• Gopika Sreekumar
• Vyshnav K

Brain age estimation from magnetic resonance imaging (MRI) is a valuable tool in understanding brain development, aging, and age-related neurological disorders. This study explores the application of Capsule Networks, a type of deep learning architecture, for accurate brain age estimation using T1 weighted MRI images from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. The data preprocessing involved data normalization to ensure optimal model performance. The Mean Squared Error (MSE) loss function was employed during training to minimize the discrepancy between predicted brain ages and ground truth labels. The model's performance was evaluated using Mean Absolute Error (MAE). The obtained MAE value of about 0.808 demonstrates the model's ability to accurately predict brain age. The results highlight the potential of Capsule Networks in capturing complex spatial patterns and relationships within brain structures. Accurate brain age estimation has significant implications for neuroscience, aging-related research, and early detection of neurodegenerative disorders. The integration of deep learning techniques in brain age estimation holds promise for advancing our understanding of brain development, aging, and neurological conditions. Further investigations and refinements of the model could contribute to even more precise brain age predictions in the future.

Brain Age, Brain Age Estimation, Magnetic Resonance Image (MRI), Capsule Network, Deep Learning, Medical Imaging, Aging Biomarkers, Medical Research.

"UNRAVELING BRAIN AGE : LEVERAGING CAPSULE NETWORKS FOR ACCURATE BRAIN AGE ESTIMATION FROM MRI", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 8, page no.a318-a327, August-2023, Available :http://www.jetir.org/papers/JETIR2308041.pdf

"UNRAVELING BRAIN AGE : LEVERAGING CAPSULE NETWORKS FOR ACCURATE BRAIN AGE ESTIMATION FROM MRI", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 8, page no. ppa318-a327, August-2023, Available at : http://www.jetir.org/papers/JETIR2308041.pdf