Deep learning predicts prevalent and incident Parkinson's disease from UK Biobank fundus imaging.


Journal

Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288

Informations de publication

Date de publication:
13 Feb 2024
Historique:
received: 02 05 2023
accepted: 10 02 2024
medline: 14 2 2024
pubmed: 14 2 2024
entrez: 13 2 2024
Statut: epublish

Résumé

Parkinson's disease is the world's fastest-growing neurological disorder. Research to elucidate the mechanisms of Parkinson's disease and automate diagnostics would greatly improve the treatment of patients with Parkinson's disease. Current diagnostic methods are expensive and have limited availability. Considering the insidious and preclinical onset and progression of the disease, a desirable screening should be diagnostically accurate even before the onset of symptoms to allow medical interventions. We highlight retinal fundus imaging, often termed a window to the brain, as a diagnostic screening modality for Parkinson's disease. We conducted a systematic evaluation of conventional machine learning and deep learning techniques to classify Parkinson's disease from UK Biobank fundus imaging. Our results suggest Parkinson's disease individuals can be differentiated from age and gender-matched healthy subjects with 68% accuracy. This accuracy is maintained when predicting either prevalent or incident Parkinson's disease. Explainability and trustworthiness are enhanced by visual attribution maps of localized biomarkers and quantified metrics of model robustness to data perturbations.

Identifiants

pubmed: 38351326
doi: 10.1038/s41598-024-54251-1
pii: 10.1038/s41598-024-54251-1
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

3637

Subventions

Organisme : National Science Foundation
ID : NSF IIS 2123809

Informations de copyright

© 2024. The Author(s).

Références

Yang, W. et al. Current and projected future economic burden of Parkinson’s disease in the US. NPJ Parkinson’s Dis. 6, 15 (2020).
doi: 10.1038/s41531-020-0117-1
World Health Organization. Parkinson disease. https://www.who.int/news-room/fact-sheets/detail/parkinson-disease (2022).
Tolosa, E., Garrido, A., Scholz, S. W. & Poewe, W. Challenges in the diagnosis of Parkinson’s disease. Lancet Neurol. 20, 385–397 (2021).
doi: 10.1016/S1474-4422(21)00030-2 pubmed: 33894193 pmcid: 8185633
Damier, P., Hirsch, E. C., Agid, Y. & Graybiel, A. M. The substantia nigra of the human brain. Brain 122, 1437–1448 (1999).
doi: 10.1093/brain/122.8.1437 pubmed: 10430830
Meissner, W. G. When does Parkinson’s disease begin? From prodromal disease to motor signs. Revue Neurologique 168, 809–814 (2012).
doi: 10.1016/j.neurol.2012.07.004 pubmed: 22981298
Postuma, R. B. et al. MDS clinical diagnostic criteria for Parkinson’s disease: MDS-PD clinical diagnostic criteria. Mov. Disord. 30, 1591–1601 (2015).
doi: 10.1002/mds.26424 pubmed: 26474316
Martin, W. R. W. et al. Is levodopa response a valid indicator of Parkinson’s disease?. Mov. Disord. 36, 948–954 (2021).
doi: 10.1002/mds.28406 pubmed: 33253432
Jankovic, J. Motor fluctuations and dyskinesias in Parkinson’s disease: Clinical manifestations. Mov. Disord. 20, S11–S16 (2005).
doi: 10.1002/mds.20458 pubmed: 15822109
De La Fuente-Fernández, R. Role of DaTSCAN and clinical diagnosis in Parkinson disease. Neurology 78, 696–701 (2012).
doi: 10.1212/WNL.0b013e318248e520 pubmed: 22323748
Postuma, R. B. et al. Validation of the MDS clinical diagnostic criteria for Parkinson’s disease. Mov. Disord. 33, 1601–1608 (2018).
doi: 10.1002/mds.27362 pubmed: 30145797
Beach, T. G. & Adler, C. H. Importance of low diagnostic accuracy for early Parkinson’s disease. Mov. Disord. 33, 1551–1554 (2018).
doi: 10.1002/mds.27485 pubmed: 30288780 pmcid: 6544441
London, A., Benhar, I. & Schwartz, M. The retina as a window to the brain—from eye research to CNS disorders. Nat. Rev. Neurol. 9, 44–53 (2013).
doi: 10.1038/nrneurol.2012.227 pubmed: 23165340
Gupta, S., Zivadinov, R., Ramanathan, M. & Weinstock-Guttman, B. Optical coherence tomography and neurodegeneration: Are eyes the windows to the brain?. Expert Rev. Neurother. 16, 765–775 (2016).
doi: 10.1080/14737175.2016.1180978 pubmed: 27138997
Archibald, N. K., Clarke, M. P., Mosimann, U. P. & Burn, D. J. The retina in Parkinson’s disease. Brain 132, 1128–1145 (2009).
doi: 10.1093/brain/awp068 pubmed: 19336464
Mohana Devi, S., Mahalaxmi, I., Aswathy, N. P., Dhivya, V. & Balachandar, V. Does retina play a role in Parkinson’s Disease?. Acta Neurologica Belgica 120, 257–265 (2020).
doi: 10.1007/s13760-020-01274-w pubmed: 31965540
Diederich, N. J., Raman, R., Leurgans, S. & Goetz, C. G. Progressive worsening of spatial and chromatic processing deficits in Parkinson disease. Arch. Neur. 59, 1249 (2002).
doi: 10.1001/archneur.59.8.1249
Kwapong, W. R. et al. Retinal microvascular impairment in the early stages of Parkinson’s disease. Investig. Ophthalmol. Vis. Sci. 59, 4115 (2018).
doi: 10.1167/iovs.17-23230
Hajee, M. E. Inner retinal layer thinning in Parkinson disease. Arch. Ophthalmol. 127, 737 (2009).
doi: 10.1001/archophthalmol.2009.106 pubmed: 19506190
Mailankody, P. et al. Optical coherence tomography as a tool to evaluate retinal changes in Parkinson’s disease. Parkinsonism Relat. Disord. 21, 1164–1169 (2015).
doi: 10.1016/j.parkreldis.2015.08.002 pubmed: 26297381
Kromer, R. et al. Evaluation of retinal vessel morphology in patients with Parkinson’s disease using optical coherence tomography. PLoS ONE 11, e0161136 (2016).
doi: 10.1371/journal.pone.0161136 pubmed: 27525728 pmcid: 4985161
Dai, L. et al. A deep learning system for detecting diabetic retinopathy across the disease spectrum. Nat. Commun. 12, 3242 (2021).
doi: 10.1038/s41467-021-23458-5 pubmed: 34050158 pmcid: 8163820
Yan, Q. et al. Deep-learning-based prediction of late age-related macular degeneration progression. Nat. Mach. Intell. 2, 141–150 (2020).
doi: 10.1038/s42256-020-0154-9 pubmed: 32285025 pmcid: 7153739
Sudlow, C. et al. UK Biobank: An open access resource for identifying the causes of a wide range of complex diseases of middle and old age. PLoS Med. 12, e1001779 (2015).
doi: 10.1371/journal.pmed.1001779 pubmed: 25826379 pmcid: 4380465
Terracciano, A. et al. Neuroticism and risk of Parkinson’s disease: A meta-analysis. Mov. Disord. 36, 1863–1870 (2021).
doi: 10.1002/mds.28575 pubmed: 33817817 pmcid: 8376751
Xu, Q. et al. Diabetes and risk of Parkinson’s disease. Diabetes Care 34, 910–915 (2011).
doi: 10.2337/dc10-1922 pubmed: 21378214 pmcid: 3064050
Kizza, J. et al. Cardiovascular risk factors and Parkinson’s disease in 500,000 Chinese adults. Ann. Clin. Transl. Neurol. 6, 624–632 (2019).
doi: 10.1002/acn3.732 pubmed: 31019987 pmcid: 6469341
Zhou, Y. et al. AutoMorph: Automated retinal vascular morphology quantification via a deep learning pipeline. Trans. Vis. Sci. Tech. 11, 12 (2022).
doi: 10.1167/tvst.11.7.12
Carelli, V., La Morgia, C., Ross-Cisneros, F. N. & Sadun, A. A. Optic neuropathies: The tip of the neurodegeneration iceberg. Hum. Mol. Genet. 26, R139–R150 (2017).
doi: 10.1093/hmg/ddx273 pubmed: 28977448 pmcid: 5886475
Pilat, A. et al. In vivo morphology of the optic nerve and retina in patients with Parkinson’s disease. Investig. Ophthalmol. Vis. Sci. 57, 4420 (2016).
doi: 10.1167/iovs.16-20020
Miri, S. et al. The avascular zone and neuronal remodeling of the fovea in Parkinson disease. Ann. Clin. Transl. Neurol. 2, 196–201 (2015).
doi: 10.1002/acn3.146 pubmed: 25750923 pmcid: 4338959
Ascherio, A. & Schwarzschild, M. A. The epidemiology of Parkinson’s disease: Risk factors and prevention. Lancet Neurol. 15, 1257–1272 (2016).
doi: 10.1016/S1474-4422(16)30230-7 pubmed: 27751556
Miller, I. N. & Cronin-Golomb, A. Gender differences in Parkinson’s disease: Clinical characteristics and cognition. Mov. Disord. 25, 2695–2703 (2010).
doi: 10.1002/mds.23388 pubmed: 20925068 pmcid: 3003756
Hu, W. et al. Retinal age gap as a predictive biomarker of future risk of Parkinson’s disease. Age Ageing 51, afac062 (2022).
doi: 10.1093/ageing/afac062 pubmed: 35352798 pmcid: 8966015
Nunes, A. et al. Retinal texture biomarkers may help to discriminate between Alzheimer’s, Parkinson’s, and healthy controls. PLoS ONE 14, e0218826 (2019).
doi: 10.1371/journal.pone.0218826 pubmed: 31226150 pmcid: 6588252
Tian, J. et al. Modular machine learning for Alzheimer’s disease classification from retinal vasculature. Sci. Rep. 11, 238 (2021).
doi: 10.1038/s41598-020-80312-2 pubmed: 33420208 pmcid: 7794289
Wisely, C. E. et al. Convolutional neural network to identify symptomatic Alzheimer’s disease using multimodal retinal imaging. Br. J. Ophthalmol. 106, 388–395 (2022).
doi: 10.1136/bjophthalmol-2020-317659 pubmed: 33243829
Bush, K., Rannikmae, K., Wilkinson, T., Schnier, C. & Sudlow, C. Definitions of Parkinson’s disease and the major causes of parkinsonism, UK Biobank Phase 1 Outcomes Adjudication. (2018).
Chua, S. Y. L. et al. Cohort profile: Design and methods in the eye and vision consortium of UK Biobank. BMJ Open 9, e025077 (2019).
doi: 10.1136/bmjopen-2018-025077 pubmed: 30796124 pmcid: 6398663
Fu, H. et al. Evaluation of Retinal Image Quality Assessment Networks in Different Color-Spaces. vol. 11764, 48–56 (2019).
Krizhevsky, A., Sutskever, I. & Hinton, G. E. ImageNet classification with deep convolutional neural networks. Commun. ACM 60, 84–90 (2017).
doi: 10.1145/3065386
Simonyan, K. & Zisserman, A. Very Deep Convolutional Networks for Large-Scale Image Recognition. Preprint at http://arxiv.org/abs/1409.1556 (2015).
Szegedy, C. et al. Going Deeper with Convolutions. Preprint at http://arxiv.org/abs/1409.4842 (2014).
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J. & Wojna, Z. Rethinking the Inception Architecture for Computer Vision. Preprint at http://arxiv.org/abs/1512.00567 (2015).
He, K., Zhang, X., Ren, S. & Sun, J. Deep Residual Learning for Image Recognition. Preprint at http://arxiv.org/abs/1512.03385 (2015).
Kingma, D. P. & Ba, J. Adam: A Method for Stochastic Optimization. Preprint at http://arxiv.org/abs/1412.6980 (2017).
Selvaraju, R. R. et al. Grad-CAM: Visual explanations from deep networks via gradient-based localization. Int J Comput Vis 128, 336–359 (2020).
doi: 10.1007/s11263-019-01228-7
Yeh, C.-K., Hsieh, C.-Y., Suggala, A. S., Inouye, D. I. & Ravikumar, P. On the (In)fidelity and Sensitivity for Explanations. Preprint at http://arxiv.org/abs/1901.09392 (2019).

Auteurs

Charlie Tran (C)

Department of Electrical and Computer Engineering, University of Florida, Gainesville, FL, 32611, USA.

Kai Shen (K)

Department of Electrical and Computer Engineering, University of Florida, Gainesville, FL, 32611, USA.

Kang Liu (K)

Department of Physics, University of Florida, Gainesville, FL, 32661, USA.

Akshay Ashok (A)

Department of Computer and Information Science and Engineering, University of Florida, Gainesville, FL, 32611, USA.

Adolfo Ramirez-Zamora (A)

Department of Neurology, University of Florida, Gainesville, FL, 32661, USA.

Jinghua Chen (J)

Department of Ophthalmology, University of Florida, Gainesville, FL, 32661, USA.

Yulin Li (Y)

Department of Biostatistics, University of Florida, Gainesville, FL, 32661, USA.

Ruogu Fang (R)

Department of Electrical and Computer Engineering, University of Florida, Gainesville, FL, 32611, USA. ruogu.fang@ufl.edu.
J. Crayton Pruitt Family Department of Biomedical Engineering, Herbert Wertheim College of Engineering, University of Florida, 1275 Center Drive, PO Box 116131, Gainesville, FL, 32611-6131, USA. ruogu.fang@ufl.edu.
Center for Cognitive Aging and Memory, University of Florida, Gainesville, FL, 32611, USA. ruogu.fang@ufl.edu.

Classifications MeSH