Kirbizakis, Dimitrios (2025) Prediction of Parkinson’s Disease with Convolutional Neural Networks using Structural T1Weighted MRIs. Masters thesis, Concordia University.
Preview |
Text (application/pdf)
8MBKirbizakis_MCompSc_W2026.pdf - Accepted Version Available under License Spectrum Terms of Access. |
Abstract
Parkinson’s disease (PD) is a progressive neurodegenerative disorder with no current cure, where early detection and accurate prediction of disease progression would be crucial for patient care and treatment planning. Structural T1-weighted Magnetic Resonance Imaging (MRI) offers a non-invasive way to investigate brain patterns, and Convolutional Neural Networks (CNNs) have shown promise in medical image analysis to detect these patterns automatically. This study evaluates how 3D CNN architectures can be used to predict PD diagnosis using baseline T1-weighted MRIs from the Parkinson’s Progression Markers Initiative (PPMI), as diagnosis is the first step to progression. We replicated two published CNN models used for PD classification and followed the preprocessing pipelines found from the original studies. The model’s performance was validated using permutation testing and explainability techniques, including Grad-CAM and saliency maps. Results showed that for PD classification, all tested CNNs achieved near-chance performance (ROC AUC around 0.6 at best), with explainability maps revealing no stable or meaningful patterns, suggesting
random predictions. To ensure the models were capable of classification in general, we tested the models on sex classification, which is correlated to MRI data. The same models performed substantially better on sex classification tasks (ROC AUC around 0.7-0.8, p-value < 0.01), with consistent spatial focus along the boundaries of the brain, indicating effective pattern recognition in a binary classification setting. These findings suggest that while the evaluated CNNs trained on PPMI data are capable of learning structural features in MRI data, their current configurations and available datasets are insufficient for reliable PD classification.
| Divisions: | Concordia University > Gina Cody School of Engineering and Computer Science > Computer Science and Software Engineering |
|---|---|
| Item Type: | Thesis (Masters) |
| Authors: | Kirbizakis, Dimitrios |
| Institution: | Concordia University |
| Degree Name: | M. Comp. Sc. |
| Program: | Computer Science |
| Date: | 4 December 2025 |
| Thesis Supervisor(s): | Glatard, Tristan |
| Keywords: | Parkinson’s disease Structural T1-weighted MRI 3D Convolutional Neural Networks Permutation testing Explainability |
| ID Code: | 996655 |
| Deposited By: | Dimitrios Kirbizakis |
| Deposited On: | 29 Jun 2026 14:57 |
| Last Modified: | 29 Jun 2026 14:57 |
References:
(1) E. R. Dorsey et al., “Global, regional, and national burden of Parkinson’s disease,1990–2016: a systematic analysis for the Global Burden of Disease Study 2016,” The
Lancet Neurology, vol. 17, no. 11, pp. 939–953, Nov. 2018, doi: 10.1016/S1474-
4422(18)30295-3.
(2) A. Govindu and S. Palwe, “Early detection of Parkinson’s disease using machine
learning,” Procedia Computer Science, vol. 218, pp. 249–261, Jan. 2023, doi:
10.1016/j.procs.2023.01.007.
(3) V. Kaul, S. Enslin, and S. A. Gross, “History of artificial intelligence in
medicine,” Gastrointestinal Endoscopy, vol. 92, no. 4, pp. 807–812, Oct. 2020, doi:
10.1016/j.gie.2020.06.040.
(4) R. Hirani et al., “Artificial Intelligence and Healthcare: A Journey through History,
Present Innovations, and Future Possibilities,” Life (Basel), vol. 14, no. 5, p. 557, Apr.
2024, doi: 10.3390/life14050557.
(5) D. Ferrucci, A. Levas, S. Bagchi, D. Gondek, and E. T. Mueller, “Watson: Beyond
Jeopardy!,” Artificial Intelligence, vol. 199–200, pp. 93–105, Jun. 2013, doi:
10.1016/j.artint.2012.06.009.
(6) N. Bakkar et al., “Artificial intelligence in neurodegenerative disease research: use
of IBM Watson to identify additional RNA-binding proteins altered in amyotrophic
lateral sclerosis,” Acta Neuropathol, vol. 135, no. 2, pp. 227–247, Feb. 2018, doi:
10.1007/s00401-017-1785-8.
(7) J. Mei, C. Desrosiers, and J. Frasnelli, “Machine Learning for the Diagnosis of Parkinson’s
Disease: A Review of Literature,” Front. Aging Neurosci., vol. 13, May 2021, doi:
10.3389/fnagi.2021.633752.
(8) S. S. Kshatri and D. Singh, “Convolutional Neural Network in Medical Image Analysis:
A Review,” Arch Computat Methods Eng, vol. 30, no. 4, pp. 2793–2810, May 2023,
doi: 10.1007/s11831-023-09898-w.
(9) A. Das, G. R. Patra, and M. N. Mohanty, “LSTM based Odia Handwritten Numeral
Recognition,” in 2020 International Conference on Communication and Signal Processing
(ICCSP), Jul. 2020, pp. 0538–0541. doi: 10.1109/ICCSP48568.2020.9182218.
(10) S. M. Anwar, M. Majid, A. Qayyum, M. Awais, M. Alnowami, and M. K. Khan, “Medical
Image Analysis using Convolutional Neural Networks: A Review,” J Med Syst, vol.
42, no. 11, pp. 1–13, Nov. 2018, doi: 10.1007/s10916-018-1088-1.
(11) C¸ . B. Erdas¸ and E. S¨umer, “A fully automated approach involving neuroimaging and
deep learning for Parkinson’s disease detection and severity prediction,” PeerJ Computer
Science, vol. 9, p. e1485, Jul. 2023, doi: 10.7717/peerj-cs.1485.
(12) N. J. Dhinagar et al., “3D convolutional neural networks for classification of
Alzheimer’s and Parkinson’s disease with T1-weighted brain MRI,” in 17th International
Symposium on Medical Information Processing and Analysis, SPIE, Dec. 2021,
pp. 277–286. doi: 10.1117/12.2606297.
(13) M. Ebel, M. Lotze, M. Domin, N. Neumann, and M. Stanke, “Classifying sex with
MRI,” Apr. 28, 2022. doi: 10.1101/2022.04.27.22274355.
(14) V. Fonov, A. C. Evans, K. Botteron, C. R. Almli, R. C. McKinstry, and D. L. Collins,
“Unbiased average age-appropriate atlases for pediatric studies,” NeuroImage, vol. 54,
no. 1, pp. 313–327, Jan. 2011, doi: 10.1016/j.neuroimage.2010.07.033.
(15) J. Mazziotta et al., “A probabilistic atlas and reference system for the human brain:
International Consortium for Brain Mapping (ICBM),” Philos Trans R Soc Lond B Biol
Sci, vol. 356, no. 1412, pp. 1293–1322, Aug. 2001, doi: 10.1098/rstb.2001.0915.
(16) S. M. Smith et al., “Advances in functional and structural MR image analysis and
implementation as FSL,” Neuroimage, vol. 23 Suppl 1, pp. S208-219, 2004, doi:
10.1016/j.neuroimage.2004.07.051.
(17) S. M. Smith, “Fast robust automated brain extraction,” Hum Brain Mapp, vol. 17, no. 3,
pp. 143–155, Nov. 2002, doi: 10.1002/hbm.10062.
(18) F. Isensee et al., “Automated brain extraction of multisequence MRI using artificial
neural networks,” Human Brain Mapping, vol. 40, no. 17, pp. 4952–4964, 2019, doi:
10.1002/hbm.24750.
(19) N. J. Tustison et al., “N4ITK: Improved N3 Bias Correction,” IEEE Transactions
on Medical Imaging, vol. 29, no. 6, pp. 1310–1320, Jun. 2010, doi:
10.1109/TMI.2010.2046908.
(20) K. Canese and S. Weis, “PubMed: The Bibliographic Database”.
(21) K. Marek et al., “The Parkinson’s progression markers initiative (PPMI) – establishing
a PD biomarker cohort,” Annals of Clinical and Translational Neurology, vol. 5, no. 12,
pp. 1460–1477, 2018, doi: 10.1002/acn3.644.
(22) M. A. Nalls et al., “Baseline genetic associations in the Parkinson’s Progression Markers
Initiative (PPMI),” Movement Disorders, vol. 31, no. 1, pp. 79–85, 2016, doi:
10.1002/mds.26374.
(23) J. Davis and M. Goadrich, “The relationship between Precision-Recall and ROC
curves,” in Proceedings of the 23rd international conference on Machine learning
- ICML ’06, Pittsburgh, Pennsylvania: ACM Press, 2006, pp. 233–240. doi:
10.1145/1143844.1143874.
(24) A. N. V. Ruigrok et al., “A meta-analysis of sex differences in human brain structure,”
Neuroscience & Biobehavioral Reviews, vol. 39, pp. 34–50, Feb. 2014, doi:
10.1016/j.neubiorev.2013.12.004.
(25) S. Konate et al., “A Comparison of Saliency Methods for Deep Learning Explainability,”
in 2021 Digital Image Computing: Techniques and Applications (DICTA), Nov. 2021,
pp. 01–08. doi: 10.1109/DICTA52665.2021.9647419.
(26) 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,”
presented at the Proceedings of the IEEE International Conference on Computer Vision,
2017, pp. 618–626.
(27) J. Adebayo, J. Gilmer, M. Muelly, I. Goodfellow, M. Hardt, and B. Kim, “Sanity Checks
for Saliency Maps,” in Advances in Neural Information Processing Systems, Curran
Associates, Inc., 2018.
(28) S. Bhat, U. R. Acharya, Y. Hagiwara, N. Dadmehr, and H. Adeli, “Parkinson’s disease:
Cause factors, measurable indicators, and early diagnosis,” Computers in Biology and
Medicine, vol. 102, pp. 234–241, Nov. 2018, doi: 10.1016/j.compbiomed.2018.09.008.
(29) T. Mahmood, A. Rehman, T. Saba, L. Nadeem, and S. A. O. Bahaj, “Recent Advancements
and Future Prospects in Active Deep Learning for Medical Image Segmentation
and Classification,” IEEE Access, vol. 11, pp. 113623–113652, 2023, doi: 10.1109/ACCESS.
2023.3313977.
(30) M. B. T. Noor, N. Z. Zenia, M. S. Kaiser, S. A. Mamun, and M. Mahmud, “Application
of deep learning in detecting neurological disorders from magnetic resonance images: a
survey on the detection of Alzheimer’s disease, Parkinson’s disease and schizophrenia,”
Brain Inf., vol. 7, no. 1, p. 11, Oct. 2020, doi: 10.1186/s40708-020-00112-2.
Repository Staff Only: item control page
Download Statistics
Download Statistics