Liver Lesion Extraction with Fuzzy Thresholding in Contrast Enhanced Ultrasound Images
In this paper, we present a new segmentation approach
for focal liver lesions in contrast enhanced ultrasound imaging. This
approach, based on a two-cluster Fuzzy C-Means methodology,
considers type-II fuzzy sets to handle uncertainty due to the image
modality (presence of speckle noise, low contrast, etc.), and to
calculate the optimum inter-cluster threshold. Fine boundaries are
detected by a local recursive merging of ambiguous pixels. The
method has been tested on a representative database. Compared to
both Otsu and type-I Fuzzy C-Means techniques, the proposed
method significantly reduces the segmentation errors.
[1] H. Becher and P. Burns, “A Handbook of Contrast Echocardiography,”
Springer: Heidelberg, 2000.
[2] E. Quaia, A. Baert, and K. Sartot, “Contrast Media in Ultrasonography:
Basic Principles and Clinical Applications,” Springer, 2006.
[3] A. Bouakaz, N. de Jong, and C. Cachard, “Standard Properties of
Ultrasound Contrast Agents,” Ultrasound Med Biol 24:469-472, 1998.
[4] T. Albrecht, et al., “Guidelines for the Use of Contrast Agents in
Ultrasound,” Ultraschall Med. 25(4), pp.249–256, 2004.
[5] J. Shan, “A Fully Automatic Segmentation Method for Breast
Ultrasound Images,” PhD thesis, Utah State University, 2011.
[6] M.S. Yang, “A Survey of Fuzzy Clustering”, Math. Comput. Modelling
18, 1–16, 1993.C. J. Kaufman, Rocky Mountain Research Lab., Boulder,
CO, private communication, 1995.
[7] Q. Williams and J. Noble, “A Spatio-temporal Analysis of Contrast
Ultrasound Image Sequences for Assessment of Tissue Perfusion,”
MICCAI 2004:899-906, 2004.
[8] R. Prevost, B. Mory, J.-M. Correas, L. D. Cohen, and R. Ardon,
“Kidney Detection and Real-time Segmentation in 3D Contrastenhanced
Ultrasound Images,” In Proceedings of IEEE ISBI, pages
1559-1562, 2012.
[9] A. Albouy-Kissi, S. Cormier, and F. Tranquart, “Perfusion
Quantification of Contrast-enhanced Ultrasound Images Based on
Coherence Enhancing Diffusion and Competitive Clustering,” ICIP
2012: 2321-2324. 2012.
[10] A. Hassanien, G. Schaefre, and H. Al-Qahri, “Prostate Boundary
Detection in Ultrasounds Images based on Type-II Fuzzy Sets and
Modified Fuzzy C-Means,” Soft Computing in Industrial Applications,
Advances in Soft Computing, 2010, Volume 75/2010, pp. 187-195, 2010.
[11] H. Li, and M. Gupta, “Fuzzy logic and Intelligent systems.” Kluwer
Academic Publishers, 1995.
[12] P. Maji and S. Pal. “Maximum Class Separability for Rough-Fuzzy CMeans
Based Brain MR Image Segmentation,” T. Rough Sets, Vol.9,
pp.114-134, 2008.
[13] H. Tizhoosh, “Image Thresholding Using Type II Fuzzy Sets,” Pattern
Recognition. 38(12), 2363–2372, 2005.
[14] J. Mendel, R. John, “Type-2 Fuzzy Sets Made Simple,” IEEE Trans.
Fuzzy Syst. 10 (2), 117–127, 2002.
[15] N. Sladoje, J. Lindbald, and I. Nyström, “Defuzzification of Discrete
Objects by Optimizing Area and Perimeter Similarity,” In: Kittler, J.,
Petrou, M., Nixon, M. (eds.) Proc. of 17th International Conference on
Pattern Recognition (ICPR 2004), Cambridge, UK, vol. 3, pp. 526–529.
IEEE Comp. Society, Los Alamitos, 2004.
[16] N. Boujemaa, G. Stamon, J. Lemoine, and E. Petit. “Fuzzy Ventricular
Endocardium Detection with Gradual Focusing Decision,” 14th Annual
International Conference of the IEEE Engineering in Medicine and
Biology Society, Vol. 14, 1992.
[17] M. Grand-Brochier, A. Vacavant, G. Cerutti, K. Bianchi, and L. Tougne,
“Comparative Study of Segmentation Methods for Tree Leaves
Extraction,” In ACM ICVS 2013, Workshop: VIGTA, Saint Petersburg,
Russia, 2013.
[18] T. Chua and W. Tan, “Interval Type-2 Fuzzy System for ECG
Arrhythmic Classification,” Fuzzy Systems in Bioinformatics and
Computational Biology, Studies in Fuzziness and Soft Computing.
Volume 242, pp 297-314, 2009.
[19] N. Otsu, "A Threshold Selection Method from Gray–level Histograms,"
IEEE Trans. Sys., Man., Cyber. 9(1): 62–66.
doi:10.1109/TSMC.1979.4310076, 1979.
[1] H. Becher and P. Burns, “A Handbook of Contrast Echocardiography,”
Springer: Heidelberg, 2000.
[2] E. Quaia, A. Baert, and K. Sartot, “Contrast Media in Ultrasonography:
Basic Principles and Clinical Applications,” Springer, 2006.
[3] A. Bouakaz, N. de Jong, and C. Cachard, “Standard Properties of
Ultrasound Contrast Agents,” Ultrasound Med Biol 24:469-472, 1998.
[4] T. Albrecht, et al., “Guidelines for the Use of Contrast Agents in
Ultrasound,” Ultraschall Med. 25(4), pp.249–256, 2004.
[5] J. Shan, “A Fully Automatic Segmentation Method for Breast
Ultrasound Images,” PhD thesis, Utah State University, 2011.
[6] M.S. Yang, “A Survey of Fuzzy Clustering”, Math. Comput. Modelling
18, 1–16, 1993.C. J. Kaufman, Rocky Mountain Research Lab., Boulder,
CO, private communication, 1995.
[7] Q. Williams and J. Noble, “A Spatio-temporal Analysis of Contrast
Ultrasound Image Sequences for Assessment of Tissue Perfusion,”
MICCAI 2004:899-906, 2004.
[8] R. Prevost, B. Mory, J.-M. Correas, L. D. Cohen, and R. Ardon,
“Kidney Detection and Real-time Segmentation in 3D Contrastenhanced
Ultrasound Images,” In Proceedings of IEEE ISBI, pages
1559-1562, 2012.
[9] A. Albouy-Kissi, S. Cormier, and F. Tranquart, “Perfusion
Quantification of Contrast-enhanced Ultrasound Images Based on
Coherence Enhancing Diffusion and Competitive Clustering,” ICIP
2012: 2321-2324. 2012.
[10] A. Hassanien, G. Schaefre, and H. Al-Qahri, “Prostate Boundary
Detection in Ultrasounds Images based on Type-II Fuzzy Sets and
Modified Fuzzy C-Means,” Soft Computing in Industrial Applications,
Advances in Soft Computing, 2010, Volume 75/2010, pp. 187-195, 2010.
[11] H. Li, and M. Gupta, “Fuzzy logic and Intelligent systems.” Kluwer
Academic Publishers, 1995.
[12] P. Maji and S. Pal. “Maximum Class Separability for Rough-Fuzzy CMeans
Based Brain MR Image Segmentation,” T. Rough Sets, Vol.9,
pp.114-134, 2008.
[13] H. Tizhoosh, “Image Thresholding Using Type II Fuzzy Sets,” Pattern
Recognition. 38(12), 2363–2372, 2005.
[14] J. Mendel, R. John, “Type-2 Fuzzy Sets Made Simple,” IEEE Trans.
Fuzzy Syst. 10 (2), 117–127, 2002.
[15] N. Sladoje, J. Lindbald, and I. Nyström, “Defuzzification of Discrete
Objects by Optimizing Area and Perimeter Similarity,” In: Kittler, J.,
Petrou, M., Nixon, M. (eds.) Proc. of 17th International Conference on
Pattern Recognition (ICPR 2004), Cambridge, UK, vol. 3, pp. 526–529.
IEEE Comp. Society, Los Alamitos, 2004.
[16] N. Boujemaa, G. Stamon, J. Lemoine, and E. Petit. “Fuzzy Ventricular
Endocardium Detection with Gradual Focusing Decision,” 14th Annual
International Conference of the IEEE Engineering in Medicine and
Biology Society, Vol. 14, 1992.
[17] M. Grand-Brochier, A. Vacavant, G. Cerutti, K. Bianchi, and L. Tougne,
“Comparative Study of Segmentation Methods for Tree Leaves
Extraction,” In ACM ICVS 2013, Workshop: VIGTA, Saint Petersburg,
Russia, 2013.
[18] T. Chua and W. Tan, “Interval Type-2 Fuzzy System for ECG
Arrhythmic Classification,” Fuzzy Systems in Bioinformatics and
Computational Biology, Studies in Fuzziness and Soft Computing.
Volume 242, pp 297-314, 2009.
[19] N. Otsu, "A Threshold Selection Method from Gray–level Histograms,"
IEEE Trans. Sys., Man., Cyber. 9(1): 62–66.
doi:10.1109/TSMC.1979.4310076, 1979.
@article{"International Journal of Information, Control and Computer Sciences:70763", author = "Abder-Rahman Ali and Adélaïde Albouy-Kissi and Manuel Grand-Brochier and Viviane Ladan-Marcus and Christine Hoeffl and Claude Marcus and Antoine Vacavant and Jean-Yves Boire", title = "Liver Lesion Extraction with Fuzzy Thresholding in Contrast Enhanced Ultrasound Images", abstract = "In this paper, we present a new segmentation approach
for focal liver lesions in contrast enhanced ultrasound imaging. This
approach, based on a two-cluster Fuzzy C-Means methodology,
considers type-II fuzzy sets to handle uncertainty due to the image
modality (presence of speckle noise, low contrast, etc.), and to
calculate the optimum inter-cluster threshold. Fine boundaries are
detected by a local recursive merging of ambiguous pixels. The
method has been tested on a representative database. Compared to
both Otsu and type-I Fuzzy C-Means techniques, the proposed
method significantly reduces the segmentation errors.", keywords = "Defuzzification, fuzzy clustering, image
segmentation, type-II fuzzy sets.", volume = "9", number = "7", pages = "1737-5", }
