Automatic Approach for Cervical Cancer Detection and Segmentation Using Neural Network Classifier
Authors:
Open Access
- 1 December 2018
- journal article
- Published by EpiSmart Science Vector Ltd in Asian Pacific Journal of Cancer Prevention
- Vol. 19 (12) , 3571-3580
Abstract
Cervical cancer leads to major death disease in women around the world every year. This cancer can be cured if itis initially screened and giving timely treatment to the patients. This paper proposes a novel methodology for screeningthe cervical cancer using cervigram images. Oriented Local Histogram Technique (OLHT) is applied on the cervicalimage to enhance the edges and then Dual Tree Complex Wavelet Transform (DT-CWT) is applied on it to obtainmulti resolution image. Then, features as wavelet, Grey Level Co-occurrence Matrix (GLCM), moment invariantand Local Binary Pattern (LBP) features are extracted from this transformed multi resolution cervical image. Theseextracted features are trained and also tested by feed forward back propagation neural network to classify the givencervical image into normal and abnormal. The morphological operations are applied on the abnormal cervical imageto detect and segment the cancer region. The performance of the proposed cervical cancer detection system is analyzedin the terms of sensitivity, specificity, accuracy, positive predictive value, negative predictive value, Likelihood Ratiopositive, Likelihood ratio negative, precision, false positive rate and false negative rate. The performance measures forthe cervical cancer detection system achieves 97.42% of sensitivity, 99.36% of specificity, 98.29% of accuracy, PPVof 97.28%, NPV of 92.17%, LRP of 141.71, LRN of 0.0936, 97.38 % precision, 96.72% FPR and 91.36% NPR. Fromthe simulation results, the proposed methodology outperforms the conventional methodologies for cervical cancerdetection and segmentation process.Keywords
This publication has 7 references indexed in Scilit:
- Multimodal Entity Coreference for Cervical Dysplasia DiagnosisIEEE Transactions on Medical Imaging, 2014
- Segmentation of cervical cell nuclei in high-resolution microscopic images: A new algorithm and a web-based software frameworkComputer Methods and Programs in Biomedicine, 2012
- Australian Newspaper Coverage of Human Papillomavirus Vaccination, October 2006–December 2009Journal of Health Communication, 2012
- Chinese-Australian Women’s Knowledge, Facilitators and Barriers Related to Cervical Cancer Screening: A Qualitative StudyJournal of Immigrant and Minority Health, 2011
- Scaling up human papillomavirus vaccination: a conceptual framework of vaccine adherenceSexual Health, 2010
- Morphologic characterization of cell neighborhoods in neoplastic and preneoplastic epithelium.2010
- Social and psychological impact of HPV testing in cervical screening: a qualitative studySexually Transmitted Infections, 2006