A fusion-based approach for uterine cervical cancer histology image classification

Expert pathologists commonly perform visual interpretation of histology slides for cervix tissue abnormality diagnosis. We investigated an automated, localized, fusion-based approach for cervix histology image analysis for squamous epithelium classification into Normal, CIN1, CIN2, and CIN3 grades of cervical intraepithelial neoplasia (CIN). The epithelium image analysis approach includes medial axis determination, vertical segment partitioning as medial axis orthogonal cuts, individual vertical segment feature extraction and classification, and image-based classification using a voting scheme fusing the vertical segment CIN grades. Results using 61 images showed at least 15.5% CIN exact grade classification improvement using the localized vertical segment fusion versus global image features.

[1]  A. Agresti.  An introduction to categorical data analysis , 1997 .

[2]  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.

[3]  R. Joe Stanley,et al.  An image feature-based approach to automatically find images for application to clinical decision support , 2011, Comput. Medical Imaging Graph..

[4]  D. Crookes,et al.  Investigation of Methodologies for the Segmentation of Squamous Epithelium from Cervical Histological Virtual Slides , 2007, International Machine Vision and Image Processing Conference (IMVIP 2007).

[5]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[6]  L. Rodney Long,et al.  A unified set of analysis tools for uterine cervix image segmentation , 2010, Comput. Medical Imaging Graph..

[7]  Giuseppe Argenziano,et al.  A basis function feature‐based approach for skin lesion discrimination in dermatology dermoscopy images , 2008, Skin research and technology : official journal of International Society for Bioengineering and the Skin (ISBS) [and] International Society for Digital Imaging of Skin (ISDIS) [and] International Society for Skin Imaging.

[8]  J. Jeronimo,et al.  A tool for collection of region based data from uterine cervix images for correlation of visual and clinical variables related to cervical neoplasia , 2004 .

[9]  P W Hamilton,et al.  Inter‐ and intra‐observer variation in the histopathological reporting of cervical squamous in traepithelial lesion susing a modified Bethesda grading system , 1998, British journal of obstetrics and gynaecology.

[10]  Helge Toutenburg,et al.  Linear models : least squares and alternatives , 1999 .

[11]  D. Soenksen.  Digital pathology at the crossroads of major health care trends: corporate innovation as an engine for change. , 2009, Archives of pathology & laboratory medicine.

[12]  P H Bartels,et al.  Computerized diagnostic decision support system for the classification of preinvasive cervical squamous lesions. , 2003, Human pathology.

[13]  F. Bray,et al.  Cancer burden in the year 2000. The global picture. , 2001, European journal of cancer.

[14]  Chih-Jen Lin,et al.  Working Set Selection Using Second Order Information for Training Support Vector Machines , 2005, J. Mach. Learn. Res..

[15]  Nicolas Loménie,et al.  Point set morphological filtering and semantic spatial configuration modeling: Application to microscopic image and bio-structure analysis , 2012, Pattern Recognit..

[16]  Tao Li,et al.  Using discriminant analysis for multi-class classification: an experimental investigation , 2006, Knowledge and Information Systems.

[17]  Leen-Kiat Soh,et al.  Texture analysis of SAR sea ice imagery using gray level co-occurrence matrices , 1999, IEEE Trans. Geosci. Remote. Sens..

[18]  Jon C. Aster,et al.  Robbins & Cotran Pathologic Basis of Disease , 2014 .

[19]  R. Newcombe,et al.  Reporting cervical intra‐epithelial neoplasia (CIN): Intra‐ and interpathologist variation and factors associated with disagreement , 1990, Histopathology.

[20]  Richard A. Johnson,et al.  Applied Multivariate Statistical Analysis , 1983 .

[21]  Nicolas Wentzensen,et al.  Molecular mapping of high‐grade cervical intraepithelial neoplasia shows etiological dominance of HPV16 , 2012, International journal of cancer.

[22]  Michael Ian Shamos,et al.  Computational geometry: an introduction , 1985 .

[23]  Mahesh Pal,et al.  Multinomial logistic regression-based feature selection for hyperspectral data , 2012, Int. J. Appl. Earth Obs. Geoinformation.

[24]  Martial Guillaud,et al.  Subvisual chromatin changes in cervical epithelium measured by texture image analysis and correlated with HPV. , 2005, Gynecologic oncology.

[25]  Yi-Ying Wang,et al.  A Color-Based Approach for Automated Segmentation in Tumor Tissue Classification , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[26]  Deborah B. Thompson,et al.  An automated machine vision system for the histological grading of cervical intraepithelial neoplasia (CIN) , 2000, The Journal of pathology.

[27]  Calvin R. Maurer,et al.  A Linear Time Algorithm for Computing Exact Euclidean Distance Transforms of Binary Images in Arbitrary Dimensions , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[28]  D. Hosmer,et al.  Applied Logistic Regression , 1991 .

[29]  Montserrat Ros,et al.  Computer aided decision support system for cervical cancer classification , 2012, Other Conferences.

[30]  Danny Crookes,et al.  Assisted Diagnosis of Cervical Intraepithelial Neoplasia (CIN) , 2009, IEEE Journal of Selected Topics in Signal Processing.

[31]  C. Dunton,et al.  Evaluation of Colposcopically Directed Cervical Biopsies Yielding a Histologic Diagnosis of CIN 1,2 , 2002, Journal of lower genital tract disease.

[32]  Junior Barrera,et al.  Method to support diagnosis of cervical intraepithelial neoplasia (CIN) based on structural analysis of histological images , 2012, 2012 25th IEEE International Symposium on Computer-Based Medical Systems (CBMS).