Journal of Applied Information Science

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Probabilistic Segmentation Methods for Early Detection of Uterine Cervical Cancer


Affiliations
1 Department of Information Technology, Tripura University (A Central University), Agartala, Tripura., India
2 Department of Computer Science & Engineering, Jadavpur University, Kolkata, West Bengal., India
3 Department of Gynecology & Obstetrics, College of Medicine & SDM Hospital, Kolkata, West Bengal., India
     

   Subscribe/Renew Journal


Uterine Cervical Cancer is one of the prevalent forms of cancer in women worldwide. Most cases of cervical cancer can be prevented through screening programs aimed at detecting precancerous lesions. In this paper, novel methods have been proposed for automated probabilistic image segmentation of cervical cancer. The detection of cervical lesions is an important issue in image processing because it has a direct impact on surgical planning. We examined the segmentation accuracy based on a validation metric against the estimated composite latent gold standard, which was derived from several experts' manual segmentations. The distribution functions of the lesion and control pixel data were parametrically assumed to be a mixture of probability distributions with different shape parameters. We also estimated the corresponding receiver operating characteristic (ROC) curve over all possible decision thresholds. The automated segmentation yielded satisfactory accuracy with protean optimal thresholds.

Keywords

Segmentation, Clustering, Gaussian Mixture Model
Subscription Login to verify subscription
User
Notifications
Font Size


  • Parkin, D. M., Bray, F., Ferlay J. & Pisani P. (2005). Global cancer statistics. CA: A Cancer Journal for Clinicians, 55(2), 74-108. [JCan05]

  • Das, A., Kar, A. & Bhattacharyya, D. (2011). Elimination of specular reflection and identification of ROI: The first step in automated detection of uterine cervical cancer using digital Colposcopy. IEEE Imaging Systems & Techniques ISSN 1550-6037 pp 237-141, 2011 [IST11]

  • Das, A., Kar, A. & Bhattacharyya, D. (2011). Preprocessing for Automatic Detection of Cervical Cancer.Paper presented at 15th International Conference on Information Visualization, University of London, U.K. [IV11]

  • Das, A., Kar, A. & Bhattacharyya, D.(2011). Biomedical visualization. In Banissi, E. et al (Eds.), In Information Visualization (pp. 597-600). USA: IEEE Computer Society. [BMV11]

  • Das, A., Kar, A. & Bhattacharyya, D. (2012). Implication of Technology on Society in Asia: Automated Detection of Cervical Cancer. Paper presented at IEEE Conference on Technology and Society in Asia (T&SA), Singapore. [TSA12]

  • Theodoridis, S. & Koutroumbas, K. (2009). Pattern Recognition. New York: Elsevier. [PR09]


Abstract Views: 363

PDF Views: 6




  • Probabilistic Segmentation Methods for Early Detection of Uterine Cervical Cancer

Abstract Views: 363  |  PDF Views: 6

Authors

Abhishek Das
Department of Information Technology, Tripura University (A Central University), Agartala, Tripura., India
Avijit Kar
Department of Computer Science & Engineering, Jadavpur University, Kolkata, West Bengal., India
Debasis Bhattacharyya
Department of Gynecology & Obstetrics, College of Medicine & SDM Hospital, Kolkata, West Bengal., India

Abstract


Uterine Cervical Cancer is one of the prevalent forms of cancer in women worldwide. Most cases of cervical cancer can be prevented through screening programs aimed at detecting precancerous lesions. In this paper, novel methods have been proposed for automated probabilistic image segmentation of cervical cancer. The detection of cervical lesions is an important issue in image processing because it has a direct impact on surgical planning. We examined the segmentation accuracy based on a validation metric against the estimated composite latent gold standard, which was derived from several experts' manual segmentations. The distribution functions of the lesion and control pixel data were parametrically assumed to be a mixture of probability distributions with different shape parameters. We also estimated the corresponding receiver operating characteristic (ROC) curve over all possible decision thresholds. The automated segmentation yielded satisfactory accuracy with protean optimal thresholds.

Keywords


Segmentation, Clustering, Gaussian Mixture Model

References