Special Issue on Selected Papers from the 6th IFIP International Conference on Artificial Intelligence Applications & Innovations (AIAI 2010); Guest Editors: H. Papadopoulos, A. S. Andreou and L. IliadisNo Access

EVALUATION OF THE RISK OF STROKE WITH CONFIDENCE PREDICTIONS BASED ON ULTRASOUND CAROTID IMAGE ANALYSIS

ANTONIS LAMBROU

Computer Learning Research Centre, Royal Holloway, University of London, UK

Search for more papers by this author

HARRIS PAPADOPOULOS

Computer Science and Engineering Department, Frederick University, Cyprus

Search for more papers by this author

EFTHYVOULOS KYRIACOU

Computer Science and Engineering Department, Frederick University, Cyprus

Search for more papers by this author

CONSTANTINOS S. PATTICHIS

Computer Science and Engineering Department, University of Cyprus, Nicosia, Cyprus

Search for more papers by this author

MARIOS S. PATTICHIS

Electrical and Computer Engineering Department, University of New Mexico, New Mexico, USA

Search for more papers by this author

ALEXANDER GAMMERMAN

Computer Learning Research Centre, Royal Holloway, University of London, UK

Search for more papers by this author

, and

ANDREW NICOLAIDES

Imperial College London, UK

Vascular screening and Diagnostic Centre, London, UK

Cyprus Cardiovascular Disease Educational Research Trust, Nicosia, Cyprus

Search for more papers by this author

https://doi.org/10.1142/S0218213012400167Cited by:9 (Source: Crossref)

Abstract

Conformal Predictors (CPs) are Machine Learning algorithms that can provide reliable confidence measures to their predictions. In this work, we make use of the Conformal Prediction framework for the assessment of stroke risk based on ultrasound images of atherosclerotic carotid plaques. For this application, images were recorded from 137 asymptomatic and 137 symptomatic plaques (symptoms are Stroke, Transient Ischaemic Attack (TIA), and Amaurosis Fugax (AF)). Two feature sets were extracted from the plaques; the first based on morphological image analysis and the second based on image texture analysis. Both sets were used in order to evaluate the performance of CPs on this problem. Four CPs were constructed using four popular classification methods, namely Artificial Neural Networks (ANNs), Support Vector Machines (SVMs), Naive Bayes Classification (NBC), and k-Nearest Neighbours. The results given by all CPs demonstrate the reliability and importance of the obtained confidence measures on the problem of stroke risk assessment.

Keywords:

Remember to check out the Most Cited Articles!
Check out Notable Titles in Artificial Intelligence.

References

Gianni Belcaroet al., Arterioscler Thromb Vasc Biol 16(7), 851 (1996). Web of Science, Google Scholar
Tony Bellotti, Zhiyuan Luo and Alexander Gammerman, Reliable classification of childhood acute leukaemia from gene expression data using confidence machines, Proceedings of IEEE International Conference on Granular Computing (GRC '06) (2006) pp. 148–153. Google Scholar
Tony Bellottiet al., International Journal of Neural Systems 15(4), 247 (2005). Link, Web of Science, Google Scholar
Christodoulos I. Christodoulouet al., Multiple feature extraction for content-based image retrieval of carotid plaque ultrasound images, Proceedings of the 5th International IEEE Special Topic Conference on Information Technology Applications in Biomedicine (2006) pp. 26–28. Google Scholar
C. I. Christodoulouet al., IEEE Transactions on Medical Imaging 22(7), 902 (2003). Web of Science, Google Scholar
Devetyarov Dmitry and Nouretdinov Ilia, Prediction with confidence based on a random forest classifier, Artificial Intelligence Applications and Innovations – 6th IFIP WG 12.5 International Conference (AIAI 2010)339 (Springer, Boston, 2010) pp. 37–44. Google Scholar
N. El-Barghoutyet al., European Journal of Vascular and Endovascular Surgery 9(4), 389 (1995). Web of Science, Google Scholar
A. Gammerman, V. Vovk and V. Vapnik, Uncertainty in Artificial Intelligence (Morgan Kaufmann, 1998) pp. 148–155. Google Scholar
Alexander Gammermanet al., Statistical Applications in Genetics and Molecular Biology 7(2), (2008). Google Scholar
G. Geroulakoset al., Journal of Vascular Surgery 20(2), 263 (1994). Web of Science, Google Scholar
Arcangelo Iannuzziet al., Stroke 26(4), 614 (1995). Web of Science, Google Scholar
E. C. Kyriacouet al., Information Technology in Biomedicine, IEEE Transactions on 14(4), 1027 (2010). Web of Science, Google Scholar
E. C. Kyriacouet al., Engineering in Medicine and Biology Magazine, IEEE 26(5), 43 (2007). Web of Science, Google Scholar
Efthyvoulos Kyriacouet al., Applied Intelligence 30(1), 3 (2009). Web of Science, Google Scholar
Antonis Lambrou, Harris Papadopoulos and Alexander Gammerman, IEEE Transactions on Information Technology in Biomedicine 15(1), 93 (2011). Web of Science, Google Scholar
Antonis Lambrouet al., Assessment of stroke risk based on morphological ultrasound image analysis with conformal prediction, Artificial Intelligence Applications and Innovations – 6th IFIP WG 12.5 International Conference (AIAI 2010) (2010) pp. 146–153. Google Scholar
M. Langsfeld, A. C. Gray-Weale and R. J. Lusby, Journal of Vascular Surgery 9(4), 548 (1989). Web of Science, Google Scholar
Thomas Melluishet al., Comparing the Bayes and Typicalness frameworks, Proceedings of the 12th European Conference on Machine Learning (ECML'01)2167, Lecture Notes in Computer Science (Springer, 2001) pp. 360–371. Google Scholar
Stavroula Gr. Mougiakakouet al., Ultrasound in Medicine & Biology 33(1), 26 (2007). Web of Science, Google Scholar
Andrew N. Nicolaideset al., Journal of Endovascular Surgery 3(2), 158 (1996). Web of Science, Google Scholar
Ilia Nouretdinovet al., Computational Learning Theory, Lecture Notes in Computer Science 2111, eds. David Helmbold and Bob Williamson (Springer, Berlin/Heidelberg, 2001) pp. 337–353. Google Scholar
Harris Papadopoulos, Tools in Artificial Intelligence, ed. Paula Fritzsche (I-Tech, Vienna, Austria, 2008) pp. 315–330, http://www.intechopen.com/download/pdf/pdfs_id/5294. Google Scholar
Harris Papadopoulos, Alex Gammerman and Volodya Vovk, Engineering Intelligent Systems 17(2-3), 115 (2009). Web of Science, Google Scholar
Harris Papadopoulos and Haris Haralambous, Neural Networks 24(8), 842 (2011). Web of Science, Google Scholar
Harris Papadopouloset al., Inductive confidence machines for regression, Proceedings of the 13th European Conference on Machine Learning (ECML'02)2430, Lecture Notes in Computer Science (Springer, 2002) pp. 345–356. Google Scholar
Harris Papadopoulos, Vladimir Vovk and Alex Gammerman, Journal of Artificial Intelligence Research 40, 815 (2011), http://dx.doi.org/10.1613/jair.3198. Web of Science, Google Scholar
Harris Papadopoulos, Volodya Vovk and Alex Gammerman, Qualified predictions for large data sets in the case of pattern recognition, Proceedings of the 2002 International Conference on Machine Learning and Applications (2002) pp. 159–163. Google Scholar
Harris Papadopoulos, Volodya Vovk and Alex Gammerman, Conformal prediction with neural networks, Proceedings of the 19th IEEE International Conference on Tools with Artificial Intelligence (ICTAI'07)2 (IEEE Computer Society, 2007) pp. 388–395. Google Scholar
Kostas Proedrouet al., Transductive confidence machines for pattern recognition, Proceedings of the 13th European Conference on Machine Learning (ECML'02)2430, Lecture Notes in Computer Science (Springer, 2002) pp. 381–390. Google Scholar
Craig Saunders, Alex Gammerman and Volodya Vovk, Transduction with confidence and credibility, Proceedings of the 16th International Joint Conference on Artificial Intelligence (Morgan Kaufmann, Los Altos, CA, 1999) pp. 722–726. Google Scholar
Volodya Vovk, Alex Gammerman and Craig Saunders, Machine-learning applications of algorithmic randomness, Proceedings of the Sixteenth International Conference on Machine Learning (Morgan Kaufmann, 1999) pp. 444–453. Google Scholar
Volodya Vovk , Alexander Gammerman and G. Shafer , Algorithmic Learning in a Random World ( Springer , New York , 2005 ) . Google Scholar
J. E. Wilhjelmet al., IEEE Transactions on Medical Imaging 17(6), 910 (1998). Web of Science, Google Scholar