• Varun Bharadwaj B.N
• Katta Chandramouli
• Veneel Kumar A
• Shilpa Sannamani

Alzheimer’s Disease (AD) is a progressive neurodegenerative disorder that significantly impacts cognitive function and quality of life. Early and accurate diagnosis is critical for managing the disease, yet traditional clinical methods often fall short due to their subjectivity and limited sensitivity. This paper presents a comprehensive analysis of deep learning methodologies applied to MRI-based neuroimaging data for automated AD classification. Publicly available datasets such as ADNI, OASIS, and Kaggle MRI repositories were utilized, incorporating both 2D and 3D MRI scans. The proposed approach combines preprocessing techniques—such as skull stripping, intensity normalization, and image registration—with advanced model architectures including 3D CNNs, segmentation-assisted models, and transfer learning pipelines. Evaluation metrics like accuracy, precision, recall, F1-score, and Dice coefficient were employed to benchmark model performance. The results demonstrate that 3D CNNs with region-specific segmentation significantly improve diagnostic accuracy, achieving performance levels exceeding 90% in some cases. Multimodal fusion strategies, leveraging MRI with PET and clinical scores, further enhance robustness. This study underscores the potential of deep learning in revolutionizing AD diagnosis and provides insights for future work in model generalization, explainability, and clinical applicability.

Alzheimer’s Disease, Deep Learning, MRI, 3D CNN, Segmentation, Multimodal Fusion.

"Comparative Analysis of Deep Learning Models for Alzheimer's Diagnosis using MRI and Brain Segmentation Techniques", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 5, page no.c406-c411, May-2025, Available :http://www.jetir.org/papers/JETIR2505249.pdf

"Comparative Analysis of Deep Learning Models for Alzheimer's Diagnosis using MRI and Brain Segmentation Techniques", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 5, page no. ppc406-c411, May-2025, Available at : http://www.jetir.org/papers/JETIR2505249.pdf