Analysis of Nuclei Detection with Stain Normalization in Histopathology Images

This paper proposes a unique detection technique to identify nuclei from microscopy images of breast histopathology slides. The method involves stain normalization, color decomposition and hysteresis thresholding. A comparative analysis of different pre-processed images on nuclei detection reveals an accuracy of 97% for Blue Ratio (BR) images. The technique uses three color channels for accurate detection of nuclei. An analysis of two stain normalization procedure is also presented.

[1]  C Wählby,et al.  Combining intensity, edge and shape information for 2D and 3D segmentation of cell nuclei in tissue sections , 2004, Journal of microscopy.

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

[3]  Erik Reinhard,et al.  Color Transfer between Images , 2001, IEEE Computer Graphics and Applications.

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

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

[6]  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).

[7]  Chao-Hui Huang,et al.  Nuclear pleomorphism scoring by selective cell nuclei detection , 2009, WACV.

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

[9]  P T Swender,et al.  Computer-assisted diagnosis. , 1974, American journal of diseases of children.

[10]  B Terracini,et al.  Malignant mesothelioma of the pleura: interobserver variability. , 1995, Journal of clinical pathology.