A Selection and Reduction Approach for the Optimization of Ultrasound Carotid Artery Images Segmentation

  • Samanta Rosati
  • Gabriella Balestra
  • Filippo MolinariEmail author
  • U. Rajendra Acharya
  • Jasjit S. Suri
Part of the Intelligent Systems Reference Library book series (ISRL, volume 56)


The segmentation of the carotid artery wall is an important aid to sonographers when measuring intima-media thickness (IMT). Automated and completely user-independent segmentation techniques are gaining increasing importance, because they avoid the bias coming from human interactions. However, automated techniques still underperform semi-automated IMT measurement methods. Automated techniques cannot reproduce human expertise in selecting the optimal point where IMT should be measured. Hence, superior intelligence must be embedded into automated techniques in order to overcome the performance limitations. A possible solution is to extract more information from the image, which could be obtained by an accurate analysis of the image at pixel level. In this study, we applied a feature selection and reduction approach to ultrasound carotid images, and measured 141 features for each image pixel and supposed that a pixel could belong to one of three classes: artery lumen, intima or media layer, or the adventitia layer. Among several approaches that are available for dimensional reduction, we chose to test three based on the Rough-Set Theory (RST): the QuickReduct Algorithm (QRA), the Entropy-Based Algorithm (EBR) and the Improved QuickReduct Algorithm (IQRA). QRA achieved the best performance and correctly classified 97.5 % of the pixels on a reduced testing image dataset and about 91.5 % for a large validation dataset. On average, QRA reduced the complexity of the system from 141 to 8 or 9 features. This result could represent a pilot study for developing an intelligent pre-classifier to improve the image segmentation performance of automated techniques in carotid ultrasound imaging.


Ultrasound imaging Intima-media thickness Atherosclerosis Segmentation Feature extraction Feature selection Quickreduct algorithm Entropy Rough set Artificial neural networks 


  1. 1.
    Amadasun M, King R (1989) Textural features corresponding to textural properties. IEEE Trans Syst Man Cyb 19(5):1264–1273CrossRefGoogle Scholar
  2. 2.
    Badimon JJ, Ibanez B, Cimmino G (2009) Genesis and dynamics of atherosclerotic lesions: implications for early detection. Cerebrovasc Dis 27(1):38–47CrossRefGoogle Scholar
  3. 3.
    Barnett H et al (1991) Beneficial effect of carotid endarterectomy in symptomatic patients with high-grade carotid stenosis. North American symptomatic carotid endarterectomy trial collaborators. N Engl J Med 325:445–453CrossRefGoogle Scholar
  4. 4.
    Chen Y, Miao D, Wang R (2010) A rough set approach to feature selection based on ant colony optimization. Pattern Recogn Lett 31:226–233CrossRefGoogle Scholar
  5. 5.
    Chen Y, Miao D, Wang R, Wu K (2011) A rough set approach to feature selection based on power set tree. Knowl-Based Syst 24:275–281CrossRefGoogle Scholar
  6. 6.
    Conners RW, Harlow CA (1980) A Theoretical comparison of texture algorithms. IEEE Trans Pattern Anal Mach Intell 2:204–222CrossRefzbMATHGoogle Scholar
  7. 7.
    de Groot E, van Leuven SI, Duivenvoorden R, Meuwese MC, Akdim F, Bots ML, Kastelein JJ (2008) Measurement of carotid intima-media thickness to assess progression and regression of atherosclerosis. Nat Clin Pract Cardiovasc Med 5:280–288CrossRefGoogle Scholar
  8. 8.
    Faita F, Gemignani V, Bianchini E, Giannarelli C, Ghiadoni L, Demi M (2008) Real-time measurement system for evaluation of the carotid intima-media thickness with a robust edge operator. J Ultrasound Med 27:1353–1361Google Scholar
  9. 9.
    Feng L, Wang GY, Li XX (2010) Knowledge acquisition in vague objective information systems based on rough sets. Expert Syst 27:129–142CrossRefGoogle Scholar
  10. 10.
    Fisher M, Martin A, Cosgrove M, Norris JW (1993) The NASCET-ACAS plaque project. North American symptomatic carotid endarterectomy trial. Asymptomatic carotid atherosclerosis study. Stroke 24:I24–I25CrossRefGoogle Scholar
  11. 11.
    Greco S, Matarazzo B, Slowinski R (2001) Rough sets theory for multicriteria decision analysis. Eur J Oper Res 129:1–47MathSciNetCrossRefzbMATHGoogle Scholar
  12. 12.
    Jain AK, Duin RPW, Mao J (2000) Statistical pattern recognition: a review. IEEE Trans Pattern Anal Mach Intell 22:4–37CrossRefGoogle Scholar
  13. 13.
    Jensen R, Shen Q (2001) A rough set-aided system for sorting WWW bookmarks. Web Intell: Res Dev 2198:95–105Google Scholar
  14. 14.
    Jensen R, Shen Q (2008) Computational intelligence and feature selection: rough and fuzzy approaches. Wiley, HobokenCrossRefGoogle Scholar
  15. 15.
    Kuncheva LI (2004) Combining pattern classifiers: methods and algorithms. Wiley, HobokenCrossRefGoogle Scholar
  16. 16.
    Liu H, Yu L (2005) Toward integrating feature selection algorithms for classification and clustering. IEEE Trans Knowl Data Eng 17:491–502CrossRefGoogle Scholar
  17. 17.
    Małyszko D, Stepaniuk J (2010) Adaptive multilevel rough entropy evolutionary thresholding. Inform Sci 180:1138–1158MathSciNetCrossRefGoogle Scholar
  18. 18.
    Matsumoto Y, Watada J (2009) Knowledge acquisition from time series data through rough sets analysis. IJICIC 5:4885–4897Google Scholar
  19. 19.
    Molinari F, Liboni W, Giustetto P, Badalamenti S, Suri JS (2009) Automatic computer-based tracings (ACT) in longitudinal 2-D ultrasound images using different scanners. J Mech Med Biol 9:481–505CrossRefGoogle Scholar
  20. 20.
    Molinari F, Zeng G, Suri JS (2010) A state of the art review on intima-media thickness (IMT) measurement and wall segmentation techniques for carotid ultrasound. Comput Methods Programs Biomed 100:201–221CrossRefGoogle Scholar
  21. 21.
    Molinari F, Zeng G, Suri J (2010) Inter-greedy technique for fusion of different segmentation strategies leading to high-performance carotid IMT measurement in ultrasound images. J Med Syst 35(5):905–919CrossRefGoogle Scholar
  22. 22.
    Molinari F, Zeng G, Suri JS (2010) Carotid wall segmentation and IMT measurement in longitudinal ultrasound images using morphological approach. Paper presented at the 2010 IEEE international symposium on biomedical imaging: from Nano to Macro, Rotterdam, The Netherlands, April 2010, pp 14–17Google Scholar
  23. 23.
    Molinari F, Acharya UR, Zeng G, Meiburger KM, Suri JS (2011) Completely automated robust edge snapper for carotid ultrasound IMT measurement on a multi-institutional database of 300 images. Med Biol Eng Comput (in press)Google Scholar
  24. 24.
    Molinari F, Meiburger KM, Zeng G, Nicolaides A, Suri JS (2011) CAUDLES-EF: carotid automated ultrasound double line extraction system using edge flow. J Digit Imaging 24(6):1059–1077CrossRefGoogle Scholar
  25. 25.
    Molinari F, Liboni W, Pantziaris M, Suri JS (2011) CALSFOAM-completed automated local statistics based first order absolute moment” for carotid wall recognition, segmentation and IMT measurement: validation and bench-marking on a 300 patient database. Int Angiol 30:227–241Google Scholar
  26. 26.
    Moradi H, Grzymala-Busse JW, Roberts JA (1998) Entropy of english text: experiments with humans and a machine learning system based on rough sets. Inf Sci 104:31–47CrossRefGoogle Scholar
  27. 27.
    Naqvi TZ (2006) Ultrasound vascular screening for cardiovascular risk assessment. Why, when and how? Minerva Cardioangiol 54:53–67Google Scholar
  28. 28.
    Pawlak Z (1982) Rough Sets. Int J Comput Inform Sci 11:341–356MathSciNetCrossRefzbMATHGoogle Scholar
  29. 29.
    Pawlak Z, Sowinski R (1994) Rough set approach to multi-attribute decision analysis. Eur J Oper Res 72:443–459CrossRefzbMATHGoogle Scholar
  30. 30.
    Pignoli P, Longo T (1988) Evaluation of atherosclerosis with B-mode ultrasound imaging. J Nucl Med Allied Sci 32:166–173Google Scholar
  31. 31.
    Poredos P (2004) Intima-media thickness: indicator of cardiovascular risk and measure of the extent of atherosclerosis. Vasc Med 9:46–54CrossRefGoogle Scholar
  32. 32.
    Prasad PS, Rao CR (2009) IQuickReduct: an improvement to quick reduct algorithm. Lect Notes Comput Sci 5908:152–159CrossRefGoogle Scholar
  33. 33.
    Roquer J, Segura T, Serena J, Castillo J (2009) Endothelial dysfunction, vascular disease and stroke: the ARTICO study. Cerebrovasc Dis 27:25–37CrossRefGoogle Scholar
  34. 34.
    Rothwell PM, Warlow CP (1999) Prediction of benefit from carotid endarterectomy in individual patients: a risk-modelling study. European carotid surgery trialists’ collaborative group. Lancet 353:2105–2110CrossRefGoogle Scholar
  35. 35.
    Rothwell PM, Gibson RJ, Slattery J, Warlow CP (1994) Prognostic value and reproducibility of measurements of carotid stenosis. A comparison of three methods on 1001 angiograms. European carotid surgery trialists’ collaborative group. Stroke 25:2440–2444CrossRefGoogle Scholar
  36. 36.
    Schargrodsky H, Hernandez–Hernandez R, Champagne BM, Silva H, Vinueza R, Silva Aycaguer LC, Touboul PJ, Boissonnet CP, Escobedo J, Pellegrini F, Macchia A, Wilson E (2008) CARMELA: assessment of cardiovascular risk in seven Latin American cities. Am J Med 121:58–65Google Scholar
  37. 37.
    Shen Q, Chouchoulas A (2000) A modular approach to generating fuzzy rules with reduced attributes for the monitoring of complex systems. Eng Appl Artif Intel 13:263–278CrossRefGoogle Scholar
  38. 38.
    Su CT, Yang CH (2008) Feature selection for the SVM: an application to hypertension diagnosis. Expert Syst Appl 34:754–763CrossRefGoogle Scholar
  39. 39.
    Swiniarski RW, Skowron A (2003) Rough set methods in feature selection and recognition. Pattern Recogn Lett 24:833–849CrossRefzbMATHGoogle Scholar
  40. 40.
    Tan JH, Ng EYK, Acharya UR, Chee C (2010) Study of normal ocular thermogram using textural parameters. Infrared Phys Tech 53:120–126CrossRefGoogle Scholar
  41. 41.
    Thangavel K, Pethalakshmi A (2009) Dimensionality reduction based on rough set theory: a review. Appl Soft Comput J 9:1–12CrossRefGoogle Scholar
  42. 42.
    Touboul PJ, Hernandez–Hernandez R, Kucukoglu S, Woo KS, Vicaut E, Labreuche J, Migom C, Silva H, Vinueza R (2007) Carotid artery intima media thickness, plaque and Framingham cardiovascular score in Asia, Africa/Middle East and Latin America: the PARC-AALA study. Int J Cardiovasc Imaging 23:557–567CrossRefGoogle Scholar
  43. 43.
    Tsumoto S (1998) Automated extraction of medical expert system rules from clinical databases based on rough set theory. Inform Sciences 112:67–84CrossRefGoogle Scholar
  44. 44.
    World Health Organization (2011) Cardiovascular disease. W. H. Organization. Accessed June 2011
  45. 45.
    Ziarko W (1993) Variable precision rough set model. J Comput Syst Sci 49:39–59MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  • Samanta Rosati
    • 1
  • Gabriella Balestra
    • 1
  • Filippo Molinari
    • 1
    Email author
  • U. Rajendra Acharya
    • 2
    • 3
  • Jasjit S. Suri
    • 4
    • 5
  1. 1.Biolab, Department of Electronics and TelecommunicationsPolitecnico di TorinoTorinoItaly
  2. 2.Department of ECENgee Ann PolytechnicSingaporeSingapore
  3. 3.Faculty of Engineering, Department of Biomedical EngineeringUniversity of MalayaKuala LumpurMalaysia
  4. 4.Global Biomedical Technologies, IncRosevilleUSA
  5. 5.Biomedical Engineering DepartmentIdaho State UniversityPocatelloUSA

Personalised recommendations