Skip to main content
SpringerLink
Log in

Unbiased confidence measures for stroke risk estimation based on ultrasound carotid image analysis

  • Engineering Applications of Neural Networks
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

We propose an approach for providing well-calibrated confidence measures for determining cerebrovascular risk stratification based on characteristics from noninvasive ultrasound imaging of carotid plaques. An important challenge we address is the class imbalance problem inherent in the particular task. The proposed approach is based on a novel framework, called conformal prediction (CP), for developing techniques that output sets of predictions guaranteed to contain the true classification of a new case with a prespecified probability. We follow a modified version of the CP framework, called Label-conditional Mondrian conformal prediction (LCMCP), so that the guarantee provided by CP does not only hold for all instances together, but also hold for the instances of each class independently, thus making prediction sets unbiased. Furthermore, LCMCP is combined with an underbagging ensemble of artificial neural networks so that its outputs are based on unbiased estimates. The important positive properties of the proposed approach are demonstrated experimentally on a dataset of patients that were followed up for eight years and had asymptomatic internal carotid artery stenosis at the baseline.

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

Similar content being viewed by others

Notes

  1. LifeQ Medical Ltd http://www.lifeqmedical.com/.

References

  1. Abbott AL (2009) Medical (non-surgical) intervention alone is now best for prevention of stroke associated with asymptomatic severe carotid stenosis: results of a systematic review and analysis. Stroke 40:573–583

    Article  Google Scholar 

  2. Barandela R, Sánchez JS, García V, Rangel E (2003) Strategies for learning in class imbalance problems. Pattern Recognit 36(3):849–851

    Article  Google Scholar 

  3. Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP (2002) Smote: synthetic minority over-sampling technique. J Artif Intell Res 16:321–357

    MATH  Google Scholar 

  4. Chawla NV, Cieslak DA, Hall LO, Joshi A (2008) Automatically countering imbalance and its empirical relationship to cost. Data Min Knowl Discov 17(2):225–252

    Article  MathSciNet  Google Scholar 

  5. Christodoulou CI, Pattichis CS, Pantziaris M, Nicolaides A (2003) Texture based classification of atherosclerotic carotid plaques. IEEE Trans Med Imaging 22(7):902–912

    Article  Google Scholar 

  6. Executive Committee for the Asymptomatic Carotid Atherosclerosis Study (1995) Endarterectomy for asymptomatic carotid artery stenosis. J Am Med Assoc 273:1421–1428

    Article  Google Scholar 

  7. Galar M, Fernandez A, Barrenechea E, Bustince H, Herrera F (2011) A review on ensembles for the class imbalance problem: bagging-, boosting-, and hybrid-based approaches. IEEE Trans Syst Man Cybern Part C 42(4):463–484

    Article  Google Scholar 

  8. Geroulakos G, Ramaswami G, Nicolaides A, James K, Labropoulos N, Belcaro G, Holloway M (1993) Characterisation of symptomatic and asymptomatic carotid plaques using high-resolution real-time ultrasonography. Br J Surg 80:1274–1277

    Article  Google Scholar 

  9. Kyriacou E, Pattichis C, Christodoulou C, Loizou C, Pattichis M, Kakkos S, Nicolaides A (2010) A review of ultrasound imaging of the carotid artery for the assessment of the risk of stroke. IEEE Trans Inf Technol Biomed 14(4):1027–1038

    Article  Google Scholar 

  10. Kyriacou EC, Petroudi S, Pattichis CS, Pattichis MS, Griffin M, Kakkos S, Nicolaides A (2012) Prediction of high risk asymptomatic carotid plaques based on ultrasonic image features. IEEE Trans Inf Technol Biomed 16(5):966–973

    Article  Google Scholar 

  11. Lambrou A, Papadopoulos H, Kyriacou E, Pattichis CS, Pattichis MS, Gammerman A, Nicolaides A (2010) Assessment of stroke risk based on morphological ultrasound image analysis with conformal prediction. In: Proceedings of the 6th IFIP international conference on artificial intelligence applications and innovations (AIAI 2010), IFIP AICT, vol 339. Springer, pp 146–153

  12. Lambrou A, Papadopoulos H, Kyriacou E, Pattichis CS, Pattichis MS, Gammerman A, Nicolaides A (2012) Evaluation of the risk of stroke with confidence predictions based on ultrasound carotid image analysis. Int J Artif Intell Tools 21(4):1240,016. doi:10.1142/S0218213012400167

    Article  Google Scholar 

  13. Leahy AL, McCollum PT, Feeley TM, Sugrue M, Grouden MC, O’Connell DJ, Moore DJ, Shanik GD (1998) Duplex ultrasonography and selection of patients for carotid endarterectomy: plaque morphology or luminal narrowing? J Vasc Surg 8:558–562

    Article  Google Scholar 

  14. Lin Y, Lee Y, Wahba G (2002) Support vector machines for classification in nonstandard situations. Mach Learn 46(1):191–202

    Article  MATH  Google Scholar 

  15. Ling CX, Sheng VS, Yang Q (2006) Test strategies for cost-sensitive decision trees. IEEE Trans Knowl Data Eng 18(8):1055–1067

    Article  Google Scholar 

  16. Liu XY, Wu J, Zhou ZH (2009) Exploratory undersampling for class-imbalance learning. IEEE Trans Syst Man Cybern Part B 39(2):539–550

    Article  Google Scholar 

  17. Löfström T, Boström H, Linusson H, Johansson U (2015a) Bias reduction through conditional conformal prediction. Intell Data Anal 9(6):1355–1375

    Article  Google Scholar 

  18. Löfström T, Zhao J, Linusson H, Jansson K (2015b) Predicting adverse drug events with confidence. In: Proceedings of the 13th Scandinavian conference on artificial intelligence (SCAI 2015), IOS Press, Frontiers in Artificial Intelligence and Applications, vol 278, pp 88–97

  19. MRC Asymptomatic Carotid Surgery Trial (ACST) Collaborative Group (2004) Prevention of disabling and fatal strokes by successful carotid endarterectomy in patients without recent neurological symptoms: randomized controlled trial. Lancet 363:1491–1502

    Article  Google Scholar 

  20. Napierala K, Stefanowski J, Wilk S (2010) Learning from imbalanced data in presence of noisy and borderline examples. Rough Sets Curr Trends Comput (Springer LNCS) 6086:158–167

    Article  Google Scholar 

  21. Naylor AR, Gaines PA, Rothwell PM (2009) Who benefits most from intervention in asymptomatic carotid stenosis: patients or professionals? Eur J Vasc Endovasc Surg 37:625–632

    Article  Google Scholar 

  22. Nicolaides AN, Kakkos SK, Kyriacou E, Griffn M, Sabetai M, Thomas DJ, Tegos T, Geroulakos G, Labropoulos N, Dore CJ, Morris TP, Naylor R, Abbott AL, Asymptomatic Carotid Stenosis and Risk of Stroke (ACSRS) Study Group (2010) Asymptomatic internal carotid artery stenosis and cerebrovascular risk stratification. J Vasc Surg 52(4):1486–1496

    Article  Google Scholar 

  23. Papadopoulos H (2008) Inductive conformal prediction theory and application to neural networks. In: Fritzsche P (ed) Tools in artificial intelligence. InTech, Vienna, pp 315–330. doi:10.5772/6078 (chapter 18)

    Google Scholar 

  24. Papadopoulos H, Kyriacou E, Nicolaides A, Pattichis C (2015) Reliable probabilistic prediction of high-risk asymptomatic carotid plaques. In: Proceedings of the 16th international conference on engineering applications of neural networks, ACM, pp 16:1–16:9

  25. Reiter M, Horvat R, Puchner S, Rinner W, Polterauer P, Lammer J, Minar E, Bucek R (2007) Plaque imaging of the internal carotid artery-correlation of b-flow imaging with histopathology. Am J Neuroradiol 28:122–126

    Google Scholar 

  26. Stefanowski J, Wilk S (2008) Selective pre-processing of imbalanced data for improving classification performance. Data Warehous Knowl Discov (Springer LNCS) 5182:283–292

    Article  Google Scholar 

  27. Vovk V, Gammerman A, Shafer G (2005) Algorithmic learning in a random world. Springer, New York

    MATH  Google Scholar 

  28. Vovk V, Fedorova V, Nouretdinov I, Gammerman A (2016) Criteria of efficiency for conformal prediction. In: Proceedings of the 5th international symposium on conformal and probabilistic prediction with applications (COPA 2016), vol 9653. Springer, LNCS, pp 23–39

  29. Wallace BC, Dahabreh IJ (2014) Improving class probability estimates for imbalanced data. Knowl Inf Syst 41(1):33–52

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science and Engineering, Frederick University, Nicosia, Cyprus

    Harris Papadopoulos

  2. Department of Computer Science and Engineering, Frederick University, Limassol, Cyprus

    Efthyvoulos Kyriacou

  3. Imperial College London, London, UK

    Andrew Nicolaides

  4. Vascular Noninvasive Screening and Diagnostic Centre, London , UK

    Andrew Nicolaides

  5. Cyprus CDER Trust, Nicosia, Cyprus

    Andrew Nicolaides

Authors
  1. Harris Papadopoulos
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Efthyvoulos Kyriacou
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Andrew Nicolaides
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Harris Papadopoulos.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Papadopoulos, H., Kyriacou, E. & Nicolaides, A. Unbiased confidence measures for stroke risk estimation based on ultrasound carotid image analysis. Neural Comput & Applic 28, 1209–1223 (2017). https://doi.org/10.1007/s00521-016-2590-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-016-2590-3

Keywords

Search

Navigation