Improvised kernel graph cuts and continuous max-flow optimization scheme-for enhanced segmentation in Cervical Cancer Detection
Journal Title: IOSR Journals (IOSR Journal of Computer Engineering) - Year 2019, Vol 21, Issue 1
Abstract
The cervical cancer refers to the uncontrolled growth of cells in the internal lining of the cervix part that connects the uterus region to the vaginal part of the women. This cervical cancer needs to be screened for identifying pre-cancers before they get transformed into invasive cancer. The Pap Smear Test is considered as the potential screening test essential for detecting pre-cancerous cells in the cervix, such that the uncontrolled growth of inter-uterine wall cells can be prevented. The majority of the segmentation schemes proposed in the literature for detecting cervical cancer failed in predominant localization of cytoplasm and nucleus boundaries from the pap smear extracted during the screening process. In this paper, an Improvised Kernel Graph Cuts and Continuous Max-Flow Optimization (IKGC-CMFO) Scheme is proposed for enhanced segmentation during the process of significant Cervical Cancer Detection. This proposed IKGC-CMFO Scheme wide opens the options of investigating the overlapping and hazy boundaries of the pap smear cells in order to ensure optimal level of cervical cancer detection. This proposed IKGC-CMFO Scheme utilized a kernel induced space in the generation of graph cut with an incorporated max-flow algorithm achieved through continuous multiplier. The simulation experiments and results of the proposed IKGC-CMFO confirmed a superior classification accuracy rate of 32% compared to the baseline Graph cut-based segmentation approaches considered for investigation.
Authors and Affiliations
Ch. Rajarao, R. P. Singh
Keywords
Related Articles
- EP ID EP441071
- DOI 10.9790/0661-2101014453.
- Views 116
- Downloads 0
Performance of Phase Congruency and Linear Feature Extraction for Satellite Images Using Smoothing Algorithm
In computer vision all of the existing researches are interested in synthetic images features extraction. These images contain many types of features. Moreover, the satellite images are one most complex rea...
Privacy Security of Multiuser on Multilevel System using XOR
Abstract: Privacy security of multiuser on multilevel system is considered in this work. On communication there is a chance for the eavesdropper’s to secretly listen to the conversation. In order to confuse the eavesdrop...
A way of managing data center networks
Evolutionary changes have occurred throughout the various elements of the data centre, starting with server and storage virtualization and also network virtualization. Motivations for server virtualization were...
Ranking Algorithm of Web Documents using Ontology
Abstract: Internet has become the most important part of everyone’s life where the large amount of information is stored in the form of text, audio, video etc. The Web information retrieval is a technique which h...
Mobile, Secure E - Voting Architecture for the Nigerian ElectoralSystem
Abstract: This work discusses electronic voting for the Nigerian electoral system, modeling a two-levelhierarchical architecture that includes the national and state level infrastructure. This solves most of theele...