Cytology Imaging Segmentation Using the Locally Constrained Watershed Transform

The segmentation of medical images poses a great challenge in the area of image processing and analysis due mainly to noise, complex background, fuzzy and overlapping objects, and nonhomogeneous gradients. This work uses the so-called locally constrained watershed transform introduced by Beare [1] to address these problems. The shape constraints introduced by this type of flexible watershed transformation permit to successfully segment and separate regions of interest. This type of watershed offers an alternative to other methods (such as distance function flooding) for particle extraction in medical imaging segmentation applications, where particle overlapping is quite common. Cytology images have been used for the experimental results.

[1]  Jean Serra,et al.  Image Analysis and Mathematical Morphology , 1983 .

[2]  L. T. Andrews,et al.  Segmentation of echocardiographic images using mathematical morphology , 1988, IEEE Transactions on Biomedical Engineering.

[3]  I. Cseke,et al.  A fast segmentation scheme for white blood cell images , 1992, Proceedings., 11th IAPR International Conference on Pattern Recognition. Vol. III. Conference C: Image, Speech and Signal Analysis,.

[4]  Petros Maragos,et al.  Evolution equations for continuous-scale morphological filtering , 1994, IEEE Trans. Signal Process..

[5]  R. McOwen.  Partial differential equations , 1995 .

[6]  Pierre Soille,et al.  Morphological Image Analysis , 1999 .

[7]  Andrew G. Dempster,et al.  Segmentation of blood images using morphological operators , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[8]  Nicholas Ayache,et al.  Medical Image Analysis: Progress over Two Decades and the Challenges Ahead , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Richard Beare.  Regularized Seeded Region Growing , 2002 .

[10]  A. Dempster,et al.  Modification on distance transform to avoid over-segmentation and under-segmentation , 2002, International Symposium on VIPromCom Video/Image Processing and Multimedia Communications.

[11]  Marcel Worring,et al.  Watersnakes: Energy-Driven Watershed Segmentation , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Victor Maojo,et al.  Morphological Image Reconstruction with Criterion from Labelled Markers , 2003, DGCI.

[13]  Ron Kikinis,et al.  Improved watershed transform for medical image segmentation using prior information , 2004, IEEE Transactions on Medical Imaging.

[14]  Fernand Meyer,et al.  The Viscous Watershed Transform , 2005, Journal of Mathematical Imaging and Vision.

[15]  Richard Beare.  A locally constrained watershed transform , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Serge Beucher,et al.  Numerical residues , 2007, Image Vis. Comput..

[17]  S T C Wong,et al.  A confident scale–space shape representation framework for cell migration detection , 2008, Journal of microscopy.

[18]  Ghassan Hamarneh,et al.  Watershed segmentation using prior shape and appearance knowledge , 2009, Image Vis. Comput..

[19]  S. Bielsa,et al.  Clinical impact and reliability of pleural fluid mesothelin in undiagnosed pleural effusions. , 2009, American journal of respiratory and critical care medicine.

[20]  Victor Maojo,et al.  Reconstruction with criterion from labeled markers: new approach based on the morphological watershed , 2010, J. Electronic Imaging.

[21]  W. Srisang,et al.  Segmentation of Overlapping Chromosome Images Using Computational Geometry , 2011 .