文章基本信息

标题：Neutrosophic graph cut-based segmentation scheme for efficient cervical cancer detection
本地全文：下载
作者：M. Anousouya Devi ; J.I. Sheeba ; K. Suresh Joseph 等
期刊名称：Journal of King Saud University @?C Computer and Information Sciences
印刷版ISSN：1319-1578
出版年度：2022
卷号：34
期号：1
页码：1352-1360
语种：English
出版社：Elsevier
摘要：Cervical cancer is the most serious category of cancer that has very low survival rate in the women’s community around the globe. This survival probability of women society affected by this cervical cancer can be potentially enhanced if it is detected at an early stage as they do not provide any realizable degree of symptoms in the early phase. This cervical cancer needs to be detected at an early stage through periodical checkups. Hence, the objective of the proposed work focuses on the merits of Neutrosophic Graph Cut-based Segmentation (NGCS) facilitated over the pre-processed cervical images. This NGCS-based segmentation is mainly employed for investigating the overlapping contexts of cervical smear pre-processed images for better classification accuracy. This NGCS-based segmentation is responsible for partitioning the input preprocessed image into a diversified number of non-overlapping regions that aids in better perception at the convenience. In NGCS-based segmentation, the preprocessed input image is transformed into a Neutrosophic set and indeterminacy filter depending on the estimated indeterminacy value that integrates the intensity and spatial information the preprocessed image. The utilized indeterminacy filter plays the anchor role in minimizing the indeterminacy value associated with each intensity and spatial information. Then a graph is defined over the image with unique weights are assigned to each of the image pixels based on the estimated indeterminacy value. Finally, the maximum flow graph approach is applied over the graph for determining optimal segmentation results. The results of this NGCS-based cervical cancer detection technique is proved to be excellent on an average by 13% compared to the traditional graph cut oriented cancer detection approaches.