Abstract
Colposcopy is a medical diagnostic procedure to examine an illuminated, magnified view of the cervix by a colposcope. Colposcopic images are acquired in raw form, contains major cervix lesions, regions outside the cervix and parts of the imaging devices such as speculum. In this paper, a preprocessing method that removes the irrelevant information from the cervical images based on Mathematical morphology and clustering based on Gaussian Mixture Modeling is presented. The detection of specularities in cervix image is based on intensity and saturation information from the HSI colour space is presented. A novel approach to detect the lesion in the cervix image based on statistical features and Bayes classifier is presented. The detection of lesion is achieved by extracting the statistical features such as mean, standard deviation and skewness and the features are used as an input to the Bayes classifier. Segmentation results are evaluated on 240 images of colposcopy.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Claude, I., Pouletaut, P.: Integrated color and texture tools for colposcopic image segmentation. In: IEEE International Conference on Image Processing, pp. 311–314 (2001)
Gordon, S., Greenspan, H.: Segmentation of Non-Convex Regions within Uterine Cervix Images. In: IEEE International Symposium on Biomedical Imaging, pp. 312–315 (2007)
Greenspan, H., Gordon, S.: Automatic Detection of Anatomical Landmarks in Uterine Cervix Images. IEEE Transaction on Medical Imaging, 454–468 (2009)
Claude, I.W.: Contour features for colposcopic image classification by artificial neural networks. In: IEEE International Conference on Pattern Recognition, pp. 771–774 (2002)
Tulpule, B., Yang, S.: Segmentation and Classification of Cervix Lesions by Pattern and Texture Analysis. In: IEEE International Conference on Fuzzy System, pp. 173–176 (2005)
Artan, Y., Huang, X.: Combining Multiple 2ν-Svm Classifiers For Tissue Segmentation. In: IEEE International Symposium on Biomedical Imaging, pp. 488–491 (2003)
Acosta-Mesa, H.G., Barbara, Z.: Cervical Cancer Detection Using Colposcopic Images: a Temporal Approach. In: IEEE International Conference on Computer Science, pp. 158–164 (2005)
Srinivasan, Y., Corona, E.: A Unified Model-Based Image Analysis Framework for Automated Detection of Precancerous Lesions in Digitized Uterine Cervix Images. IEEE Journal of Selected Topics In Signal Processing, 101–111 (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
RamaPraba, P.S., Ranganathan, H. (2012). Automatic Lesion Detection in Colposcopy Cervix Images Based on Statistical Features. In: Krishna, P.V., Babu, M.R., Ariwa, E. (eds) Global Trends in Information Systems and Software Applications. ObCom 2011. Communications in Computer and Information Science, vol 270. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-29216-3_46
Download citation
DOI: https://doi.org/10.1007/978-3-642-29216-3_46
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-29215-6
Online ISBN: 978-3-642-29216-3
eBook Packages: Computer ScienceComputer Science (R0)