Accurate evaluation of HER-2 amplification in FISH images

Fluorescence in situ hybridization (FISH) is a cytogenetic technique used to detect the presence of specific DNA sequences on chromosomes. An application of FISH targets the measurement of the amplification of the HER-2 gene within the chromosomes. This requires computation of the ratio of HER-2 over centromere 17 (CEP-17) markers detected within a representative number of nuclei. Selection of the nuclei that are used to compute this ratio is a crucial step to yield an accurate estimation of HER-2 amplification. In fact, errors deriving from overlapping, clustered and oversegmented nuclei can bias the estimation of the ratio and yield inaccurate evaluation of HER-2 amplification. In this paper, a model is presented to associate a reliability score with each nucleus. The reliability score enables refinement of segmentation results—yielding more accurate identification of the boundary of each nucleus—as well as ranking of detected nuclei so as to use just the most reliable nuclei to compute the ratio. Experimental results demonstrate that the adoption of the proposed model improves the estimation of HER-2 amplification.

[1]  Raimund Leitner,et al.  Spot Counting for Automated Analysis of Unmixed Hyper-Spectral M-FISH Images , 2008 .

[2]  W. F. Clocksin,et al.  Feature representation and signal classification in fluorescence in-situ hybridization image analysis , 2001, IEEE Trans. Syst. Man Cybern. Part A.

[3]  Sunil R Lakhani,et al.  The pathology of familial breast cancer: Immunohistochemistry and molecular analysis , 1999, Breast Cancer Research.

[4]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[5]  J Lundin,et al.  A public-domain image processing tool for automated quantification of fluorescence in situ hybridisation signals , 2007, Journal of Clinical Pathology.

[6]  Boaz Lerner,et al.  Segmentation and Classification of Dot and Non-Dot-Like Fluorescence in situ Hybridization Signals for Automated Detection of Cytogenetic Abnormalities , 2007, IEEE Transactions on Information Technology in Biomedicine.

[7]  D. Alspach.  A gaussian sum approach to the multi-target identification-tracking problem , 1975, Autom..

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

[9]  F del Pozo,et al.  Automated FISH spot counting in interphase nuclei: statistical validation and data correction. , 1998, Cytometry.

[10]  Ioannis Pitas,et al.  FISH Image Analysis Using a Modified Radial Basis Function Network , 2007, 2007 International Symposium on Signals, Circuits and Systems.

[11]  K. Castleman,et al.  Dot count proportion estimation in FISH specimens , 1995 .

[12]  Anil K. Jain.  Fundamentals of Digital Image Processing , 2018, Control of Color Imaging Systems.

[13]  Ioannis Pitas,et al.  Automated evaluation of her-2/neu status in breast tissue from fluorescent in situ hybridization images , 2005, IEEE Transactions on Image Processing.

[14]  H. Netten,et al.  FISH and chips: automation of fluorescent dot counting in interphase cell nuclei. , 1997, Cytometry.

[15]  Dennis M. Healy,et al.  Contrast enhancement of medical images using multiscale edge representation , 1994, Defense, Security, and Sensing.

[16]  Luc Vincent,et al.  Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[17]  Kenneth R Castleman,et al.  Strategies for automated fetal cell screening. , 2002, Human reproduction update.