Article Details

Abstract

Alzheimer's disease (AD) is a neurodegenerative disease characterized by progressive cognitive dysfunction. Clinical cognitive scores (such as the Mini-Mental State Examination and the Clinical Dementia Rating) are important criteria for characterizing disease severity, determining pathological stages, and predicting disease progression. However, traditional scale-based assessment procedures are time-consuming and are easily influenced by physicians' subjective judgment and individual differences among subjects, resulting in a certain degree of subjectivity in the assessment results. To improve the objectivity and accuracy of cognitive assessment, this study proposes a hybrid deep network based on structural magnetic resonance imaging (sMRI) to achieve automatic estimation of clinical cognitive scores. This method constructs a regression model that integrates a three-dimensional convolutional neural network (3D-CNN) with a Transformer attention mechanism for the joint prediction of multiple cognitive scores. Experiments are conducted on the ADNI dataset. The results demonstrate that the proposed method can effectively capture brain structural features related to cognitive decline and achieve stable and reliable predictive performance in cognitive score estimation tasks, providing a feasible solution for the objective assessment and assisted diagnosis of AD.

Keywords

cognitive assessment; brain image; attention mechanism; neural network

References

1. [1] Jiang Jiwei, Zhao Min, Ren Qiwei, etc The correlation between caregiver characteristics and clinical manifestations of Alzheimer's disease dementia patients [J]. Chinese Journal of Health Management, 2025, 19 (2): 87-92
2. [2] Chen Yu, Chen Dacai, Chen Xinyu, etc Research on the Application of MRI in Evaluating Vascular Injury and Brain Atrophy in Patients with Alzheimer's Disease, Vascular Dementia, and Mixed Dementia [J]. Chinese Journal of CT and MRI, 2024, 22 (2): 18-21
3. [3] Li Fangjian, Chen Fei, Dong Congsong, etc The relationship between MRI findings and cognitive function in Alzheimer's disease patients [J]. Chinese Journal of CT and MRI, 2025, 23 (1): 28-29, 32
4. [4] He Jianglin, Wang Yuanjun Research progress on key methods of Alzheimer's disease radiomics [J]. Chinese Journal of Medical Imaging Technology, 2019, 35 (10): 1569-1573
5. [5] Gao Xichun, Liu Guobiao, Li Haoliang, etc Research progress on structural radiomics of Alzheimer's disease based on deep learning [J]. Advances in Clinical Medicine, 2025, 15 (10): 2317-2325
6. [6] Zhu Binbin, Zhou Yanling, Jin Lufei, etc Intelligent diagnosis of Alzheimer's disease and mild cognitive impairment based on MRI deep learning: methods and applications [J]. Chinese Journal of Neuropsychiatric Diseases, 2022, 48 (4): 251-256
7. [7] Li Meng, Cai Dijun, Shi Jiannan, etc Innovative research on intelligent diagnosis of Alzheimer's disease based on ADNI and convolutional neural network CNN deep learning [J]. Modern Medical Research, 2025 (2): 42-45
8. [8] Wu Huidong, Liu Licheng, Pan Dan Research on Alzheimer's Disease Diagnosis Combining View Aware CNN and Transformer [J]. Electronic Measurement Technology, 2025, 48 (1): 145-153
9. [9] Potter W Z，Buckholtz N S，Paul S M. The Origins of ADNI [J].Alzheimer's & Dementia，2024，20（11）：8188-8191.
10. [10] Liu M J，Tang J L，Yu W X，et al. Attention-based 3D ResNet for Detection of Alzheimer's Disease Process [C]//In International Conference on Neural Information Processing，2021：342-353.
11. [11] Gotkowski K，Gonzalez C，Bucher A，et al. M3d- CAM: A PyTorch Library to Generate 3D Attention Maps for Medical Deep Learning [C]//Bildverarbeitung für die Medizin 2021，2021：217-222.
12. [12] Wu Qi, Zhang Hongqiang, Che Kuanyu, etc Application of MRI based changes in hippocampal structure, morphology, and function in the diagnosis of Alzheimer's disease [J]. Chinese Journal of Gerontology, 2025, 45 (9): 2124-2127
13. [13] Lian C，Liu M，Wang L，et al. Multi-Task Weakly-Supervised Attention Network for Dementia Status Estimation with Structural MRI [J].IEEE Transactions on Neural Networks and Learning Systems，2021，33（8）：4056-4068.

Funding

Open Project of Fujian Medical Big Data Engineering Key Laboratory (KLKF202304)

About the authors

Huang Ji (1980-), male, Han ethnicity, from Fuzhou, Fujian, senior engineer, master's student, research interests include healthcare informatization, big data and healthcare management; Zhu Kexin (1995-), male, Han ethnicity, from Zibo, Shandong, teaching assistant, master's student, research interests include algorithms and data structures; Xu Bin (1998-), male, Han ethnicity, from Yingtan, Jiangxi, teaching assistant, research interests include information security and management.