Batch-invariant nuclear segmentation in whole mount histology sections

The Cancer Genome Atlas (TCGA) provides a rich repository of whole mount tumor sections that are collected from different laboratories. However, there are a significant amount of technical and biological variations that impede analysis. We have developed a novel approach for nuclear segmentation in histology sections, which addresses the problem of technical and biological variations by incorporating information from manually annotated reference patches with the local color space of the original image. Subsequently, the problem is formulated within a multi-reference graph cut with geodesic constraints. This approach has been validated on manually curated samples and then applied to a dataset of 440 whole mount tissue sections, originating from different laboratories, which are typically 40k-by-40k pixels or larger. Segmentation results, through a zoomable interface, and extracted morphometric data are available at: http://tcga.lbl.gov.

[1]  A. Ruifrok,et al.  Quantification of histochemical staining by color deconvolution. , 2001, Analytical and quantitative cytology and histology.

[2]  Gyan Bhanot,et al.  Expectation–Maximization-Driven Geodesic Active Contour With Overlap Resolution (EMaGACOR): Application to Lymphocyte Segmentation on Breast Cancer Histopathology , 2010, IEEE Transactions on Biomedical Engineering.

[3]  Dirk R. Padfield,et al.  Color and texture based segmentation of molecular pathology images usING HSOMS , 2008, 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[4]  Yousef Al-Kofahi,et al.  Improved Automatic Detection and Segmentation of Cell Nuclei in Histopathology Images , 2010, IEEE Transactions on Biomedical Engineering.

[5]  Serge J. Belongie,et al.  Unsupervised Color Decomposition Of Histologically Stained Tissue Samples , 2003, NIPS.

[6]  Kimerly A Powell,et al.  Automated cell nuclear segmentation in color images of hematoxylin and eosin-stained breast biopsy. , 2003, Analytical and quantitative cytology and histology.

[7]  Todd H. Stokes,et al.  Automatic batch-invariant color segmentation of histological cancer images , 2011, 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[8]  Marie-Pierre Jolly,et al.  Interactive Graph Cuts for Optimal Boundary and Region Segmentation of Objects in N-D Images , 2001, ICCV.

[9]  Bahram Parvin,et al.  Morphometic analysis of TCGA glioblastoma multiforme , 2011, BMC Bioinformatics.

[10]  Marie-Pierre Jolly,et al.  Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[12]  Domenico Tegolo,et al.  An automated image analysis methodology for classifying megakaryocytes in chronic myeloproliferative disorders , 2008, Medical Image Anal..

[13]  Bahram Parvin,et al.  Graphical methods for quantifying macromolecules through bright field imaging , 2009, Bioinform..

[14]  Bahram Parvin,et al.  Molecular bases of morphometric composition in Glioblastoma multiforme , 2012, 2012 9th IEEE International Symposium on Biomedical Imaging (ISBI).

[15]  A. Ruifrok,et al.  Comparison of Quantification of Histochemical Staining By Hue-Saturation-Intensity (HSI) Transformation and Color-Deconvolution , 2003, Applied immunohistochemistry & molecular morphology : AIMM.

[16]  Vladimir Kolmogorov,et al.  Computing geodesics and minimal surfaces via graph cuts , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[17]  Bahram Parvin,et al.  A Delaunay triangulation approach for segmenting clumps of nuclei , 2009, 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.