Skip to main content
SpringerLink
Log in

Comparison of two neural network classifiers in the differential diagnosis of essential tremor and Parkinson’s disease by 123I-FP-CIT brain SPECT

  • Original Article
  • Published:
European Journal of Nuclear Medicine and Molecular Imaging Aims and scope Submit manuscript

An Erratum to this article was published on 15 July 2010

Abstract

Purpose

To contribute to the differentiation of Parkinson’s disease (PD) and essential tremor (ET), we compared two different artificial neural network classifiers using 123I-FP-CIT SPECT data, a probabilistic neural network (PNN) and a classification tree (ClT).

Methods

123I-FP-CIT brain SPECT with semiquantitative analysis was performed in 216 patients: 89 with ET, 64 with PD with a Hoehn and Yahr (H&Y) score of ≤2 (early PD), and 63 with PD with a H&Y score of ≥2.5 (advanced PD). For each of the 1,000 experiments carried out, 108 patients were randomly selected as the PNN training set, while the remaining 108 validated the trained PNN, and the percentage of the validation data correctly classified in the three groups of patients was computed. The expected performance of an “average performance PNN” was evaluated. In analogy, for ClT 1,000 classification trees with similar structures were generated.

Results

For PNN, the probability of correct classification in patients with early PD was 81.9±8.1% (mean±SD), in patients with advanced PD 78.9±8.1%, and in ET patients 96.6±2.6%. For ClT, the first decision rule gave a mean value for the putamen of 5.99, which resulted in a probability of correct classification of 93.5±3.4%. This means that patients with putamen values >5.99 were classified as having ET, while patients with putamen values <5.99 were classified as having PD. Furthermore, if the caudate nucleus value was higher than 6.97 patients were classified as having early PD (probability 69.8±5.3%), and if the value was <6.97 patients were classified as having advanced PD (probability 88.1%±8.8%).

Conclusion

These results confirm that PNN achieved valid classification results. Furthermore, ClT provided reliable cut-off values able to differentiate ET and PD of different severities.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

References

  1. Benamer HTS, Patterson J, Grosset DG. Accurate differentiation of Parkinsonism and essential tremor using visual assessment of 123I-FP-CIT SPECT imaging: the 123I-FP-CIT study. Mov Disord 2000;15(3):503–10.

    Article  CAS  PubMed  Google Scholar 

  2. Marshall V, Grosset D. Role of dopamine transporter imaging in routine clinical practice. Mov Disord 2003;18(12):1415–23.

    Article  PubMed  Google Scholar 

  3. Antonini A, Berto P, Lopatriello S, Tamma F, Annemans L, Chambers M. Cost-effectiveness of 123I-FP-CIT SPECT in the differential diagnosis of essential tremor and Parkinson's disease in Italy. Mov Disord 2008;15;23(15):2202–9.

    Article  Google Scholar 

  4. Van Laere K, Varrone A, Booij J, Vander Borght T, Nobili F, Kapucu OL, et al. EANM procedure guidelines for brain neurotransmission SPECT/PET using dopamine D2 receptor ligands, version 2. Eur J Nucl Med Mol Imaging 2010;37(2):434–42.

    Article  CAS  PubMed  Google Scholar 

  5. Hamilton D, List A, Butler T, Hogg S, Cawley M. Discrimination between parkinsonian syndrome and essential tremor using artificial neural network classification of quantified DaTSCAN data. Nucl Med Commun 2006;27(12):939–44.

    Article  PubMed  Google Scholar 

  6. Specht DF. Probabilistic neural network. Neural Netw 1990;3(1):109–18.

    Article  Google Scholar 

  7. Breiman L. Hinging hyperplanes for regression, classification and function approximation. IEEE Trans Inf Theory 1993;39(3):999–1013.

    Article  Google Scholar 

  8. Deuschl G, Bain P, Brin M. Consensus Statement of the Movement Disorder Society on tremor. Ad hoc Scientific Committee. Mov Disord 1998;13 Suppl 3:2–23.

    PubMed  Google Scholar 

  9. Hoehn M, Yahr MD. Parkinsonism: onset, progression, and mortality. Neurology 1967;17:427–42.

    CAS  PubMed  Google Scholar 

  10. Wasserman PD. Advanced methods in neural computing. New York: Van Nostrand Rei Synopsis; 1993.

    Google Scholar 

  11. Breiman L, Friedman JH, Olshen RA, Stone CJ. Classification and regression trees. London: Chapman and Hall/CRC Press; 1984.

    Google Scholar 

  12. Page PA, Howard RJ, O’ Brien JT, Buxton-Thomas MS, Pickering AD. Use of neural networks in brain SPECT to diagnose Alzheimer’s disease. J Nucl Med 1996;37:195–200.

    CAS  PubMed  Google Scholar 

  13. Hamilton D, O'Mahony D, Coffey J, Murphy J, O'Hare N, Freyne P, et al. Classification of mild Alzheimer's disease by artificial neural network analysis of SPET data. Nucl Med Commun 1997;18(9):805–10.

    Article  CAS  PubMed  Google Scholar 

  14. Warkentin S, Ohlsson M, Wollmer P, Edenbrandt L, Minthon L. Regional cerebral blood flow in Alzheimer's disease: classification and analysis of heterogeneity. Dement Geriatr Cogn Disord 2004;17(3):207–14.

    Article  PubMed  Google Scholar 

  15. Acton PD, Newberg A. Artificial neural network classifier for the diagnosis of Parkinson's disease using [99mTc]TRODAT-1 and SPECT. Phys Med Biol 2006;21;51(12):3057–66.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Nuclear Medicine Section, Department of Surgical, Radiological and Odontostomatological Sciences, Ospedale S. Maria della Misericordia, University of Perugia, S. Andrea delle Fratte, 06124, Perugia, Italy

    Barbara Palumbo

  2. Department of Electronic and Information Engineering, University of Perugia, Perugia, Italy

    Mario Luca Fravolini

  3. Department of Nuclear Medicine, University of Sassari, Sassari, Italy

    Susanna Nuvoli, Angela Spanu & Giuseppe Madeddu

  4. Department of Neurology, University of Sassari, Sassari, Italy

    Kai Stephan Paulus

  5. Department of Biopathology and Diagnostic Imaging, University Tor Vergata, Rome, Italy

    Orazio Schillaci

  6. IRCSS Neuromed, Pozzilli, Italy

    Orazio Schillaci

Authors
  1. Barbara Palumbo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mario Luca Fravolini
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Susanna Nuvoli
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Angela Spanu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Kai Stephan Paulus
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Orazio Schillaci
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Giuseppe Madeddu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Barbara Palumbo.

Additional information

An erratum to this article can be found at http://dx.doi.org/10.1007/s00259-010-1547-5

Rights and permissions

Reprints and permissions

About this article

Cite this article

Palumbo, B., Fravolini, M.L., Nuvoli, S. et al. Comparison of two neural network classifiers in the differential diagnosis of essential tremor and Parkinson’s disease by 123I-FP-CIT brain SPECT. Eur J Nucl Med Mol Imaging 37, 2146–2153 (2010). https://doi.org/10.1007/s00259-010-1481-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00259-010-1481-6

Keywords

Search

Navigation