High-Throughput Biomarker Segmentation on Ovarian Cancer Tissue Microarrays via Hierarchical Normalized Cuts

We present a system for accurately quantifying the presence and extent of stain on account of a vascular biomarker on tissue microarrays. We demonstrate our flexible, robust, accurate, and high-throughput minimally supervised segmentation algorithm, termed hierarchical normalized cuts (HNCuts) for the specific problem of quantifying extent of vascular staining on ovarian cancer tissue microarrays. The high-throughput aspect of HNCut is driven by the use of a hierarchically represented data structure that allows us to merge two powerful image segmentation algorithms-a frequency weighted mean shift and the normalized cuts algorithm. HNCuts rapidly traverses a hierarchical pyramid, generated from the input image at various color resolutions, enabling the rapid analysis of large images (e.g., a 1500 × 1500 sized image under 6 s on a standard 2.8-GHz desktop PC). HNCut is easily generalizable to other problem domains and only requires specification of a few representative pixels (swatch) from the object of interest in order to segment the target class. Across ten runs, the HNCut algorithm was found to have average true positive, false positive, and false negative rates (on a per pixel basis) of 82%, 34%, and 18%, in terms of overlap, when evaluated with respect to a pathologist annotated ground truth of the target region of interest. By comparison, a popular supervised classifier (probabilistic boosting trees) was only able to marginally improve on the true positive and false negative rates (84% and 14%) at the expense of a higher false positive rate (73%), with an additional computation time of 62\% compared to HNCut. We also compared our scheme against a k-means clustering approach, which both the HNCut and PBT schemes were able to outperform. Our success in accurately quantifying the extent of vascular stain on ovarian cancer TMAs suggests that HNCut could be a very powerful tool in digital pathology and bioinformatics applications where it could be used to facilitate computer-assisted prognostic predictions of disease outcome.

[1]  Bilge Karaçali,et al.  Automated detection of regions of interest for tissue microarray experiments: an image texture analysis , 2007, BMC Medical Imaging.

[2]  Albert Y. Zomaya.  Parallel and Distributed Computing Handbook , 1995 .

[3]  Purang Abolmaesumi,et al.  Probabilistic pairwise Markov models: application to prostate cancer detection , 2009, Medical Imaging.

[4]  Andrew Janowczyk,et al.  Hierarchical Normalized Cuts: Unsupervised Segmentation of Vascular Biomarkers from Ovarian Cancer Tissue Microarrays , 2009, MICCAI.

[5]  Xuelin Huang,et al.  Validation of tissue microarray technology in ovarian carcinoma , 2004, Modern Pathology.

[6]  Stephen J. McKenna,et al.  Classification of breast tissue-microarray spots using texton histograms , 2008 .

[7]  David A. Landgrebe,et al.  A survey of decision tree classifier methodology , 1991, IEEE Trans. Syst. Man Cybern..

[8]  Zhuowen Tu,et al.  Probabilistic boosting-tree: learning discriminative models for classification, recognition, and clustering , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[9]  S. P. Lloyd,et al.  Least squares quantization in PCM , 1982, IEEE Trans. Inf. Theory.

[10]  Anant Madabhushi,et al.  Predicting classifier performance with a small training set: Applications to computer-aided diagnosis and prognosis , 2010, 2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[11]  Yi Pan,et al.  Improved K-means clustering algorithm for exploring local protein sequence motifs representing common structural property , 2005, IEEE Transactions on NanoBioscience.

[12]  Sharat Chandran,et al.  Improved Cut-Based Foreground Identification , 2004, ICVGIP.

[13]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[14]  Kannappan Palaniappan,et al.  Cell Segmentation Using Coupled Level Sets and Graph-Vertex Coloring , 2006, MICCAI.

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

[16]  Laurent D. Cohen,et al.  Global Minimum for Active Contour Models: A Minimal Path Approach , 1997, International Journal of Computer Vision.

[17]  Vijay V. Vazirani,et al.  Approximation Algorithms , 2001, Springer Berlin Heidelberg.

[18]  Robert Jenssen,et al.  Mean shift spectral clustering , 2008, Pattern Recognit..

[19]  A. M. Turing,et al.  Computing Machinery and Intelligence , 1950, The Philosophy of Artificial Intelligence.

[20]  Anant Madabhushi,et al.  A Boosting Cascade for Automated Detection of Prostate Cancer from Digitized Histology , 2006, MICCAI.

[21]  Dorin Comaniciu,et al.  Mean Shift: A Robust Approach Toward Feature Space Analysis , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[22]  David J. Foran,et al.  A prototype for unsupervised analysis of tissue microarrays for cancer research and diagnostics , 2004, IEEE Transactions on Information Technology in Biomedicine.

[23]  Vladimir Kolmogorov,et al.  An experimental comparison of min-cut/max- flow algorithms for energy minimization in vision , 2001, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  S DhillonInderjit,et al.  Weighted Graph Cuts without Eigenvectors A Multilevel Approach , 2007 .

[25]  Vladimir Kolmogorov,et al.  An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision , 2004, IEEE Trans. Pattern Anal. Mach. Intell..

[26]  Gabriela Alexe,et al.  Towards Improved Cancer Diagnosis and Prognosis Using Analysis of Gene Expression Data and Computer Aided Imaging , 2009, Experimental biology and medicine.

[27]  Hallgeir Rui,et al.  Creating tissue microarrays by cutting-edge matrix assembly , 2005, Expert review of medical devices.

[28]  Ronald Simon,et al.  Tissue microarray (TMA) applications: implications for molecular medicine , 2003, Expert Reviews in Molecular Medicine.

[29]  A. Madabhushi.  Digital pathology image analysis: opportunities and challenges. , 2009, Imaging in medicine.

[30]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.

[31]  David S. Johnson,et al.  Computers and Intractability: A Guide to the Theory of NP-Completeness , 1978 .

[32]  Andrew Janowczyk,et al.  A weighted mean shift, normalized cuts initialized color gradient based geodesic active contour model: applications to histopathology image segmentation , 2010, Medical Imaging.

[33]  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.

[34]  Zhe Zhang,et al.  Improved K-Means Clustering Algorithm , 2008, 2008 Congress on Image and Signal Processing.

[35]  V. Devabhaktuni,et al.  Microarray image segmentation using chan-vese active contour model and level set method , 2009, 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[36]  Stephen M. Hewitt,et al.  Framework for parsing, visualizing and scoring tissue microarray images , 2006, IEEE Transactions on Information Technology in Biomedicine.

[37]  D. Krag,et al.  Grb7-based molecular therapeutics in cancer , 2003, Expert Reviews in Molecular Medicine.

[38]  Gustavo Carneiro,et al.  Detection and Measurement of Fetal Anatomies from Ultrasound Images using a Constrained Probabilistic Boosting Tree , 2008, IEEE Transactions on Medical Imaging.

[39]  David J. Foran,et al.  Unsupervised imaging, registration and archiving of tissue microarrays , 2002, AMIA.

[40]  Larry D. Hostetler,et al.  The estimation of the gradient of a density function, with applications in pattern recognition , 1975, IEEE Trans. Inf. Theory.

[41]  Larry S. Davis,et al.  Improved fast gauss transform and efficient kernel density estimation , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[42]  O. Kallioniemi,et al.  Tissue microarray technology for high-throughput molecular profiling of cancer. , 2001, Human molecular genetics.

[43]  Jitendra Malik,et al.  Normalized cuts and image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[44]  ChengYizong.  Mean Shift, Mode Seeking, and Clustering , 1995 .

[45]  C. D. Kemp,et al.  Density Estimation for Statistics and Data Analysis , 1987 .

[46]  Anant Madabhushi,et al.  A Boosted Bayesian Multiresolution Classifier for Prostate Cancer Detection From Digitized Needle Biopsies , 2012, IEEE Transactions on Biomedical Engineering.

[47]  M. Sobrinho-Simões,et al.  The origin and significance of thyroid psammoma bodies. , 1980, Laboratory investigation; a journal of technical methods and pathology.

[48]  Hai Jin,et al.  Color Image Segmentation Based on Mean Shift and Normalized Cuts , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[49]  George Coukos,et al.  Tumor vascular proteins as biomarkers in ovarian cancer. , 2007, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[50]  Inderjit S. Dhillon,et al.  Weighted Graph Cuts without Eigenvectors A Multilevel Approach , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[51]  Ran He,et al.  Agglomerative Mean-Shift Clustering via Query Set Compression , 2009, SDM.

[52]  Junyu Dong,et al.  Image quantification of high-throughput tissue microarray , 2006, SPIE Medical Imaging.

[53]  Hans Vrolijk,et al.  Automated acquisition of stained tissue microarrays for high-throughput evaluation of molecular targets. , 2003, The Journal of molecular diagnostics : JMD.

[54]  Constantine Katsinis,et al.  Automated identification of microstructures on histology slides , 2004, 2004 2nd IEEE International Symposium on Biomedical Imaging: Nano to Macro (IEEE Cat No. 04EX821).

[55]  Purang Abolmaesumi,et al.  High-throughput detection of prostate cancer in histological sections using probabilistic pairwise Markov models , 2010, Medical Image Anal..

[56]  Yizong Cheng,et al.  Mean Shift, Mode Seeking, and Clustering , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[57]  Anant Madabhushi,et al.  Spectral Embedding Based Probabilistic Boosting Tree (ScEPTre): Classifying High Dimensional Heterogeneous Biomedical Data , 2009, MICCAI.

[58]  Anant Madabhushi,et al.  AUTOMATED GRADING OF PROSTATE CANCER USING ARCHITECTURAL AND TEXTURAL IMAGE FEATURES , 2007, 2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[59]  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.

[60]  Richard M. Leahy,et al.  An Optimal Graph Theoretic Approach to Data Clustering: Theory and Its Application to Image Segmentation , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[61]  Jie Yang,et al.  Unsupervised color-texture segmentation based on soft criterion with adaptive mean-shift clustering , 2006, Pattern Recognit. Lett..