Abstract
Pixel classifiers are often adopted in pattern recognition as a suitable method for image segmentation. A common approach to the performance evaluation of classifier systems is based on the measurement of the classification errors and, at the same time, on the computational time. In general, multiclassifiers have proven to be more precise in the classification in many applications, but at the cost of a higher computational load. This paper analyzes different classifiers and proposes an evaluation of the classifiers in the case of semi-automatic processes with human interaction. Medical imaging is a typical application, where automatic or semi-automatic segmentation can be a valuable support to the diagnosis. The paper focuses on the segmentation of cardiac images of fruit flies (genetic model for analyzing human heart’s diseases). Analysis is based on M-modes, that are gray-level images derived from mono-dimensional projections of the video frames on a line. Segmentation of the M-mode images is provided by classifiers and integrated in a multiclassifier. A neural network classifier, a Bayesian classifier, and a classifier based on hidden Markov chains are joined by means of a Behavior Knowledge Space fusion rule. The comparative evaluation is discussed in terms of both accuracy and required time, in which the time to correct the classifier errors by means of human intervention is also taken into account.
Similar content being viewed by others
Notes
The term “end-systole” identifies the moment in which the heart has its minimum opening, whereas the term “end-diastole” identifies the moment with the maximum opening.
References
Paternostro G, Vignola C, Bartsch DU, Omens JH, McCulloch AD, Reed JC (2001) Age-associated cardiac dysfunction in Drosophila melanogaster. Circ Res 88:1053–1058
Lakatta EG (2001) Heart aging: a fly in the ointment? Circ Res 88:984–986
Frangi AF, Niessen WJ, Viergever MA (2001) Three-dimensional modeling for functional analysis of cardiac images, a review. IEEE Trans Med Imaging 20(1):2–25
McEachen JK II, Duncan JS (1997) Shape-based tracking of left ventricular wall motion. IEEE Trans Med Imaging 26(3):270–283
McVeigh ER (1996) MRI of myocardial function: motion tracking techniques. Magn Reson Imaging 14(2):137–150
Nahrendorf M, Hiller K-H, Hu K, Ertl G, Haase A, Bauer WR (2003) Cardiac magnetic resonance imaging in small animal models of human heart failure. Med Image Anal 7(3):369–375
Waiter GD, McKiddie FI, Redpath TW, Semple SIK, Trent RJ (1999) Determination of normal regional left ventricular function from cine-MR images using a semi-automated edge detection method. Magn Reson Imaging 17(1):99–107
Amini AA, Yasheng C, Elayyadi M, Radeva P (2001) Tag surface reconstruction and tracking of myocardial beads from SPAMM-MRI with parametric B-spline surfaces. IEEE Trans Med Imaging 20(2):94–103
Denney TS Jr (1999) Estimation and detection of myocardial tags in MR image without user-defined myocardial contours. IEEE Trans Med Imaging 18(4):330–344
Haber I, Metaxas DN, Axel L (2000) Three-dimensional motion reconstruction and analysis of the right ventricle using tagged MRI. Med Image Anal 4(4):335–355
Osman NF, McVeigh ER, Prince JL (2000) Imaging heart motion using harmonic phase MRI. IEEE Trans Med Imaging 19(3):186–202
Klein GJ, Huesman RH (2002) Four-dimensional processing of deformable cardiac PET data. Med Image Anal 6(1):29–46
Debreuve E, Barlaud M, Aubert G, Laurette I, Darcourt J (2001) Space–time segmentation using level set active contours applied to myocardial gated SPECT. IEEE Trans Med Imaging 20(7):643–659
Bosch JG, Mitchell SC, Lelieveldt BPF, Nijland F, Kamp O, Sonka M, Reiber JHC (2002) Automatic segmentation of echocardiographic sequences by active appearance motion models. IEEE Trans Med Imaging 21(11):1374–1383
Gerard O, Billon AC, Rouet JM, Jacob M, Fradkin M, Allouche C (2002) Efficient model-based quantification of left ventricular function in 3-D echocardiography. IEEE Trans Med Imaging 21(9):1059–1068
Jacob G, Noble JA, Behrenbruch C, Kelion AD, Banning AP (2002) A shape-space-based approach to tracking myocardial borders and quantifying regional left-ventricular function applied in echocardiography. IEEE Trans Med Imaging 21(3):226–238
Montagnat J, Sermesant M, Delingette H, Malandain G, Ayache N (2003) Anisotropic filtering for model-based segmentation of 4D cylindrical echocardiographic images, Pattern Recognit Lett 24(4–5):815–828
Clarysse P, Friboulet D, Magnin IE (1997) Tracking geometrical descriptors on 3-D deformable surfaces: application to the left-ventricular surface of the heart. IEEE Trans Med Imaging 16(4):392–404
Herment A, Mousseaux E, Dumée P, Decesare A (1998) Automatic detection of left ventricular borders on electron beam CT sequential cardiac images using an adaptive algorithm, Comput Med Imaging Graph 22(4):291–299
Kass M, Witkin A, Terzopolous D (1988) Snakes: active contour models. Int J Comput Vis 1:321–331
Staib LH, Duncan JS (1992) Boundary finding with parametrically deformable models. IEEE Trans Patt Anal Mach Intell 14(11):1061–1075
Chalana V, Linker DT, Haynor DR, Yongmin K (1996) A multiple active contour model for cardiac boundary detection on echocardiographic sequences. IEEE Trans Med Imaging 15(3):290–298
Yuille AL, Hallinan P (1992) Deformable templates. In: Blake A, Yuille AL (eds) Active vision. MIT press, Cambridge, pp 20–38
Cootes TF, Taylor CJ, Cooper DH, Graham P (1992) Training models of shape from sets of examples. In: Proceedings of British machine vision conference, pp 9–18
García-Fernández MA, Zamorano JL, Azevedo J (1997) Doppler tissue imaging. McGraw-Hill, New York
Malpica N, Santos A, Pérez E, García-Fernández MA, Desco M (2003) A snake model for anatomic M-mode tracking in echocardiography. In: Loncaric S, Neri A, Babic H (eds) Proceedings of 3rd international symposium on image and signal processing and analysis 2, pp 722–726
Mele D, Pedini I, Alboni P, Levine RA (1998) Anatomic M-mode: a new technique for quantitative assessment of left ventricular size and function. Am J Cardiol 81:82G–85G
Haralick RM, Shapiro LG (1985) Image segmentation techniques. Comp Vis Graph Image Process 29:100–132
Pal NR, Pal SK (1993) A review of image segmentation techniques. Pattern Recognit 26(9):1277–1294
Tobias OJ, Seara R (2002) Image segmentation by histogram thresholding using fuzzy sets. IEEE Trans Image Process 11(12):1457–1465
Manay S, Yezzi A (2003) Anti-geometric diffusion for adaptive thresholding and fast segmentation. IEEE Trans Image Process 12(11):1310–1323
Roli F, Giacinto G (2002) Design of multiple classifier systems. In: Bunke H, Kandel A (eds) Hybrid methods in pattern recognition. World Scientific Publishing, Singapore
Kittler J, Hater M, Duin RPW (1996) On combining classifiers. In: Proceedings of 13th international conference on pattern recognition, vol 2, pp 897–901
Woods K, Kegelmeyer WP Jr, Bowyer K (1997) Combination of multiple classifiers using local accuracy estimates. IEEE Trans Pattern Anal Mach Intell 19(4):405–410
Plessis B, Sicsu A, Heutte L, Menu E, Lecolinet E, Debon O, Moreau J-V (1993) A multi-classifier combination strategy for the recognition of handwritten cursive words. In: Proceedings of 2nd international conference on document analysis and recognition, pp 642–645
Dasarathy BV, McCullough CL (1998) Intelligent multi-classifier fusion for decision making in ballistic missile defense applications. In: Proceedings of IEEE conference on decision and control, vol 1, pp 233–238
Briem GJ, Benediktsson JA, Sveinsson JR (2001) Boosting, bagging, and consensus based classification of multisource remote sensing data. In: Josef Kittler, Fabio Roli (eds) Proceedings of 2nd international workshop on multiple classifier systems (LNCS 2096). Springer, Berlin Heidelberg New York, pp 279–288
Jain AK, Prabhakar S, Hong L (1999) A multichannel approach to fingerprint classification. IEEE Trans Pattern Anal Mach Intell 21(4):348–358
Chiou GI, Hwang J-N (1994) Image sequence classification using a neural network based active contour model and a hidden Markov model. In: Proceedings of international conference on image processing, vol 3, pp 926–930
Shah S, Sastry PS (2004) Fingerprint classification using a feedback-based line detector. IEEE Trans Syst Man Cybern B 34(1):85–94
Zhang X-P (2001) Thresholding neural network for adaptive noise reduction. IEEE Trans Neural Netw 12(3):567–584
Komo D, Chang C-I, Ko H (1994) Neural network technology for stock market index prediction. In: Proceedings of international symposium on speech, image processing and neural networks, vol 2, pp 543–546
Kuntimad G, Ranganath HS (1999) Perfect image segmentation using pulse coupled neural networks. IEEE Trans Neural Netw 10(3):591–598
Rae R, Ritter HJ (1998) Recognition of human head orientation based on artificial neural networks. IEEE Trans Neural Netw 9(2):257–265
Anthony M, Bartlett PL (1999) Neural network learning: theoretical foundation. Cambridge University Press, Cambridge
Lei T, Udupa JK (2003) Performance evaluation of finite normal mixture model-based image segmentation techniques. IEEE Trans Image Process 12(10):1153–1169
Acton ST, Mukherjee DP (2000) Scale space classification using area morphology. IEEE Trans Image Process 9(4):623–635
Giordana N, Pieczynski W (1997) Estimation of generalized multisensor hidden Markov chains and unsupervised image segmentation. IEEE Trans Pattern Anal Mach Intell 19(5):465–475
Pieczynski W (2003) Pairwise Markow chains. IEEE Trans Pattern Anal Mach Intell 25(5):634–639
Marroquin JL, Santana EA, Botello S (2003) Hidden Markov measure field models for image segmentation. IEEE Trans Pattern Anal Mach Intell 25(11):1380–1387
Cai J, Liu Z-Q (2001) Hidden Markov models with spectral features for 2D shape recognition. IEEE Trans Pattern Anal Mach Intell 23(12):1454–1458
Chien J-T (1999) Online hierarchical transformation of hidden Markov models for speech recognition. IEEE Trans Speech Audio Proc 7(6):656–667
Bao P, Zhang L (2003) Noise reduction for magnetic resonance images via adaptive multiscale products thresholding. IEEE Trans Med Imaging 22(9):1089–1099
Fjortoft R, Delignon Y, Pieczynski W, Sigelle M, Tupin F (2003) Unsupervised classification of radar images using hidden Markov chains and hidden Markov random fields. IEEE Trans Geos Rem Sensing 41(3):675–686
Ephraim Y, Merhav N (2002) Hidden Markov processes. IEEE Trans Inform Theory 48(6):1518–1569
Forney GD Jr (1973) The Viterbi algorithm. Proc IEEE 61:268–278
Viterbi AJ (1967) Error bounds for convolutional codes and an asymptotically optimum decoding algorithm. IEEE Trans Inform Theory IT-13:260–269
Xu L, Krzyzak A, Suen CY (1992) Methods for combining multiple classifiers and their applications to handwriting recognition. IEEE Trans Syst Man Cybern 22(3):418–435
Huang YS, Suen CY (1995) A method of combining multiple experts for the recognition of unconstrained handwritten numerals. IEEE Trans Pattern Anal Mach Intell 17(1):90–94
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Bertelli, L., Cucchiara, R., Paternostro, G. et al. A semi-automatic system for segmentation of cardiac M-mode images. Pattern Anal Applic 9, 293–306 (2006). https://doi.org/10.1007/s10044-006-0034-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-006-0034-x