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.
S. De et al., "A Fusion-based Approach for Uterine Cervical Cancer Histology Image Classification," Computerized Medical Imaging and Graphics, vol. 37, no. 7-8, pp. 475-487, Elsevier, Oct 2013.
The definitive version is available at http://dx.doi.org/10.1016/j.compmedimag.2013.08.001
Electrical and Computer Engineering
Keywords and Phrases
Cervical intraepithelial neoplasias; Feature analysis; Feature extraction and classification; Image-based classification; Medial axis determinations; Tissue abnormalities; Uterine cervical cancer; Visual interpretation; Data fusion; Feature extraction; Histology; Image analysis; Image processing; Image segmentation; Image classification; cancer grading; human; pathologist; priority journal; squamous epithelium; uterine cervix cancer; uterine cervix carcinoma in situ; Cervical intraepithelial neoplasia; Algorithms; Female; Humans; Image Enhancement; Image Interpretation; Computer-Assisted; Microscopy; Microtomy; Neoplasm Grading; Neoplasms; Pattern Recognition; Automated; Reproducibility of Results; Sensitivity and Specificity; Subtraction Technique; Uterine Cervical Neoplasms
International Standard Serial Number (ISSN)
Article - Journal
© 2013 Elsevier, All rights reserved.