Hybrid 3D CNN and ResNet Deep Transfer Learning for High-Resolution Hippocampal Atrophy Mapping and Automated Alzheimer’s MRI Diagnosis
Deep Hybrid 3D CNN and ResNet Transfer Learning for High-Resolution Hippocampal Atrophy Mapping and Automated Alzheimer’s MRI Diagnosis
Received: 8 April 2025 | Revised: 17 May 2025 | Accepted: 24 May 2025 | Online: 2 August 2025
Corresponding author: Garima Shukla
Abstract
Early and accurate detection of Alzheimer's disease (AD) is crucial for a timely clinical intervention. Atrophy of the hippocampus has been established as a key neurodegenerative biomarker. This study presents a Hybrid 3D CNN–ResNet model for automated hippocampal segmentation and dementia classification using high-resolution MRI scans. The proposed framework integrates 3D U-Net-based hippocampal segmentation with multi-scale feature extraction and deep residual learning, enabling a precise atrophy quantification and robust classification across the AD stages. A standardized preprocessing pipeline, incorporating NIfTI conversion, spatial normalization, denoising, and contrast enhancement, ensures consistency across multi-site datasets. The model was optimized using AdamW, Cyclical Learning Rate (CLR), and early stopping, achieving 97.31% classification accuracy and a 92.84% Dice Similarity Coefficient (DSC) for hippocampal segmentation. Grad-CAM and SHAP-based interpretability confirm the biologically meaningful feature representations, aligning with established hippocampal atrophy patterns in AD progression. The external validation on the OASIS dataset demonstrated strong generalization, with only a 2.3% accuracy reduction, underscoring the model’s robustness and clinical applicability. These findings establish the proposed approach as an effective and interpretable deep learning framework for early AD diagnosis and longitudinal disease monitoring.
Keywords:
Alzheimer’s disease, hippocampal atrophy, hybrid 3D CNN–ResNet, deep learning, MRI segmentation, multi-scale feature extraction, dementia classificationDownloads
References
H. Wang, C. Lei, D. Zhao, L. Gao, and J. Gao, "DeepHipp: accurate segmentation of hippocampus using 3D dense-block based on attention mechanism," BMC Medical Imaging, vol. 23, no. 1, Oct. 2023, Art.no. 158, https://doi.org/10.1186/s12880-023-01103-5 DOI: https://doi.org/10.1186/s12880-023-01103-5
W. Won and C. Hahn, "P2–192: Hippocampal subfields segmentation using automated method in people with Alzheimer’s disease," Alzheimer’s & Dementia, vol. 9, no. 4S_Part_10, pp. P424–P424, 2013, https://doi.org/10.1016/j.jalz.2013.05.837. DOI: https://doi.org/10.1016/j.jalz.2013.05.837
M. Chupin et al., "Fully automatic hippocampus segmentation and classification in Alzheimer’s disease and mild cognitive impairment applied on data from ADNI," Hippocampus, vol. 19, no. 6, pp. 579–587, Jun. 2009, https://doi.org/10.1002/hipo.20626. DOI: https://doi.org/10.1002/hipo.20626
Y. Shi, K. Cheng, and Z. Liu, "Hippocampal subfields segmentation in brain MR images using generative adversarial networks," BioMedical Engineering OnLine, vol. 18, no. 1, Jan. 2019, Art.no. 5, https://doi.org/10.1186/s12938-019-0623-8. DOI: https://doi.org/10.1186/s12938-019-0623-8
J. E. Iglesias et al., "A computational atlas of the hippocampal formation using ex vivo, ultra-high resolution MRI: Application to adaptive segmentation of in vivo MRI," NeuroImage, vol. 115, pp. 117–137, Jul. 2015, https://doi.org/10.1016/j.neuroimage.2015.04.042. DOI: https://doi.org/10.1016/j.neuroimage.2015.04.042
M. Schell, M. Foltyn-Dumitru, M. Bendszus, and P. Vollmuth, "Automated hippocampal segmentation algorithms evaluated in stroke patients," Scientific Reports, vol. 13, no. 1, Jul. 2023, Art.no. 11712, https://doi.org/10.1038/s41598-023-38833-z. DOI: https://doi.org/10.1038/s41598-023-38833-z
I. Sarasua, S. Pölsterl, and C. Wachinger, "Hippocampal representations for deep learning on Alzheimer’s disease," Scientific Reports, vol. 12, no. 1, May 2022, Art.no. 8619, https://doi.org/10.1038/s41598-022-12533-6. DOI: https://doi.org/10.1038/s41598-022-12533-6
D. Chen, W. Liu, Y. Huang, T. Tong, and Y. Yu, "Enhancement Mask for Hippocampus Detection and Segmentation." arXiv, Feb. 12, 2019, https://doi.org/10.48550/arXiv.1902.04244.
R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, "Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization," International Journal of Computer Vision, vol. 128, no. 2, pp. 336–359, Feb. 2020, https://doi.org/10.1007/s11263-019-01228-7. DOI: https://doi.org/10.1007/s11263-019-01228-7
M. Adachi et al., "Morphology of the Inner Structure of the Hippocampal Formation in Alzheimer Disease," American Journal of Neuroradiology, vol. 24, no. 8, pp. 1575–1581, Sep. 2003.
S. G. Mueller, N. Schuff, K. Yaffe, C. Madison, B. Miller, and M. W. Weiner, “Hippocampal atrophy patterns in mild cognitive impairment and Alzheimer’s disease,” Human Brain Mapping, vol. 31, no. 9, pp. 1339–1347, Sep. 2010, https://doi.org/10.1002/hbm.20934. DOI: https://doi.org/10.1002/hbm.20934
B. K. Raghupathy, M. R. Reddy, P. Theeda, E. Balasubramanian, R. K. Namachivayam, and M. Ganesan, "Harnessing Explainable Artificial Intelligence (XAI) based SHAPLEY Values and Ensemble Techniques for Accurate Alzheimer’s Disease Diagnosis," Engineering, Technology & Applied Science Research, vol. 15, no. 2, pp. 20743–20747, Apr. 2025, https://doi.org/10.48084/etasr.9619. DOI: https://doi.org/10.48084/etasr.9619
J. G. Csernansky et al., "Preclinical detection of Alzheimer’s disease: hippocampal shape and volume predict dementia onset in the elderly," NeuroImage, vol. 25, no. 3, pp. 783–792, Apr. 2005, https://doi.org/10.1016/j.neuroimage.2004.12.036. DOI: https://doi.org/10.1016/j.neuroimage.2004.12.036
N. Schuff et al., "MRI of hippocampal volume loss in early Alzheimer’s disease in relation to ApoE genotype and biomarkers," Brain, vol. 132, no. 4, pp. 1067–1077, Apr. 2009, https://doi.org/10.1093/brain/awp007. DOI: https://doi.org/10.1093/brain/awp007
M. Punzi et al., “Atrophy of hippocampal subfields and amygdala nuclei in subjects with mild cognitive impairment progressing to Alzheimer’s disease,” Heliyon, vol. 10, no. 6, Mar. 2024, Art.no. e27429, https://doi.org/10.1016/j.heliyon.2024.e27429. DOI: https://doi.org/10.1016/j.heliyon.2024.e27429
"Alzheimer’s Disease Neuroimaging Initiative," ADNI. https://adni-lde.loni.usc.edu/.
Downloads
How to Cite
License
Copyright (c) 2025 Garima Shukla, Vanshaj Awasthi, Dipti Theng, Rolly Gupta, Sakshi Nipane, Sofia Singh
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
