p. 106118, 2024.
• K. Tadokoro et al., “Early detection of cognitive decline in mild cognitive impairment and Alzheimer’s disease with a novel eye tracking test,” Journal of the Neurological Sciences, vol. 427, p. 117529, 2021.
• T. Zhu, C. Cao, Z. Wang, G. Xu, and J. Qiao, “Anatomical landmarks and DAG network learning for Alzheimer’s disease diagnosis,” IEEE Access, vol. 8, pp. 206063–206073, 2020.
• Y. Zhang et al., “Alzheimer’s disease multiclass diagnosis via multimodal neuroimaging embedding feature selection and fusion,” Information Fusion, vol. 66, pp. 170–183, 2021.
• T. Zhang et al., “Predicting MCI to AD conversion using integrated sMRI and rs-fMRI: A machine learning and graph theory approach,” Frontiers in Aging Neuroscience, vol. 13, p. 688926, 2021.
• Y. Wang et al., “Transition of mild cognitive impairment to Alzheimer’s disease: Medications as modifiable risk factors,” PLOS ONE, vol. 19, no. 8, p. e0306270, 2024.
• J. Zhang et al., “Recent advances in Alzheimer’s disease: Mechanisms, clinical trials and new drug development strategies,” Signal Transduction and Targeted Therapy, vol. 9, no. 1, p. 211, 2024.
• M. Sandhya and P. Dhanalakshmi, “Segmentation and classification of Alzheimer’s disease using deep fuzzy clustering and deep learning techniques with sea lion optimization algorithm,” Indian Journal of Natural Sciences, pp. 86187–86195, 2024.