Detection of mitotic nuclei in breast histopathology images using localized ACM and Random Kitchen Sink based classifier

The exact measure of mitotic nuclei is a crucial parameter in breast cancer grading and prognosis. This can be achieved by improving the mitotic detection accuracy by careful design of segmentation and classification techniques. In this paper, segmentation of nuclei from breast histopathology images are carried out by Localized Active Contour Model (LACM) utilizing bio-inspired optimization techniques in the detection stage, in order to handle diffused intensities present along object boundaries. Further, the application of a new optimal machine learning algorithm capable of classifying strong non-linear data such as Random Kitchen Sink (RKS), shows improved classification performance. The proposed method has been tested on Mitosis detection in breast cancer histological images (MITOS) dataset provided for MITOS-ATYPIA CONTEST 2014. The proposed framework achieved 95% recall, 98% precision and 96% F-score.

[1]  Anthony J. Yezzi,et al.  A Fully Global Approach to Image Segmentation via Coupled Curve Evolution Equations , 2002, J. Vis. Commun. Image Represent..

[2]  O. Sertel,et al.  Computer-aided Prognosis of Neuroblastoma: Detection of mitosis and karyorrhexis cells in digitized histological images , 2009, 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[3]  E. Berg,et al.  World Health Organization Classification of Tumours , 2002 .

[4]  Amir Hossein Alavi,et al.  Krill herd: A new bio-inspired optimization algorithm , 2012 .

[5]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[6]  John Meyer,et al.  Grading nuclear pleomorphism on histological micrographs , 2008, 2008 19th International Conference on Pattern Recognition.

[7]  Andrew K. C. Wong,et al.  A new method for gray-level picture thresholding using the entropy of the histogram , 1985, Comput. Vis. Graph. Image Process..

[8]  Allen R. Tannenbaum,et al.  Localizing Region-Based Active Contours , 2008, IEEE Transactions on Image Processing.

[9]  Madhu S. Nair,et al.  Automatic segmentation and classification of mitotic cell nuclei in histopathology images based on Active Contour Model , 2014, 2014 International Conference on Contemporary Computing and Informatics (IC3I).

[10]  V. Anari,et al.  Computer-aided detection of proliferative cells and mitosis index in immunohistichemically images of meningioma , 2010, 2010 6th Iranian Conference on Machine Vision and Image Processing.

[11]  G. R. Bindu,et al.  Analysis of Nuclei Detection with Stain Normalization in Histopathology Images , 2015 .

[12]  H. Irshad.  Automated mitosis detection in histopathology using morphological and multi-channel statistics features , 2013, Journal of pathology informatics.

[13]  Nasir M. Rajpoot,et al.  A Nonlinear Mapping Approach to Stain Normalization in Digital Histopathology Images Using Image-Specific Color Deconvolution , 2014, IEEE Transactions on Biomedical Engineering.

[14]  K. P. Soman,et al.  Tamil Characters Classification Using Random Kitchen Sink Algorithm (RKS) , 2014, ICONIAAC '14.

[15]  K. P. Soman,et al.  Condition Monitoring in Roller Bearings using Cyclostationary Features , 2015, WCI '15.

[16]  W. Ma,et al.  Novel Agents on the Horizon for Cancer Therapy , 2009, CA: a cancer journal for clinicians.

[17]  Benjamin Recht,et al.  Weighted Sums of Random Kitchen Sinks: Replacing minimization with randomization in learning , 2008, NIPS.

[18]  K P Soman,et al.  TamilCharacters classification using random kitchen sink algorithm , 2014 .

[19]  Mrinal K. Mandal,et al.  Toward Automatic Mitotic Cell Detection and Segmentation in Multispectral Histopathological Images , 2014, IEEE Journal of Biomedical and Health Informatics.