Refining Parkinson’s neurological disorder identification through deep transfer learning

  • Amina Naseer
  • Monail Rani
  • Saeeda Naz
  • Muhammad Imran RazzakEmail author
  • Muhammad Imran
  • Guandong Xu
Intelligent Biomedical Data Analysis and Processing


Parkinson’s disease (PD), a multi-system neurodegenerative disorder which affects the brain slowly, is characterized by symptoms such as muscle stiffness, tremor in the limbs and impaired balance, all of which tend to worsen with the passage of time. Available treatments target its symptoms, aiming to improve the quality of life. However, automatic diagnosis at early stages is still a challenging medicine-related task to date, since a patient may have an identical behavior to that of a healthy individual at the very early stage of the disease. Parkinson’s disease detection through handwriting data is a significant classification problem for identification of PD at the infancy stage. In this paper, a PD identification is realized with help of handwriting images that help as one of the earliest indicators for PD. For this purpose, we proposed a deep convolutional neural network classifier with transfer learning and data augmentation techniques to improve the identification. Two approaches like freeze and fine-tuning of transfer learning are investigated using ImageNet and MNIST dataset as source task independently. A trained network achieved 98.28% accuracy using fine-tuning-based approach using ImageNet and PaHaW dataset. Experimental results on benchmark dataset reveal that the proposed approach provides better detection of Parkinson’s disease as compared to state-of-the-art work.


Parkinson disease Handwriting analysis Neurodegenerative disorder 


Compliance with ethical standards

Conflict of interest

All authors declare that they have no conflict of interest.


  1. 1.
    Lücking CB, Dürr A, Bonifati V, Vaughan J, De Michele G, Gasser T, Harhangi BS et al (2000) Association between early-onset Parkinson's disease and mutations in the parkin gene. N Engl J Med 342(21):1560–1567CrossRefGoogle Scholar
  2. 2.
    Grandi LC, Di Giovanni G, Galati S (2018) Animal models of early-stage Parkinsons disease and acute dopamine deficiency to study compensatory neurodegenerative mechanisms. J Neurosci Methods 308:205–218CrossRefGoogle Scholar
  3. 3.
    Masliah E, Rockenstein E, Veinbergs I, Mal-lory M, Hashimoto M, Takeda A, Sagara Y, Sisk A, Mucke L (2000) Dopaminergic loss and inclusion body formation in a-synuclein mice: implications for neurodegenerative disorders. Science 287(5456):1265–1269CrossRefGoogle Scholar
  4. 4.
    Letanneux A, Danna J, Velay J-L, Viallet F, Pinto S (2014) From micrographia to Parkinson’s disease dysgraphia. Mov Disord 29(12):1467–1475CrossRefGoogle Scholar
  5. 5.
    Thomas M, Lenka A, Kumar Pal P (2017) Hand-writing analysis in Parkinson’s disease: current status and future directions. Mov Disord Clin Pract 4(6):806–818CrossRefGoogle Scholar
  6. 6.
    Crespo Y, Soriano MF, Iglesias-Parro S, Aznarte JI, Ibáñez-Molina AJ (2018) Spatial analysis ofhandwritten texts as a marker of cognitive control. J Mot Behav 50(6):643–652CrossRefGoogle Scholar
  7. 7.
    Collett J, Franssen M, Winward C, Izadi H, Meaney A, Mahmoud W, Bogdanovic M, Tims M, Wade D, Dawes H (2017) A long-term self-managed handwriting intervention for people with Parkinsons disease: results from the control group of a phase II randomized controlled trial. Clin Rehabilit 31(12):1636–1645CrossRefGoogle Scholar
  8. 8.
    Nackaerts E, Broeder S, Pereira MP, Swinnen SP, Vandenberghe W, Nieuwboer A, Heremans E (2017) Handwriting training in Parkinsons disease: a trade-off between size, speed and fluency. PLoS ONE 12(12):e0190223CrossRefGoogle Scholar
  9. 9.
    Vasquez-Correa JC, Orozco-Arroyave JR, Arora R, Nöth E, Dehak N, Christensen H, Rudzicz F, Bocklet T, Cernak M, Chinaei H et al (2017) Multi-view representation learning via gcca for multimodal analysis of Parkinson’s disease. In: 2017 IEEE international conference on in acoustics, speech and signal processing (ICASSP). IEEE, pp 2966–2970Google Scholar
  10. 10.
    Moetesum M, Siddiqi I, Vincent N, Cloppet F (2018) Assessing visual attributes of handwriting for prediction of neurological disorders case study on Parkinsons disease. Pattern Recognit Lett. Google Scholar
  11. 11.
    di Biase L, Summa S, Tosi J, Taffoni F, Marano M, Cascio Rizzo A, Vecchio F, Formica D, Di Lazzaro V, Di Pino G et al (2018) Quantitative analysis of bradykinesia and rigidity in Parkinsons disease. Front Neurol 9:121CrossRefGoogle Scholar
  12. 12.
    Werner P, Rosenblum S, Bar-On G, Heinik J, Korczyn A (2006) Handwriting process variables discriminating mild Alzheimer’s disease and mild cognitive impairment. J Gerontol Ser B Psychol Sci Soc Sci 61(4):P228–P236CrossRefGoogle Scholar
  13. 13.
    Razzak I, Imran M, Xu G (2018) Efficient brain tumor segmentation with multiscale two-pathway-group conventional neural networks. IEEE J Biomed Health Inform. Google Scholar
  14. 14.
    Razzak MI, Naz S, Zaib A (2018) Deep learning for medical image processing: Overview, challenges and the future. In: Classification in bioapps. Springer, pp 323–350Google Scholar
  15. 15.
    Razzak MI, Naz S (2017) Microscopic blood smear segmentation and classification using deep contour aware cnn and extreme machine learning. In: 2017 IEEE conference on computer vision and pattern recognition workshops (CVPRW). IEEE, pp 801–807Google Scholar
  16. 16.
    Naz S, Umar AI, Ahmad R, Siddiqi I, Ahmed SB, Razzak MI, Shafiat F (2017) Urdu Nastaliq recognition using convolutional recursive deep learning. NeuroComputing 243:80–87CrossRefGoogle Scholar
  17. 17.
    Naz S, Umar AI, Ahmad R, Ahmed SB, Shirazi SH, Razzak MI (2017) Urdu Nastaliq text recognition system based on multi-dimensional recurrent neural network and statistical features. Neural Comput Appl 28(2):219–231CrossRefGoogle Scholar
  18. 18.
    Naz S, Umar AI, Ahmad R, Ahmed SB, Sid-diqi I, Razzak MI (2016) Offline cursive Nastaliq script recognition using multidimensional recurrent neural networks with statistical features. NeuroComputing 177:228–241CrossRefGoogle Scholar
  19. 19.
    Rehman A, Naz S, Razzak MI, Hameed IA (2019) Automatic visual features for writer identification: a deep learning approach. Neural Comput ApplGoogle Scholar
  20. 20.
    McLennan J, Nakano K, Tyler H, Schwab R (1972) Micrographia in parkinson’s disease. J Neurol Sci 15(2):141–152CrossRefGoogle Scholar
  21. 21.
    Tsanas A, Little MA, McSharry PE, Spiel-man J, Ramig LO (2012) Novel speech signal processing algorithms for high-accuracy classification of Parkinson’s disease. IEEE Trans Biomed Eng 59(5):1264–1271CrossRefGoogle Scholar
  22. 22.
    Millian-Morell L, Lopez-Alburquerque T, Rodriguez-Rodriguez A, Gomez-Nieto R, Carro J, Meilan JJ, Martinez-Sanchez F, Sancho C, Lopez DE (2018) Relations between sensorimotor integration and speech disorders in Parkinson’s disease. Curr Alzheimer Res 15(2):149–156CrossRefGoogle Scholar
  23. 23.
    Hariharan M, Polat K, Sindhu R (2014) A new hybrid intelligent system for accurate detection of Parkinson’s disease. Comput Methods Programs Biomed 113(3):904–913CrossRefGoogle Scholar
  24. 24.
    Rusz J, Cmejla R, Růžičková H, Klempíř J, Majerová V, Picmausová J, Roth J, Růžička E (2011) Acoustic assessment of voice and speech disorders in Parkinson’s disease through quick vocal test. Mov Disord 26(10):1951–1952CrossRefGoogle Scholar
  25. 25.
    Pettorino M, Pellegrino E, Busà MG (2016) Speech disorders and Parkinson’s disease. Parkinsonism Relat Disord 22:e48CrossRefGoogle Scholar
  26. 26.
    Aich S, Younga K, Hui KL, Al-Absi AA, Sain M (2018) A nonlinear decision tree based classification approach to predict the Parkinson’s disease using different feature sets of voice data. In: 2018 20th international conference on advanced communication technology (ICACT). IEEE, pp 638–642Google Scholar
  27. 27.
    Caliskan A, Badem H, Basturk A, Yuksel ME (2017) Diagnosis of the Parkinson disease by using deep neural network classifier. Istanb Univ J Electr Electron Eng 17(2):3311–3319Google Scholar
  28. 28.
    Delrobaei M, Memar S, Pieterman M, Stratton TW, McIsaac K, Jog M (2018) Towards remote monitoring of Parkinsons disease tremor using wearable motion capture systems. J Neurol Sci 384:38–45CrossRefGoogle Scholar
  29. 29.
    Cancela J, Pastorino M, Waldmeyer MTA (2018) Trends and new advances on wearable and mobile technologies for Parkinson’s disease monitoring and assessment of motor symptoms: how new technologies can support Parkinson’s disease. In: Biomedical engineering: concepts, methodologies, tools, and applications. IGI Global, pp 1180–1204Google Scholar
  30. 30.
    Xia Y, Yao Z, Lu Y, Zhang D, Cheng N (2018) A machine learning approach to detecting of freezing of gait in Parkinson’s disease patients. J Med Imag Health Inform 8(4):647–654CrossRefGoogle Scholar
  31. 31.
    Xu C, He J, Zhang X, Wang C, Duan S (2018) Template-matching-based detection of freezing of gait using wearable sensors. Procedia Comput Sci 129:21–27CrossRefGoogle Scholar
  32. 32.
    Eskofier BM, Lee SI, Daneault J-F, Golabchi FN, Ferreira-Carvalho G, Vergara-Diaz G, Sapienza S, Costante G, Klucken J, Kautz T (2016) Recent machine learning advancements in sensor-based mobility analysis: deep learning for Parkinson’s disease assessment. In: IEEE 38th annual international conference of the engineering in medicine and biology society (EMBC). IEEE, pp 655–658Google Scholar
  33. 33.
    Ruonala V, Pekkonen E, Airaksinen O, Kankaanpää M, Karjalainen PA, Rissanen SM (2018) Levodopa-induced changes in electromyographic patterns in patients with advanced Parkinsons disease. Front Neurol 9:35CrossRefGoogle Scholar
  34. 34.
    Bond AE, Shah BB, Elias WJ (2018) Assessing tremor and adverse events in patients with tremor-dominant parkinson disease undergoing focused ultrasound thalamotomy reply. JAMA Neurol 75(5):633CrossRefGoogle Scholar
  35. 35.
    Pereira CR, Weber SA, Hook C, Rosa GH, Papa JP (2016) Deep learning-aided Parkinson. In: 2016 29th SIBGRAPI conference on graphics, patterns and images (SIBGRAPI). IEEE, pp 340–346Google Scholar
  36. 36.
    Pereira CR, Pereira DR, Papa JP, Rosa GH, Yang X-S (2016) Convolutional neural networks applied for Parkinsons disease identification. In: Machine learning for health informatics. Springer, pp 377–390Google Scholar
  37. 37.
    Pereira CR, Pereira DR, Rosa GH, Al-buquerque VH, Weber SA, Hook C, Papa JP (2018) Handwritten dynamics assessment through convolutional neural networks: an application to Parkinson’s disease identification. Artif Intell Med 87:67–77CrossRefGoogle Scholar
  38. 38.
    Zhang Y (2017) Can a smartphone diagnose Parkinson disease? A deep neural network method and telediagnosis system implementation. Parkinsons Dis 2017:1–11Google Scholar
  39. 39.
    Grover S, Bhartia S, Yadav A, Seeja K et al (2018) Predicting severity of Parkinsons disease using deep learning. Procedia Comput Sci 132:1788–1794CrossRefGoogle Scholar
  40. 40.
    Choi H, Ha S, Im HJ, Paek SH, Lee DS (2017) Refining diagnosis of Parkinson’s disease with deep learning-based interpretation of dopamine transporter imaging. NeuroImage Clin 16:586–594CrossRefGoogle Scholar
  41. 41.
    Afonso LCS, Rosa GH, Pereira CR, Weber SAT, Hook C, Albuquerque VHC, Papa JP (2019) A recurrence plot-based approach for Parkinson’s disease identification. Future Gener Comput Syst 94:282–292. CrossRefGoogle Scholar
  42. 42.
    Gupta D, Julka A, Jain S, Aggarwal T, Khanna A, Arunkumar N, de Albu-querque VHC (2018) Optimized cuttlefish algorithm for diagnosis of Parkinson’s disease. Cognit Syst Res 52:36–48. CrossRefGoogle Scholar
  43. 43.
    Gupta D, Sundaram S, Khanna A, Has-sanien AE, de Albuquerque VHC (2018) Improved diagnosis of Parkinson’s disease using optimized crow search algorithm. Comput Electr Eng 68:412–424CrossRefGoogle Scholar
  44. 44.
    Ratliff J, Ortega RA, Ooi HY, Mirallave A, Glickman A, Yu Q, Raymond D, Bressman S, Pullman S, Saunders-Pullman R (2018) Digitized spiral analysis may be a potential biomarker for brachial dystonia. Parkinsonism Relat Disord 57:16–21CrossRefGoogle Scholar
  45. 45.
    San Luciano M, Wang C, Ortega RA, Yu Q, Boschung S, Soto-Valencia J, Bressman SB, Lipton RB, Pullman S, Saunders-Pullman R (2016) Digitized spiral drawing: A possible biomarker for early Parkinsons disease. PLoS ONE 11(10):e0162799CrossRefGoogle Scholar
  46. 46.
    Saunders-Pullman R, Derby C, Stanley K, Floyd A, Bressman S, Lipton RB, Deligtisch A, Severt L, Yu Q, Kurtis M et al (2008) Validity of spiral analysis in early Parkinson’s disease. Mov Disord 23(4):531–537CrossRefGoogle Scholar
  47. 47.
    Aly N, Playfer J, Smith S, Halliday D (2007) A novel computer-based technique for the assessment of tremor in Parkinson’s disease. Age Ageing 36(4):395–399CrossRefGoogle Scholar
  48. 48.
    Drotr P, Mekyska J, Rectorova I, Masarova L, Smekal Z, Faundez-Zanuy M (2014) Analysis of in-air movement in handwriting: a novel marker for parkinsons disease. Comput Methods Programs Biomed 117:405–411CrossRefGoogle Scholar
  49. 49.
    Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105Google Scholar
  50. 50.
    Kraus PH, Hoffmann A (2010) Spiralometry: computerized assessment of tremor amplitude on the basis of spiral drawing. Mov Disord 25(13):2164–2170CrossRefGoogle Scholar
  51. 51.
    Stanley K, Hagenah J, Brüggemann N, Reetz K, Severt L, Klein C, Yu Q, Derby C, Pullman S, Saunders-Pullman R (2010) Digitized spiral analysis is a promising early motor marker for Parkinson disease. Parkinsonism Relat Disord 16(3):233–234CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2019

Authors and Affiliations

  • Amina Naseer
    • 1
  • Monail Rani
    • 1
  • Saeeda Naz
    • 1
  • Muhammad Imran Razzak
    • 2
    Email author
  • Muhammad Imran
    • 3
  • Guandong Xu
    • 2
  1. 1.Computer Science DepartmentGovt Girls Postgraduate College No.1AbbottabadPakistan
  2. 2.Advanced Analytics InstituteUniversity of TechnologySydneyAustralia
  3. 3.Deanship of e-Transactions and CommunicationKing Saud UniversityRiyadhSaudi Arabia

Personalised recommendations