Page 38 - AIH-2-4

Artificial Intelligence in Health Early Parkinson’s detection through CNNs

doi: 10.1016/j.ijmedinf.2016.03.001 doi: 10.1212/wnl.17.5.427
27. Prashanth R, Roy SD, Mandal PK, Ghosh S. High-accuracy 37. LeCun Y, Bengio Y, Hinton G. Deep learning. Nature.
classification of Parkinson’s disease through shape analysis 2015;521(7553):436-444.
and surface fitting in 123I-Ioflupane SPECT imaging. IEEE J
Biomed Health Inform. 2017;21(2):794-802. doi: 10.1038/nature14539
doi: 10.1109/JBHI.2016.2547901 38. Cortes C, Vapnik V. Support-vector networks. Mach Learn.
1995;20(3):273-297.
28. Segovia F, Gorriz JM, Ramirez J, Alvarez I, Jimenez-
Hoyuela JM, Ortega SJ. Improved parkinsonism diagnosis doi: 10.1007/BF00994018
using a partial least squares based approach. Med Phys. 39. Lee SI, Lee H, Abbeel P, Ng AY. Efficient l-1 regularized
2012;39(7):4395-4403. logistic regression. In: Proceedings of the 21 National
st
doi: 10.1118/1.4730289 Conference on Artificial Intelligence (AAAI). 2006. p. 401-408.
29. Illan IA, Gorrz JM, Ramirez J, Segovia F, Jimenez-Hoyuela JM, 40. Bergstra JS, Bardenet R, Bengio Y, Kégl B. Algorithms for
Ortega Lozano SJ. Automatic assistance to Parkinson’s disease hyper-parameter optimization. In: Advances in Neural
diagnosis in DaTSCAN SPECT imaging. Med Phys. Information Processing Systems 24. 2011. p. 2546-2554.
2012;39(10):5971-5980.
41. Srivastava N, Hinton G, Krizhevsky A, Sutskever I,
doi: 10.1118/1.4742055 Salakhutdinov R. Dropout: A simple way to prevent
30. Rojas A, Górriz JM, Ramírez J, et al. Application of neural networks from overfitting. J Mach Learn Res.
empirical mode decomposition (EMD) on DaTSCAN 2014;15(1):1929-1958.
SPECT images to explore Parkinson disease. Expert Syst 42. Perez L, Wang J. The Effectiveness of Data Augmentation in
Appl. 2013;40(7):2756-2766.
Image Classification using Deep Learning. [arXiv Preprint];
doi: 10.1016/j.eswa.2012.11.017 2017.
31. Towey DJ, Bain PG, Nijran KS. Automatic classification 43. Goodfellow I, Pouget-Abadie J, Mirza M, et al. Generative
of 123I-FP-CIT (DaTSCAN) SPECT images. Nucl Med adversarial nets. In: Advances in Neural Information
Commun. 2011;32(8):699-707. Processing Systems 27. [Preprint]; 2014. p. 2672-2680
doi: 10.1097/MNM.0b013e328347cd09 44. Muller R, Kornblith S, Hinton GE. When does label
32. Huertas-Fernandez I, Garcia-Gomez F, Garcia-Solis D, smoothing help? In: Advances in Neural Information
et al. Machine learning models for the differential diagnosis Processing Systems 32. 2019. p. 4696-4705.
of vascular parkinsonism and Parkinson’s disease using 45. Shiiba T, Takano K, Takaki A, Suwazono S. Dopamine
[(123) I] FP-CIT SPECT. Eur J Nucl Med Mol Imaging. transporter single-photon emission computed tomography-
2015;42(1):112-119.
derived radiomics signature for detecting Parkinson’s
doi: 10.1007/s00259-014-2882-8 disease. EJNMMI Res. 2022;12(1):39.
33. Oliveira FP, Faria DB, Costa DC, Castelo-Branco M, doi: 10.1186/s13550-022-00910-1
Tavares JMR. Extraction, selection and comparison of
features for an effective automated computer-aided diagnosis 46. Tufail AB, Ma YK, Zhang QN, et al. 3D convolutional neural
of Parkinson’s disease based on [ I] FP-CIT SPECT images. networks-based multiclass classification of Alzheimer’s and
123
Eur J Nucl Med Mol Imaging. 2018;45(6):1052-1062. Parkinson’s diseases using PET and SPECT neuroimaging
modalities. Brain Inform. 2021;8(1):23.
doi: 10.1007/s00259-017-3918-7
doi: 10.1186/s40708-021-00144-2
34. Zhang X, Chou J, Liang J, et al. Data-driven subtyping of
Parkinson’s disease using longitudinal clinical records: A 47. Majhi B, Kashyap A, Mohanty SS, et al. An improved method
cohort study. Sci Rep. 2019;9(1):797. for diagnosis of Parkinson’s disease using deep learning
doi: 10.1038/s41598-018-37545-z models enhanced with metaheuristic algorithm. BMC Med
Imaging. 2024;24(1):156.
35. Marek K, Chowdhury S, Siderowf A, et al. The Parkinson’s
progression markers initiative (PPMI) - establishing a doi: 10.1186/s12880-024-01335-z
PD biomarker cohort. Ann Clin Transl Neurol. 2018; 48. Khachnaoui H, Chikhaoui B, Khlifa N, Mabrouk R. Enhanced
5(12):1460-1477. Parkinson’s disease diagnosis through convolutional neural
doi: 10.1002/acn3.644 network models applied to spect datscan images. IEEE
Access. 2023;11:91157-91172.
36. Hoehn MM, Yahr MD. Parkinsonism: Onset, progression
and mortality. Neurology. 1967;17(5):427-442. doi: 10.1109/ACCESS.2023.3308075

Volume 2 Issue 4 (2025) 32 doi: 10.36922/AIH025040005