Abstract
Segmentation of tissue components of atherosclerotic plaques in MRI is promising for improving future treatment strategies of cardiovascular diseases. Several methods have been proposed before with varying results. This study aimed to perform a structured comparison of various classifiers, training set sizes, and MR image sequences to determine the most promising strategy for methodology development. Five different classifiers (linear discriminant classifier (LDC), quadratic discriminant classifier (QDC), random forest (RF), and support vector classifiers with both a linear (SVM\(_{lin}\)) and radial basis function kernel (SVM\(_{rbf}\))) were evaluated. We used carotid MRI data from 124 symptomatic patients, scanned in 4 centres with 2 different MRI protocols (45 and 79 patients). Firstly, learning curves of accuracy as a function of increasing training data size showed stabilisation of performance after using \(\sim \)10–15 patients for training. Best results were found for LDC, QDC and RF. Intraplaque haemorrhage was most accurately classified in both protocols, and lowest accuracy was found for the lipid-rich necrotic core. Secondly, for LDC and RF it was shown that leaving out different MRI sequences usually negatively affects results for one or more classes. However, leaving out T2-weighted scans did not have a big impact. In conclusion, several classifiers obtain generally good results for classification of plaque components in MRI. Identification of intraplaque haemorrhage is the most promising, and lipid-rich necrotic core remains the most difficult.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
World Health Organisation: WHO global burden of disease 2000–2015 (2015)
Finn, A.V., Nakano, M., Narula, J., Kolodgie, F.D., Virmani, R.: Concept of vulnerable/unstable plaque. Arterioscler. Thromb. Vasc. Biol. 30(7), 1282–1292 (2010)
Paraskevas, K.I., Mikhailidis, D.P., Veith, F.J.: Comparison of the five 2011 guidelines for the treatment of carotid stenosis. J. Vasc. Surg. 55(5), 1504–1508 (2012)
Sanz, J., Fayad, Z.A.: Imaging of atherosclerotic cardiovascular disease. Nature 451(7181), 953–957 (2008)
Huibers, A., de Borst, G., Wan, S., Kennedy, F., Giannopoulos, A., Moll, F., Richards, T.: Non-invasive carotid artery imaging to identify the vulnerable plaque: current status and future goals. Eur. J. Vasc. Endovasc. Surg. 50(5), 563–572 (2015)
Yuan, C., Mitsumori, L.M., Ferguson, M.S., Polissar, N.L., Echelard, D., Ortiz, G., Small, R., Davies, J.W., Kerwin, W.S., Hatsukami, T.S.: In vivo accuracy of multispectral magnetic resonance imaging for identifying lipid-rich necrotic cores and intraplaque hemorrhage in advanced human carotid plaques. Circulation 104(17), 2051–2056 (2001)
Saam, T., Ferguson, M., Yarnykh, V., Takaya, N., Xu, D., Polissar, N., Hatsukami, T., Yuan, C.: Quantitative evaluation of carotid plaque composition by in vivo MRI. Arterioscler. Thromb. Vasc. Biol. 25(1), 234–239 (2005)
Gupta, A., Baradaran, H., Schweitzer, A.D., Kamel, H., Pandya, A., Delgado, D., Dunning, A., Mushlin, A.I., Sanelli, P.C.: Carotid plaque MRI and stroke risk. Stroke 44(11), 3071–3077 (2013)
Saam, T., Hetterich, H., Hoffmann, V., Yuan, C., Dichgans, M., Poppert, H., Koeppel, T., Hoffmann, U., Reiser, M.F., Bamberg, F.: Meta-analysis and systematic review of the predictive value of carotid plaque hemorrhage on cerebrovascular events by magnetic resonance imaging. J. Am. Coll. Cardiol. 62(12), 1081–1091 (2013)
Sun, J., Zhao, X.Q., Balu, N., Neradilek, M.B., Isquith, D.A., Yamada, K., Canton, G., Crouse, J.R., Anderson, T.J., Huston, J., OBrien, K., Hippe, D.S., Polissar, N.L., Yuan, C., Hatsukami, T.S.: Carotid plaque lipid content and fibrous cap status predict systemic CV outcomes: the MRI substudy in AIM-HIGH. JACC: Cardiovasc. Imaging 10(3), 241–249 (2017)
Liu, F., Xu, D., Ferguson, M.S., Chu, B., Saam, T., Takaya, N., Hatsukami, T.S., Yuan, C., Kerwin, W.S.: Automated in vivo segmentation of carotid plaque MRI with morphology-enhanced probability maps. Magn. Reson. Med. 55(3), 659–668 (2006)
Hofman, J., Branderhorst, W., ten Eikelder, H., Cappendijk, V., Heeneman, S., Kooi, M., Hilbers, P., ter Haar Romeny, B.: Quantification of atherosclerotic plaque components using in vivo MRI and supervised classifiers. Magn. Reson. Med. 55(4), 790–799 (2006)
van’t Klooster, R., Naggara, O., Marsico, R., Reiber, J., Meder, J.F., van der Geest, R., Touz, E., Oppenheim, C.: Automated versus manual in vivo segmentation of carotid plaque MRI. Am. J. Neuroradiol. 33, 1621–1627 (2012)
van Engelen, A., Niessen, W.J., Klein, S., Groen, H.C., Verhagen, H.J.M., Wentzel, J.J., van der Lugt, A., de Bruijne, M.: Atherosclerotic plaque component segmentation in combined carotid MRI and CTA data incorporating class label uncertainty. PLOS ONE 9(4), 1–14 (2014)
van Engelen, A., van Dijk, A., Truijman, M., van’t Klooster, R., van Opbroek, A., van der Lugt, A., Niessen, W., Kooi, M., de Bruijne, M.: Multi-center MRI carotid plaque component segmentation using feature normalization and transfer learning. IEEE Trans. Med. Imaging 34(6), 1294–1305 (2015)
Gao, S., van’t Klooster, R., van Wijk, D.F., Nederveen, A.J., Lelieveldt, B.P.F., van der Geest, R.J.: Repeatability of in vivo quantification of atherosclerotic carotid artery plaque components by supervised multispectral classification. Magn. Reson. Mater. Phys., Biol. Med. 28(6), 535–545 (2015)
Truijman, M., Kooi, M., van Dijk, A., de Rotte, A., van der Kolk, A., Liem, M., Schreuder, F., Boersma, E., Mess, W., van Oostenbrugge, R., Koudstaal, P., Kappelle, L., Nederkoorn, P., Nederveen, A., Hendrikse, J., van der Steen, A., Daemen, M., van der Lugt, A.: Plaque At RISK (PARISK): prospective multicenter study to improve diagnosis of high-risk carotid plaques. Int. J. Stroke 9, 747–754 (2013)
van’t Klooster, R., Staring, M., Klein, S., Kwee, R.M., Kooi, M.E., Reiber, J.H.C., Lelieveldt, B.P.F., van der Geest, R.J.: Automated registration of multispectral MR vessel wall images of the carotid artery. Med. Phys. 40(12), 121904 (2013)
van’t Klooster, R., de Koning, P.J., Dehnavi, R.A., Tamsma, J.T., de Roos, A., Reiber, J.H., van der Geest, R.J.: Automatic lumen and outer wall segmentation of the carotid artery using deformable three-dimensional models in MR angiography and vessel wall images. J. Magn. Reson. Imaging 35(1), 156–165 (2012)
Cai, J., Hatsukami, T.S., Ferguson, M.S., Kerwin, W.S., Saam, T., Chu, B., Takaya, N., Polissar, N.L., Yuan, C.: In vivo quantitative measurement of intact fibrous cap and lipid-rich necrotic core size in atherosclerotic carotid plaque: Comparison of high-resolution, contrast-enhanced magnetic resonance imaging and histology. Circulation 112(22), 3437–3444 (2005)
Cappendijk, V.C., Heeneman, S., Kessels, A.G., Cleutjens, K.B., Schurink, G.W.H., Welten, R.J., Mess, W.H., van Suylen, R.J., Leiner, T., Daemen, M.J., van Engelshoven, J.M., Kooi, M.E.: Comparison of single-sequence T1w TFE MRI with multisequence MRI for the quantification of lipid-rich necrotic core in atherosclerotic plaque. J. Magn. Reson. Imaging 27(6), 1347–1355 (2008)
Kwee, R.M., van Engelshoven, J.M., Mess, W.H., ter Berg, J.W., Schreuder, F.H., Franke, C.L., Korten, A.G., Meems, B.J., van Oostenbrugge, R.J., Wildberger, J.E., Kooi, M.E.: Reproducibility of fibrous cap status assessment of carotid artery plaques by contrast-enhanced MRI. Stroke 40(9), 3017–3021 (2009)
Hastie, T., Tibshirani, R., Friedman, J.H.: The Elements of Statistical Learning, Corrected edn. Springer, New York (2003)
Criminisi, A., Shotton, J., Konukoglu, E.: Decision Forests: A Unified Framework for Classification, Regression, Density Estimation, Manifold Learning and Semi-Supervised Learning. NOW Publishers, Breda (2012)
Duin, R., Juszczak, P., Paclik, P., Pekalska, E., de Ridder, D., Tax, D., Verzakov, S.: PRTools4.1, A Matlab Toolbox for Pattern Recognition. Delft University of Technology (2007)
Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2, 27:1–27:27 (2011)
Liaw, A., Wiener, M.: Classification and regression by randomforest. R News 2(3), 18–22 (2002)
Tustison, N.J., Avants, B.B., Cook, P.A., Zheng, Y., Egan, A., Yushkevich, P.A., Gee, J.C.: N4ITK: improved N3 bias correction. IEEE Trans. Med. Imaging 29(6), 1310–1320 (2010)
Acknowledgments
This research has been supported by an EPSRC Technology Strategy Board CR&D Grant (EP/L505304/1). The PARISK study was performed within the framework of the Center for Translational Molecular Medicine (www.ctmm.nl), project PARISK (Plaque At RISK; grant 01C-202) and supported by the Dutch Heart Foundation. This research was also partly funded by the Netherlands Organisation for Scientific Research (NWO).
The Division of Imaging Sciences also receives support from the Centre of Excellence in Medical Engineering (funded by the Welcome Trust and EPSRC; grant number WT 088641/Z/09/Z) and the Department of Health through the National Institute for Health Research (NIHR) Biomedical Research Centre award to Guy’s and St Thomas’ NHS Foundation Trust in partnership with King’s College London, and by the NIHR Healthcare Technology Co-operative for Cardiovascular Disease at Guys and St Thomas NHS Foundation Trust. The views expressed are those of the author(s) and not necessarily those of the NHS, the NIHR or the Department of Health.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
van Engelen, A. et al. (2017). Evaluating Classifiers for Atherosclerotic Plaque Component Segmentation in MRI. In: Valdés Hernández, M., González-Castro, V. (eds) Medical Image Understanding and Analysis. MIUA 2017. Communications in Computer and Information Science, vol 723. Springer, Cham. https://doi.org/10.1007/978-3-319-60964-5_14
Download citation
DOI: https://doi.org/10.1007/978-3-319-60964-5_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-60963-8
Online ISBN: 978-3-319-60964-5
eBook Packages: Computer ScienceComputer Science (R0)