Q-Metrics for Early Detection of Cervical Cancer

A. Das, A. Kar, D. Bhattacharyya

Abstract


The most prevalent form of cancer in women worldwide is uterine cervical cancer. Through screening programs aimed at detecting precancerous lesions most cases of cervical cancer can be prevented. In this article, Q-metrics has been proposed for carrying out automated image segmentation of uterine cervical cancer. The validation of detection of cervical lesions is an important issue in medical image processing because it has a specific impact on surgical planning. We evaluated the segmentation accuracy on the basis of a four-sample validation metric against the estimated gold standard, which was derived from several domain experts’ manual segmentations by a novel algorithm. The distribution functions of the lesion and control pixel data were parametrically assumed to be a mixture of two beta distributions with different shape parameters. We estimated the corresponding receiver operating characteristic (R.O.C.) curve and Dice similarity coefficient (D.S.C.) in all possible decision thresholds. The automated segmentation yielded satisfactory accuracy with varied optimal thresholds.

Keywords


cervical cancer, automated segmentation, E.M. algorithm, sensitivity, specificity, clustering, R.O.C., D.S.C.

Full Text:

PDF

References


Parkin,D. M. , Bray, F. , Ferlay, J. and Pisani,P. “Global cancer statistics,” Ca-Cancer J. Clin. (55), 74–108 ( 2005).

Wesley,R. ,Sankaranarayanan, R. , Mathew,B. ,Chandralekha, B., Aysha-Begum, A.,. Amma, N. S and Nair,M. K. “Evaluation of visual inspection as a screening test for cervical cancer,” Br. J. Cancer. (75), 436–440( 1997).

Ferris,D. G. ,Lawhead,R. A. ,Dickman, E. D. ,Holtzapple, N. , Miller,J. A. , Grogan,S. ,Bambot,S. , Agrawal,A. andFaupel,M. L. “Multimodal hyperspectral imaging for the noninvasive diagnosis of cervical neoplasia,” J. Low. Genit. Tract Dis. 5(2), 65–72( 2001).

CraineB. L. andCraine,E. R. “Digital imaging colposcopy: basic concepts and applications,” Obstet. Gynecol. Clin. North Am. (82), 869–873 (1993).

Shafi,M. I. , Dunn,J. A.,Chenoy,R. , Buxton,E. J. , Williams,C. and Luesley,D. M. , “Digital imaging colposcopy, image analysis and quantification of the colposcopic image,” Br. J. Obstet. Gynaecol. (101), 234–238(1994).

Cristoforoni, P. M. ,Gerbaldo,G., Perino, A., Piccoli,R. ,Montz, F. J., and Capitanio,G. L. , “Computerized colposcopy: results of a pilot study and analysis of its clinical relevance,” Obstet. Gynecol. (85) 1011–1016 (1995).

Das, A., Kar, A.and Bhattacharyya,D. ,"Elimination of Specular reflection and Identification of ROI: The First Step in Automated Detection of Uterine Cervical Cancer using Digital Colposcopy" In: Proc. of IEEE Imaging Systems & Techniques(IST), Penang, Malaysia,237-141(2011).

Das, A., Kar, A.and Bhattacharyya,D. ,“Preprocessing for automatic detection of Cervical Cancer" In: Proc of 15th International Conference on Information Visualisation(IV), London, U.K , 597-600 (2011).

Das, A., Kar, A. and Bhattacharyya,D. ,Book Chapter on ‘BioMedicalVisualisation’ in the Book Titled ‘Information Visualisation’ published by IEEE Computer Society, USA, ISSN 1550-6037 (2011).

Jaccard,P., “The distribution of flora in the alpine zone.” New Phytologist(11) 37-50 (1912).

LR Dice, “Measures of the amount of ecologic association between species.” Ecology (26)297-302(1945).

Das, A., Kar, A. and Bhattacharyya,D. ,"Early Detection of Cervical Cancerusing novel segmentation algorithms” Invertis J. of Sci. & Tech., ISSN 0973-8940, (2013).

Das, A., Kar, A, and Bhattacharyya,D. , “Implication of technology on societyin Asia: Automated detection of Cervical Cancer.” In: Proc of IEEEConference on Technology and Society in Asia (T&SA),Singapore, 1-4 (2012).

Das, A., Kar, A.and Bhattacharyya,D. , “Probabilistic Segmentation Methods for Early Detection of Uterine Cervical Cancer”, J. of Applied Information Sc.., ISSN 2321-6115, 11(1) ,28-31(2013).


Refbacks

  • There are currently no refbacks.


This site has been shifted to https://stmcomputers.stmjournals.com/