An effective diagnosis of cervical cancer neoplasia by extracting the diagnostic features using CRF

Cervical cancer is one of the most common forms of cancer in the woman worldwide. Most cases of cervical cancer can be prevented if it is detected earlier through various screening programs. This paper provides various methods for the automated diagnosis of cervical cancer neoplasia. The techniques that are investigated to create a fully automated system to locate precancerous and cancerous regions in an image of a cervix generated by the digital colposcope is considered. The image regions corresponding to different tissue types are identified for the extraction of domain-specific anatomical features. Domain-specific diagnostic features are used in a probabilistic manner using Conditional Random Fields (CRF). The abnormal areas in colposcopic images are located exactly. Thus this automated diagnosis of cervical cancer method is more useful for the developing countries since they have low-resource settings and poor financial condition.

[1]  Sun Young Park,et al.  Domain-Specific Image Analysis for Cervical Neoplasia Detection Based on Conditional Random Fields , 2011, IEEE Transactions on Medical Imaging.

[2]  Wenjing Li,et al.  Detection and Characterization of Abnormal Vascular Patterns in Automated Cervical Image Analysis , 2006, ISVC.

[3]  D G Ferris,et al.  Identification of Cervical Neoplasia Using a Simulation of Human Vision , 2001, Journal of lower genital tract disease.

[4]  A. Singer,et al.  Visualization Techniques (Colposcopy, Direct Visual Inspection, and Spectroscopic and Other Visual Methods) , 2002, Acta Cytologica.

[5]  Magdy S Mikhail,et al.  Computerized measurement of intercapillary distance using image analysis in women with cervical intraepithelial neoplasia: correlation with severity. , 2004, Acta obstetricia et gynecologica Scandinavica.

[6]  Holger Lange,et al.  Automatic glare removal in reflectance imagery of the uterine cervix , 2005, SPIE Medical Imaging.

[7]  Abhishek Das,et al.  Elimination of specular reflection and identification of ROI: The first step in automated detection of Cervical Cancer using Digital Colposcopy , 2011, 2011 IEEE International Conference on Imaging Systems and Techniques.

[8]  Brett D. Thackray,et al.  Semi-automatic segmentation of vascular network images using a rotating structuring element (ROSE) with mathematical morphology and dual feature thresholding , 1993, IEEE Trans. Medical Imaging.

[9]  Rebecca Richards-Kortum,et al.  Optical imaging for cervical cancer detection: solutions for a continuing global problem , 2008, Nature Reviews Cancer.

[10]  Sung K. Chang,et al.  Multispectral digital colposcopy for in vivo detection of cervical cancer. , 2003, Optics express.

[11]  Jose Jeronimo,et al.  Visual inspection with acetic acid for cervical cancer screening outside of low-resource settings. , 2005, Revista panamericana de salud publica = Pan American journal of public health.

[12]  Andrew McCallum,et al.  Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.