Parkinson’s Disease Classification Using Gray Matter MRI and Deep Learning: A Comparative Framework
Source abstract
Abstract
In this study, we propose multiple deep learning models for classifying gray matter MRI images of healthy individuals, prodromal Parkinson’s disease (PD) subjects, and diagnosed PD patients. The two proposed models extend conventional deep learning architectures—MedicalNet3D and 3D ResNet18—by performing feature extraction separately for each class and inputting these features into distinct multilayer perceptron (MLP) classifiers constructed via fine-tuning. To mitigate overfitting problem and improve generalizability, we introduce a training method based on group-wise feature fusion, in which subject IDs are separated to avoid data leakage during training. Through comparative experiments using the PPMI database, the effectiveness of the proposed approach was validated.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Parkinson's Disease Mechanisms and Treatments · Voice and Speech Disorders · Neurological disorders and treatments
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Graduate School of Engineering, Nippon Institute of Technology, 4-1 Gakuendai, Miyashiro-machi, Saitama 345-8501, Japan
Graduate School of Health Data Science, Juntendo University, 2-1-1 Hongo, Bunkyo-ku, Tokyo 113-8421, Japan
Department of Rehabilitation, Nihon Institute of Medical Science, 1276 Shimogawara, Moroyama-machi, Iruma-gun, Saitama 350-0435, Japan
Department of Information Technology and Media Design, Nippon Institute of Technology, 4-1 Gakuendai, Miyashiro-machi, Saitama 345-8501, Japan
Funding
Japan Society for the Promotion of Science
References (34)
Show source-provided references
1. Welton, T., Hartono, S., Lee, W., Teh, P.Y., Hou, W., Chen, R.C., Chen, C., Lim, E.W., Prakash, K.M., and Tan, L.C.S. (2024). Classification of Parkinson’s Disease by Deep Learning on Midbrain MRI. Front. Aging Neurosci., 16.10.3389/fnagi.2024.1425095 ↗
2. Dentamaro, V., Impedovo, D., Musti, L., Pirlo, G., and Taurisano, P. (2024). Enhancing early Parkinson’s disease detection through multimodal deep learning and explainable AI: Insights from the PPMI database. Sci. Rep., 14.10.1038/s41598-024-70165-4 ↗
3. Makarious, M.B., Leonard, H.L., Vitale, D., Iwaki, H., Sargent, L., Dadu, A., Violich, I., Hutchins, E., Saffo, D., and Bandres-Ciga, S. (2022). Multi-modality machine learning predicting Parkinson’s disease. npj Park. Dis., 8.10.1038/s41531-022-00288-w ↗
4. Li, S., Lei, H., Zhou, F., Gardezi, J., and Lei, B. (2019, January 8–11). Longitudinal and Multi-modal Data Learning for Parkinson’s Disease Diagnosis via Stacked Sparse Auto-encoder. Proceedings of the 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), Venice, Italy.10.1109/ISBI.2019.8759385 ↗
5. Pahuja, G., and Prasad, B. (2022). Deep learning architectures for Parkinson’s disease detection by using multi-modal features. Comput. Biol. Med., 146.10.1016/j.compbiomed.2022.105610 ↗
6. Makarious, M.B., Leonard, H.L., Vitale, D., Iwaki, H., Sargent, L., Dadu, A., Violich, I., Hutchins, E., Saffo, D., and Bandres-Ciga, S. (2021). Multimodal phenotypic axes of Parkinson’s disease. npj Park. Dis., 7.
7. Huang, Z., Lei, H., Zhao, Y., Zhou, F., Yan, J., Elazab, A., and Lei, B. (2018, January 4–7). Longitudinal and multi-modal data learning for Parkinson’s disease diagnosis. Proceedings of the 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), Washington, DC, USA.10.1109/ISBI.2018.8363836 ↗
8. Voxel-Based Meta-Analysis of Gray Matter Volume Reductions Associated with Cognitive Impairment in Parkinson’s Disease10.1007/s00415-016-8122-3 ↗
9. Calomino, C., Bianco, M.G., Oliva, G., Laganà, F., Pullano, S.A., and Quattrone, A. (2024, January 26–28). Comparative Analysis of Cross-Validation Methods on PPMI Dataset. Proceedings of the 2024 IEEE International Symposium on Medical Measurements and Applications (MeMeA), Eindhoven, The Netherlands.10.1109/MeMeA60663.2024.10596885 ↗
10. Li, J., Yang, J., Gan, H., and Huang, Z. (2024, January 27–30). Parkinson’s Disease Diagnosis with Sparse Learning of Multi-Modal Adaptive Similarity. Proceedings of the 2024 IEEE International Symposium on Biomedical Imaging (ISBI), Athens, Greece.10.1109/ISBI56570.2024.10635628 ↗
11. Qiu, S., Miller, M.I., Joshi, P.S., Lee, J.C., Xue, C., Ni, Y., Wang, Y., De Anda-Duran, I., Hwang, P.H., and Cramer, J.A. (2022). Multimodal deep learning for Alzheimer’s disease dementia assessment. Nat. Commun., 13.10.1038/s41467-022-31037-5 ↗
12. Cui, X., Zhou, Y., Zhao, C., Li, J., Zheng, X., Li, X., Shan, S., Liu, J.-X., and Liu, X. (2024). A Multiscale Hybrid Attention Networks Based on Multiview Images for the Diagnosis of Parkinson’s Disease. IEEE Trans. Instrum. Meas., 73.10.1109/TIM.2023.3315407 ↗
13. Exploiting macro- and micro-structural brain changes for improved Parkinson’s disease classification from MRI data10.1038/s41531-024-00647-9 ↗
14. Zhang, J. (2022). Mining imaging and clinical data with machine learning approaches for the diagnosis and early detection of Parkinson’s disease. npj Park. Dis., 8.10.1038/s41531-021-00266-8 ↗
15. Camacho, M., Wilms, M., Mouches, P., Almgren, H., Souza, R., Camicioli, R., Ismail, Z., Monchi, O., and Forkert, N.D. (2023). Explainable Classification of Parkinson’s Disease Using Deep Learning Trained on a Large Multi-Center Database of T1-Weighted MRI Datasets. NeuroImage Clin., 38.10.1016/j.nicl.2023.103405 ↗
16. Hara, K., Kataoka, H., and Satoh, Y. (2018, January 18–22). Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00685 ↗
17. Chakraborty, S., Aich, S., and Kim, H.-C. (2020). Detection of Parkinson’s Disease from 3T T1-Weighted MRI Scans Using 3D Convolutional Neural Network. Diagnostics, 10.10.3390/diagnostics10060402 ↗
18. Chen, S., Ma, K., and Zheng, Y. (2019). Med3D: Transfer Learning for 3D Medical Image Analysis. arXiv.
19. scikit-learn (2025, September 17). GroupKFold (and StratifiedGroupKFold)—Documentation. Available online: https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.GroupKFold.html.
20. Bu, S., Pang, H., Li, X., Zhao, M., Wang, J., Liu, Y., and Yu, H. (2023). Multi-Parametric Radiomics of Conventional T1-Weighted and Susceptibility-Weighted Imaging for Differential Diagnosis of Idiopathic Parkinson’s Disease and Multiple System Atrophy. BMC Med. Imaging, 23.10.1186/s12880-023-01169-1 ↗
21. Bradshaw, T.J., Huemann, Z., Hu, J., and Rahmim, A. (2023). A Guide to Cross-Validation for Artificial Intelligence in Medical Imaging. Radiol. Artif. Intell., 5.10.1148/ryai.220232 ↗
22. Yan, J., Luo, X., Xu, J., Li, D., Qiu, L., Li, D., Cao, P., and Zhang, C. (2024). Unlocking the Potential: T1-Weighted MRI as a Powerful Predictor of Levodopa Response in Parkinson’s Disease. Insights Imaging, 15.10.1186/s13244-024-01690-z ↗
23. The Parkinson Progression Marker Initiative (PPMI)10.1016/j.pneurobio.2011.09.005 ↗
24. The Parkinson’s Progression Markers Initiative (PPMI)—Establishing a PD Biomarker Cohort10.1002/acn3.644 ↗
25. Fonov, V.S., Evans, A.C., McKinstry, R.C., Almli, C.R., and Collins, D.L. (2009). Unbiased Nonlinear Average Age-Appropriate Brain Templates from Birth to Adulthood. NeuroImage, 47.10.1016/S1053-8119(09)70884-5 ↗
26. Gaser, C., Dahnke, R., Thompson, P.M., Kurth, F., and Luders, E. (2024). Computational Anatomy Toolbox 12: Isotropic Surfaces, Sulcal Depth, and Developmental Data. GigaScience, 13.10.1093/gigascience/giae049 ↗
27. (2025, September 17). SPM12 Manual Wellcome Centre for Human Neuroimaging, U.C.L. Available online: https://www.fil.ion.ucl.ac.uk/spm/doc/manual.pdf.
28. (2025, September 17). Torchvision: r3d_18—Video Models, A.P.I. Available online: https://docs.pytorch.org/vision/main/models/generated/torchvision.models.video.r3d_18.html.
29. Rumala, D.J. (2023). How You Split Matters: Data Leakage and Subject Characteristics Studies in Longitudinal Brain MRI Analysis. arXiv.10.1007/978-3-031-45249-9_23 ↗
30. Hu, J., Shen, L., and Sun, G. (2018, January 18–22). Squeeze-and-Excitation Networks. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00745 ↗
31. Woo, S., Park, J., Lee, J.-Y., and Kweon, I.S. (2018, January 8–14). CBAM: Convolutional Block Attention Module. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01234-2_1 ↗
32. Tan, M., and Le, Q. (2019, January 9–15). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. Proceedings of the International Conference on Machine Learning (ICML), Long Beach, CA, USA.
33. Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., and Guo, B. (2021, January 11–17). Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Online.10.1109/ICCV48922.2021.00986 ↗
34. Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017, January 22–29). Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.74 ↗