Human papillomaviruses (HPVs) belong to a small spherical virus family and are transmitted through direct contact, most often through sexual behavior. More than 200 types of HPV are known, a dozen or so of which are classified as high-risk viruses (HR HPV) and may contribute to the development of cervical cancer. HPV is a small virus with a capsid composed of L1 and L2 proteins, which are crucial for entry to the cell. The infection begins at the basal cell layer and progresses to involve cells from higher layers of the cervical epithelium. E6 and E7 viral proteins are involved in the process of carcinogenesis. They interact with suppressors of oncogenesis, including p53 and Rb proteins. This leads to DNA replication and intensive cell divisions. The persistent HR HPV infection leads to the development of dysplasia and these changes may progress to invasive cancer. During the initial stage of carcinogenesis, telomeres shorten until telomerase activates. The activation of telomerase, the enzyme necessary to extend chromosome ends (telomeres) is the key step in cell immortalization. Analyzing the expression level of hTERT and hTERC genes encoding telomerase and telomere length measurement may constitute new markers of the early carcinogenesis.

No abstract

In this paper, a combination of two methods based on texture analysis, contour grouping, and pattern recognition techniques is presented to detect and classify pathologic cells in cervical vaginal smears using the phase-contrast microscopy. The first method applies statistical geometrical features to detect image regions that contain epithelial cells and hide those regions with medium and contamination. Sequential forward floating selection was used to identify the most representative features. A shape of cells was identified by applying an active contour model supported by some postprocessing techniques. The second method applies edge detection, ridge following, contour grouping, and Fisher linear discriminant to detect abnormal nuclei. Evaluation of the algorithms' performance and comparison with alternative approaches show that both methods are reliable and, when combined, improve the classification. By presenting only images or their parts that are diagnostically important, the method unburdens a physician from massive and messy data. It also indicates abnormalities marking atypical nuclei and, in that sense, supports diagnosis of cervical cancer.

No abstract