Unsupervised segmentation method for cuboidal cell nuclei in histological prostate images based on minimum cross entropy

This paper presents a novel segmentation method for cuboidal cell nuclei in images of prostate tissue stained with hematoxylin and eosin. The proposed method allows segmenting normal, hyperplastic and cancerous prostate images in three steps: pre-processing, segmentation of cuboidal cell nuclei and post-processing. The pre-processing step consists of applying contrast stretching to the red (R) channel to highlight the contrast of cuboidal cell nuclei. The aim of the second step is to apply global thresholding based on minimum cross entropy to generate a binary image with candidate regions for cuboidal cell nuclei. In the post-processing step, false positives are removed using the connected component method. The proposed segmentation method was applied to an image bank with 105 samples and measures of sensitivity, specificity and accuracy were compared with those provided by other segmentation approaches available in the specialized literature. The results are promising and demonstrate that the proposed method allows the segmentation of cuboidal cell nuclei with a mean accuracy of 97%.

[1]  Hyun Joo Choi,et al.  Automatic Histologic Grading for Lobular Carcinoma In Situ , 2009 .

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

[3]  Amitava Chatterjee,et al.  An adaptive bacterial foraging algorithm for fuzzy entropy based image segmentation , 2011, Expert Syst. Appl..

[4]  Luiz Otávio Murta,et al.  Quantification of fractal dimension and Shannon’s entropy in histological diagnosis of prostate cancer , 2013, BMC Clinical Pathology.

[5]  A. Madabhushi,et al.  Histopathological Image Analysis: A Review , 2009, IEEE Reviews in Biomedical Engineering.

[6]  Anant Madabhushi,et al.  Multi-Field-of-View Framework for Distinguishing Tumor Grade in ER+ Breast Cancer From Entire Histopathology Slides , 2013, IEEE Transactions on Biomedical Engineering.

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

[8]  Jonathan Ira Epstein,et al.  Biopsy Interpretation Of The Prostate , 2007 .

[9]  Barbara Franceschini,et al.  Fractal analysis of two-dimensional vascularity in primary prostate cancer and surrounding non-tumoral parenchyma. , 2009, Pathology, research and practice.

[10]  Rafael C. González,et al.  Digital image processing using MATLAB , 2006 .

[11]  M. Y. Mashor,et al.  Local and Global Contrast Stretching For Color Contrast Enhancement on Ziehl-Neelsen Tissue Section Slide Images , 2008 .

[12]  Allan D. Jepson,et al.  Benchmarking Image Segmentation Algorithms , 2009, International Journal of Computer Vision.

[13]  Xavier Cufí,et al.  Yet Another Survey on Image Segmentation: Region and Boundary Information Integration , 2002, ECCV.

[14]  L. Rodney Long,et al.  Histology image analysis for carcinoma detection and grading , 2012, Comput. Methods Programs Biomed..

[15]  W. Pratt.  Digital Image Processing: Piks Scientific Inside , 1978 .

[16]  Du-Ming Tsai,et al.  A fast thresholding selection procedure for multimodal and unimodal histograms , 1995, Pattern Recognit. Lett..

[17]  Anant Madabhushi,et al.  Automated grading of breast cancer histopathology using spectral clustering with textural and architectural image features , 2008, 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[18]  David Borland,et al.  Image and statistical analysis of melanocytic histology , 2012, Histopathology.

[19]  Qiang Wu,et al.  Microscope Image Processing , 2010 .

[20]  Wilhelm Burger,et al.  Principles of Digital Image Processing - Fundamental Techniques , 2010, Undergraduate Topics in Computer Science.

[21]  Chun-hung Li,et al.  Minimum cross entropy thresholding , 1993, Pattern Recognit..

[22]  P. Humphrey,et al.  Prostate cancer diagnosis. , 2010, Missouri medicine.

[23]  Kim L. Boyer,et al.  A multi-resolution image analysis system for computer-assisted grading of neuroblastoma differentiation , 2008, SPIE Medical Imaging.

[24]  Gustavo K. Rohde,et al.  A General System for Automatic Biomedical Image Segmentation Using Intensity Neighborhoods , 2011, Int. J. Biomed. Imaging.

[25]  D. Okada,et al.  Digital Image Processing for Medical Applications , 2009 .

[26]  Martial Guillaud,et al.  Quantitative Histopathological Analysis of Cervical Intra-Epithelial Neoplasia Sections: Methodological Issues , 2004, Cellular oncology : the official journal of the International Society for Cellular Oncology.

[27]  Isaac N. Bankman,et al.  Handbook of medical imaging , 2000 .

[28]  Anant Madabhushi,et al.  Cascaded multi-class pairwise classifier (CascaMPa) for normal, cancerous, and cancer confounder classes in prostate histology , 2011, 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[29]  Gleason Df.  Classification of prostatic carcinomas. , 1966 .

[30]  A. Mescher.  Junqueira's Basic Histology: Text and Atlas , 2013 .

[31]  Nikhil R. Pal,et al.  On minimum cross-entropy thresholding , 1996, Pattern Recognit..

[32]  Sim Heng Ong,et al.  A new unified level set method for semi-automatic liver tumor segmentation on contrast-enhanced CT images , 2012, Expert Syst. Appl..

[33]  Ming Zhou,et al.  Prostate Biopsy Interpretation: An Illustrated Guide , 2011 .

[34]  Erik Valdemar Cuevas Jiménez,et al.  A Comparison of Nature Inspired Algorithms for Multi-threshold Image Segmentation , 2013, Expert Syst. Appl..

[35]  Toby P. Breckon,et al.  Fundamentals of Digital Image Processing: A Practical Approach with Examples in Matlab , 2011 .

[36]  Sankar K. Pal,et al.  A review on image segmentation techniques , 1993, Pattern Recognit..