Skip to main content

The application of an artificial neural network to Doppler ultrasound waveforms for the classification of arterial disease

International journal of clinical monitoring and computing volume 13, pages 85–91 (1996)Cite this article

Abstract

In this study we have investigated the application of an Artificial Neural Net classifier to the diagnosis of vascular disease using Doppler ultrasound blood-velocity/time waveforms. A multi-layer perceptron network was trained with waveforms from control subjects and from patients with arterial disease. The diseased cases were confirmed by angiography and allocated to three groups according to the location of the stenosis: proximal or distal to the site of measurement or multi-segmental. We compared network classification results with a Bayesian classifier following a Principal Component Analysis of the waveforms. Versions of both classifiers were trained to discriminate two classes (normal v. abnormal) and four classes. In both cases the neural networks gave superior discrimination to the Bayesian classifier. While the four-class network was unable to provide useful discrimination among the stenosis sites, discrimination between abnormal and normal classes was obtained which is comparable to that achieved by a human expert observer.

This is a preview of subscription content, access via your institution.

References

  • Forrest APM, Carter DC, Macleod IB. Principles and Practice of Surgery. Edinburgh: Churchill-Livingstone, 1992.

    Google Scholar 

  • Souhami RL, Moxham J, editors. Textbook of Medicine. Edinburgh: Churchill-Livingstone, 1990.

    Google Scholar 

  • Gosling RG, Dunbar G, King DH, Newman DL, Side CD, Woodcock JP, Fitzgerald DE, Keates JS, MacMillan D. The quantitative analysis of peripheral arterial disease by a non-intrusive ultrasonic technique. Angiology. 1971; 22: 52–5.

    PubMed  Article  CAS  Google Scholar 

  • May AG, Dewesse JA, Rob CG. Haemodynamic effects of arterial stenosis. Surgery 1963; 53: 513–24.

    PubMed  CAS  Google Scholar 

  • Skidmore R, Woodcock JP. Physiological Interpretation of Doppler-shift Waveforms—I. Theoretical considerations. Ultrasound in Med. & Biol. 1980; 6: 7–10.

    Article  CAS  Google Scholar 

  • Prytherch DR, Evans DH, Smith MJ, Macpherson DS. On-line classification of arterial severity using principal component analysis applied to Doppler ultrasound. Clin. Phys. Physiol. Meas. 1982; 3: 191–200.

    PubMed  Article  CAS  Google Scholar 

  • Beale R, Jackson T. Neural Computing: An Introduction. Bristol: Institute of Physics Publishing Ltd, 1992.

    Google Scholar 

  • Clark JW. Neutral Network Modelling. Phys. Med. Biol. 1991; 36: 1259–317.

    PubMed  Article  CAS  Google Scholar 

  • Evans DH. The interpretation of continuous wave ultrasonic Doppler blood velocity signals viewed as a problem in pattern recognition. J. Biomed. Eng. 1984; 6: 272–80.

    PubMed  Article  CAS  Google Scholar 

  • Rumelhart DE, Hinton GE, Williams RJ. Learning Representations by back-propagating errors. Nature 1986; 323: 533–6.

    Article  Google Scholar 

  • McClelland JL, Rumelhart DE. Exploration in Parallel Distributed Processing: A handbook of Models, Programs and Exercises. Cambridge, MA: MIT Press, 1988.

    Google Scholar 

  • Martin TRP, Barber DC, Sherriff SB, Prichard DR. Objective feature extraction applied to the diagnosis of carotid artery disease using a Doppler ultrasound technique. Clin. Phys. Physiol. Meas. 1980; 1: 71–81.

    Article  Google Scholar 

  • Evans DH, MacPherson DS, Bentley S, Asher MJ, Bell PRF. The effect of proximal stenosis on Doppler waveforms: a comparison of three methods of waveform analysis in an animal model. Clin. Phys. Physiol. Meas. 1981; 2: 17–25.

    PubMed  Article  CAS  Google Scholar 

  • Barber DC, Sherriff SB. Carotid artery blood flow: single factor classification of Doppler waveforms. Clin. Phys. Physiol. Meas. 1986; 7: 271–5.

    PubMed  Article  CAS  Google Scholar 

  • Sherriff SB, Barber DC. A simple quantitative screening test for the detection of extracranial carotid artery disease. Clin. Phys. Physiol. Meas. 1989; 10 (Suppl. A): 23–32.

    PubMed  Article  Google Scholar 

  • Evans DH, Macpherson DS, Bell PRF. A comparison of three methods of analysis of Ultrasonic Doppler waveforms recorded from the common femoral artery of patients with vascular disease. Ann. 8th Brazilian Biomed. Engng. Cong. 1983: 112–7.

  • Bland M. An Introduction to Medical Statistics. Oxford: Oxford University Press, 1993.

    Google Scholar 

  • Allen J, Murray A. Development of a neural network screening aid for diagnosing lower limb peripheral vascular disease from photoelectric plethysmography pulse waveforms. Physiol. Meas. 1993; 14: 13–22.

    PubMed  Article  CAS  Google Scholar 

  • Allen J, Murray A. Prospective assessment of an artificial neural network for the detection of peripheral vascular disease from lower limb pulse waveforms. Physiol. Meas. 1995; 16: 29–38.

    PubMed  Article  CAS  Google Scholar 

  • James M. Classification Algorithms. Chichester: Wiley, 1985.

    Google Scholar 

  • Piper J. Variability and bias in experimentally measured classification error rates. Patt. Recog. Lett. 1992; 13: 685–92.

    Article  Google Scholar 

  • Errington PA. Application of Artificial neural Networks to Chromosome Analysis, (PhD Thesis), Manchester (UK): Univ. of Manchester, 1995.

    Google Scholar 

Download references

Author information

Affiliations

  1. Department of Medical Biophysics, University of Manchester, Oxford Road, M13 9PT, Manchester, UK

    Julia H. Smith & Jim Graham

  2. Department of Medical Physics, Salford Royal Hospitals NHS Trust, Hope Hospital, Stott Lane, M6 8HD, Salford, UK

    Robert J. Taylor

Authors
  1. Julia H. Smith
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jim Graham
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Robert J. Taylor
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Smith, J.H., Graham, J. & Taylor, R.J. The application of an artificial neural network to Doppler ultrasound waveforms for the classification of arterial disease. J Clin Monit Comput 13, 85–91 (1996). https://doi.org/10.1007/BF02915843

Download citation

  • Received:

  • Accepted:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF02915843

Key words

  • arterial disease classification
  • artificial neural networks
  • doppler ultrasound
  • multi-layer perceptron