An efficient method based on watershed and rule-based merging for segmentation of 3-D histo-pathological images

Abstract This paper deals with the segmentation of 3-D histo-pathological images. Here we have presented a region-based segmentation method involving watershed algorithm and the rule-based merging technique. We have implemented a new method similar to flooding process for circumventing the inability to automatically mark the regional minima in small isolated objects. The 3-D histo-pathological images for testing the algorithm are obtained using confocal microscope in the form of a stack of optical sections. Normally, result of a classical watershed algorithm on grey-scale textured images such as tissue images is over-segmentation. We have proposed a rule-based heuristic merging technique to reduce the over-segmentation of cells. The tiny fragments of the cells and their parents are identified based on some heuristic rules and are merged together. Rule-based merging gives more than 90% accurate segmentation when compared to simple classical watershed extended to 3-D. Results are shown on 3-D images of prostate cancer tissue specimen.

[1]  S J Lockett,et al.  Automatic detection of clustered, fluorescent-stained nuclei by digital image-based cytometry. , 1994, Cytometry.

[2]  J. Pawley,et al.  Handbook of Biological Confocal Microscopy , 1990, Springer US.

[3]  Serge Beucher,et al.  Use of watersheds in contour detection , 1979 .

[4]  P. S. Umesh Adiga,et al.  Efficient cell segmentation tool for confocal microscopy tissue images and quantitative evaluation of FISH signals , 1999, Microscopy research and technique.

[5]  Steven W. Zucker,et al.  Region growing: Childhood and adolescence* , 1976 .

[6]  Henri Maître,et al.  A robust method for picture segmentation based on a split-and-merge procedure , 1986, Comput. Vis. Graph. Image Process..

[7]  D Marr,et al.  Theory of edge detection , 1979, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[8]  Catherine Garbay,et al.  Image Structure Representation and Processing: A Discussion of Some Segmentation Methods in Cytology , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  R. Kohler.  A segmentation system based on thresholding , 1981 .

[10]  Laurent Najman,et al.  Geodesic Saliency of Watershed Contours and Hierarchical Segmentation , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Marcus J. Grote,et al.  The Collection, Processing, and Display of Digital Three-Dimensional Images of Biological Specimens , 1995 .

[12]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  J J Vaquero,et al.  Applying watershed algorithms to the segmentation of clustered nuclei. , 1998, Cytometry.

[14]  P.K Sahoo,et al.  A survey of thresholding techniques , 1988, Comput. Vis. Graph. Image Process..

[15]  Rangachar Kasturi,et al.  Machine vision , 1995 .

[16]  Luc Vincent,et al.  Morphological grayscale reconstruction in image analysis: applications and efficient algorithms , 1993, IEEE Trans. Image Process..

[17]  Gunilla Borgefors,et al.  On Digital Distance Transforms in Three Dimensions , 1996, Comput. Vis. Image Underst..

[18]  Jayaram K. Udupa,et al.  Boundary and object labelling in three-dimensional images , 1990, Comput. Vis. Graph. Image Process..

[19]  Linda G. Shapiro,et al.  Computer and Robot Vision , 1991 .

[20]  Leszek Wojnar,et al.  Image Analysis , 1998 .

[21]  Falai Chen,et al.  The µ-basis of a planar rational curve: properties and computation , 2002 .

[22]  Lennart Thurfjell,et al.  A new three-dimensional connected components labeling algorithm with simultaneous object feature extraction capability , 1992, CVGIP Graph. Model. Image Process..

[23]  T. Stephenson.  Image analysis , 1992, Nature.