Optimizing cervical cancer diagnosis with accurate cell classification using modified HDFF

Eradication of cervical cancer involves the expansion of human papillomavirus (HPV) vaccine coverage and the development of efficient screening guidelines that take vaccination into account. In Korea, the HPV National Immunization Program was launched in 2016 and is expected to shift the prevalence of HPV genotypes in the country, among other effects. The experiences of another countries that implement national immunization programs should be applied to Korea. If HPV vaccines spread nationwide with broader coverage, after a few decades, cervical intraepithelial lesions or invasive cancer should become a rare disease, leading to a predictable decrease in the positive predictive value of cervical screening cytology. HPV testing is the primary screening tool for cervical cancer and has replaced traditional cytology-based guidelines. The current screening strategy in Korea does not differentiate women who have received complete vaccination from those who are unvaccinated. However, in the post-vaccination era, newly revised policies will be needed. We also discuss on how to increase the vaccination rate in adolescence.

Since the Papanicolaou (Pap) smear became implemented as a screening tool for cervical cancer, the mortality from cervical cancer has sharply declined in the United States. The discovery of the human papillomavirus (HPV) as the causative agent in the progression from dysplasia of the cervix to cervical cancer has changed the types of screening offered to women and the management of abnormal Pap smears. The management of abnormal Pap smears has changed depending on the age of the woman, with women under the age of 24 years being managed more conservatively given the low rates of cervical cancer in this age group and the high rates of regression of HPV and cytologic abnormalities. Colposcopy remains the first line in evaluation of an abnormal Pap smear, with excisional treatment reserved for high-grade dysplasias with a high risk of progression to cervical cancer. Treatment for cervical dysplasia is highly effective, but even after treatment, there is an increased risk of recurrence or progression to cervical cancer for up to 25 years, and these women should be followed closely. This review contains 18 figures, 3 tables, and 43 references. Key words: cervical cancer screening, high-grade cervical dysplasia, human papillomavirus, low-grade cervical dysplasia, management of abnormal Pap smears, Pap smear, recurrence of cervical dysplasia, treatment of dysplasia

The aim of this survey was to examine the knowledge, attitudes, and behavior of gynecologists in terms of human papillomavirus (HPV) DNA testing as a primary screening tool for cervical cancer. A national cross-sectional web survey was carried out through multistage sampling using an overall sample of 1000 gynecologists. Gynecologists were asked to fill in a self-administered questionnaire exploring their knowledge, attitudes, and practice toward cervical cancer screening and HPV-DNA testing. A total of 582 gynecologists completed the web questionnaire. Of these, 24.5% were uncertain on the higher sensitivity of HPV-DNA compared with the Pap test, whereas 19% were uncertain on the role of the HPV-DNA test as a primary test in women younger than 30 years old and only 44.9% knew that a negative HPV-DNA test allows for an extension of the test interval to 5 years. Most gynecologists showed a definite positive attitude on the role of screening for cervical cancer prevention and were prepared to accept new technologies. The HPV-DNA test was considered highly effective by 86.9%, whereas 94% recommend/perform HPV-DNA tests in women older than 30 years of age; 25.5% performed HPV-DNA as a primary test, followed by a Pap test in those cases that were positive. Only 56.3% recommended/performed HPV-DNA tests 1 year after a positive HPV-DNA test, followed by a negative Pap test, whereas 42.9% recommended colposcopy. Although the use of the HPV-DNA test is very widespread among Italian gynecologists performing cervical cancer screening, there is lack of standardization of practices according to current guidelines.

Objective To investigate the value of DNA ploidy analysis in cervical cancer screening for outpatients.Methods 840 from 2 692 outpatients examed by Thin Prep cytology,DNA ploidy analysis were performed directed biopsy simultaneously.Sample were taken by cervix brush and transported into a fixative solution.Two slides were made from each sample for staining with Feulgen DNA specific staining and the other with Pap stained,respectively.The routine cytological diagnosis of Pap smear was done by cytology physicians,and the Feulgen staining tablets by the automated DNA ploidy analysis system.Results Among 840 cases,554 cases (66.0 ％) were histological diagnosed as chronic cervicitis,25 cases (3.0 ％) as cervical intraepithelial neoplasia (CIN) Ⅰ,59 cases (7.0 ％) as CIN Ⅱ,100 cases (11.9 ％) as CINⅢ and 102 cases (12.1％) as cervical invasive cancer by pathological biopsy.486 cases were observed with DNA heteroploid and 354 were not.The sensitivity,specificity,positive predictive values and negative predictive values of scanning CIN Ⅱ or more severe cervical diseases by DNA heteroploid positive or heteroploid ≥3 for were 91.9 ％ or 89.2 ％,58.5 ％ or 35.8 ％,49.4 ％ or 57.3 ％,94.1％ or 77.2 ％,respectively,while those of scanning equal or more than LSIS andthe above diseases by Thin Prep cytology were 40.2 ％,90.0 ％,39.6 ％ and 76.9 ％.Conclusion DNA ploidy analysis might be a useful tool for cervical cancer screening and has a competitive sensitivity compared with conventional cytology. Key words: DNA ploidy analysis; Cervical cancer; Conventional cytology; Screen

The regular Papanicolaou (Pap) smear is the cornerstone of women's preventive healthcare. The introduction of the regular Pap smear as a screening tool for cervical cancer has markedly decreased the number of deaths from cervical cancer. During the past decade, however, the rate of death from cervical cancer has remained relatively static. This screening method is known to have a high percentage of false negative results. To improve the detection of cervical lesions using the Pap smear in screening, a number of adjunct procedures have been developed. The purpose of this study is to evaluate the utility of a magnified chemoluminescent screening examination (Colposcopy) combined with the Pap smear in detecting cervical abnormalities. We investigated a cohort of 58 subjects who have been forwarded for colposcopic evaluation due to referral cytology suggestive of persistent inflammatory process not otherwise specified, and cervical intraepithelial or invasive neoplasia, in Chania Colposcopic clinic. The higher the lesion detected by cytology, the more severe the corresponding colposcopic impression viewed. The data presented here are in harmony with previous reports and share our experience in a Regional Community Hospital Colposcopy Clinic. An integrated cytology-colposcopy program facilitates the assessment and identification of women harboring cervical pathological conditions.

HPV-16 and -18 account for about 80% of cervical cancers. We evaluated the performance of HPV-16/18 oncoprotein to predict precancer and cancer in corresponding tissue biopsy specimens. 1,008 women attending cervical cancer screening program and 638 women referred to colposcopy with biopsy-confirmed cervical intraepithelial neoplasia grade 2 or worse (CIN2+) from 4 hospitals were recruited (1,646 in total). All women were tested OncoE6 (AVC), Liquid-Based Cytology (Hologic) and cobas HPV test (Roche). Colposcopy was performed on women with any abnormal results. The final diagnoses were based on a consensus panel review of the histology. There were 919 normal, 69 CIN1, 53 CIN2, 91 CIN3,474 squamous cell carcinoma(SCC) and 40 adenocarcinoma (ADC) cases, the prevalence of OncoE6 was 1.7%, 10.1%, 13.2%, 44.0%, 80.4% and 65.0%, respectively. The percent positive for cobas was higher than that of OncoE6 in detection of HPV16/18 in entire population (p < 0.001). However, the disparity of positive rate between these two tests became tiny among cervical cancer patients (CIN2: 26.4% vs. 13.2%, CIN3: 73.6% vs. 44.0%, SCC: 84.0% vs. 80.4%, ADC: 67.5% vs. 65.0%). OncoE6 was less sensitive than cobas (73.9% vs. 93.6%, p < 0.001), but more specific (97.1% vs. 75.4%, p < 0.001) for CIN3+ in entire population; OncoE6 yielded a sensitivity of 77.7% and a specificity of 91.0% for CIN3+ among cobas positive women, which can reduce nearly half of the colposcopy referral numbers. OncoE6 can be considered as a useful tool for cervical cancer screening and a potential powerful biomarker for HPV positive triage.

Genital human papillomavirus (HPV) is the most common sexually transmitted viral infection in the United States, with a prevalence of 13% to 46% in young women.1–3 The incidence of anogenital HPV is also rising in prepubertal children, who may acquire the infection at birth or through sexual abuse. HPV has been recognized as a key factor in the pathogenesis of cervical cancer in women. The Papanicolaou (Pap) smear is an effective screening tool for cervical cancer and its precursors, and the Bethesda system, which was developed by consensus of the National Cancer Institute, is currently used for classification of Pap smears. Under the Bethesda system, epithelial cell abnormalities include atypical cells of undetermined significance (ASCUS), low-grade squamous intraepithelial lesion (LG SIL), high-grade squamous intraepithelial lesion (HG SIL), and squamous cell carcinoma. Early detection of cervical cytologic abnormalities, particularly HG SIL, which is clearly a cancer precursor, provides the opportunity to prevent progression to cervical cancer. The relative risk for cervical cancer is 0.25 to 0.37 in women who have been screened by …

Cervical cancer represents a major cause of death for women. Automatic classification of cervical images from acetic acid test could serve as a promising screening tool for cervical cancer. Despite an increasing volume of studies on automatic classification of cervical images, reported methods varied markedly in terms of features and classifiers used, and therefore the performance. The classification performance using different configurations of the classifier has not been well characterized. The objective of this study was to evaluate several frequently used features and classifiers in acetic-acid cervical image based cervical intraepithelial neoplasia classification. Seven typically used color or texture-based features and four frequently used classifiers (Support Vector Machine, Random Forest, Back-Propagation Neural Network and K-Nearest Neighbors) were included in the comparison based on a balanced large sample size including 175 CIN negative and 175 CIN positive patients. The results showed that the Support Vector Machine demonstrated the best classification accuracy when a subset of features was used. The finding of this study may provide useful reference values to the development of an automatic cervical cancer screening tool.

Most of women diagnosed as having cervical cancer have not participated in organized cytological screening. Aim. A study was conducted to evaluate the accuracy of human papilloma virus testing by self-collected vaginal samples in comparison to regular cytological screening. The agreement of hybrid capture 2 assay and polymerase chain reaction assay for detection of human papilloma virus DNA in self-collected vaginal samples and clinician-obtained cervical smears was investigated. Forty-three women aged 23-58 years admitted for further examination due to previous positive cytology in the organized screening participated in self-collecting of vaginal samples with a novel self-sampling device. During the visit a clinician also collected a cervical smear using a cytobrush. The vaginal samples collected with the self-sampling device were analyzed for high-risk human papilloma virus with the hybrid capture 2 assay technique and the cervical smears were Pap-stained, examined cytologically and after that reanalyzed for human papilloma virus DNA using a polymerase chain reaction assay. The vaginal samples were positive for high-risk human papilloma virus in 37% of the cases using hybrid capture 2 assay. Twelve of the 43 Pap smears showed positive cytology (ASCUS-CIN 3), of which 4 showed CIN 2-3. When polymerase chain reaction assay was performed, human papilloma virus DNA was detected in 40% of the glass slides. The agreement between cytology and the two human papilloma virus testing techniques was 67-74% (kappa 0.27-0.45) and the agreement between the two human papilloma virus tests was 70% (kappa 0.36). Testing for high-risk human papilloma virus can identify more women at risk of developing cervical cancer than cytology irrespective of the sampling method. Furthermore, offering a self-sampling device for collection of vaginal smear seems to be a useful screening tool for cervical cancer among women not responding to an invitation for smear sampling.

Cervical cancer is a major gynecological malignant tumor that threatens women's health. Current cytological methods have certain limitations for cervical cancer early screening. Light scattering patterns can reflect small differences in the internal structure of cells. In this study, we develop a light scattering pattern specific convolutional network (LSPS-net) based on deep learning algorithm and integrate it into a 2D light scattering static cytometry for automatic, label-free analysis of single cervical cells. An accuracy rate of 95.46% for the classification of normal cervical cells and cancerous ones (mixed C-33A and CaSki cells) is obtained. When applied for the subtyping of label-free cervical cell lines, we obtain an accuracy rate of 93.31% with our LSPS-net cytometric technique. Furthermore, the three-way classification of the above different types of cells has an overall accuracy rate of 90.90%, and comparisons with other feature descriptors and classification algorithms show the superiority of deep learning for automatic feature extraction. The LSPS-net static cytometry may potentially be used for cervical cancer early screening, which is rapid, automatic and label-free.

Self-sampling using vaginal swabs could be a valuable alternative to screen for cervical cancer for women who do not attend regular cytological screening. The aim of this study was to determine the prevalence of high and low-risk HPV types and of HPV type 16 and 18 DNA load in self-collected vaginal swabs from 35- to 69-year-old Southern French women of low socioeconomic level or migrant populations who do not attend regular cervical screening. A good concordance (93.1%) was found between cervical brush and vaginal swabs in 29 samples. Self-collected vaginal swabs were examined from 120 women. HPV infection was found in 28 women (23.3%; median age 48 years), 17 (14.1%) of whom harbored high-risk HPV types. HPV type 16 was the high risk type found most frequently, followed by types 53, 31, 18, 58, and 66. The low-risk type detected most frequently was HPV type 6, followed by types 61, 70, and 81. The mean HPV 16 and 18 load was 6.3 log(10) copies/10(6) cells and 2.4 log(10) copies/10(6) cells, respectively. These results suggest that vaginal self-swabs can be a reliable tool for cervical cancer screening in non-attending and inadequately screened elderly women.

Objective:Bacterial vaginosis (BV) is a common reproductive tract infection (RTI) reported among Indian women. BV can influence the persistence of high-risk oncogenic human papillomavirus, a causative factor for cervical cancer. BV and cervical cancer are major public health issues in a developing country like India. It becomes important for a resource-constrained country like India with poor healthcare access to implement control measures to screen and treat RTI in an attempt to prevent the risk for cervical cancer. Papanicolaou (Pap) smear is an established screening tool for cervical cancer and the diagnosis of RTIs, forms a part of its evaluation. The present study explores the validity of conventional Pap smear in diagnosing BV.Methodology:Pap smear and Gram stain smear were collected for 254 women with clinically evident cervicitis/cervicovaginitis (genital infection). Using the Nugent score on Gram stain as a gold standard, we determined the sensitivity and specificity of Pap smear to diagnose BV.Results:The overall prevalence of BV in the study population was 44% using the Nugent score. Pap smear showed sensitivity and specificity of 70.9%. (CI- 61.5% - 79.2%) and 56.8% (CI – 48.2%–65.2%), respectively. The positive predictive value of Pap smear to diagnose BV was 56.5% (CI – 47.8%–64.9%), and the negative predictive value was 71.2% (CI – 61.8%–79.4%).Conclusion:In the present study, conventional Pap smear demonstrates good accuracy to detect BV. Pap testing for cervical cancer screening can additionally serve as an effective screening tool for diagnosing BV among women with genital infection in healthcare settings.

Cervical cancer remains a leading cause of mortality for women in low-income countries. Therefore, there is an urgent need for a point-of-care cervical cancer screening test for community-based settings that can be used for triaging and managing women with preinvasive and early invasive lesions of cervix. A cross-sectional study was conducted to evaluate the diagnostic accuracy of an indigenous artificial intelligence (AI)-enabled trans-vaginal colposcopic device called SmartScope®. Parallel screening with cervical cytology and assessment of magnified digital images was done by a trained observer to minimize false negatives. Cervical biopsy was taken for any abnormality identified on any of the three tests. Histopathology report of the biopsy was taken as the reference standard. A total of 268 women were recruited for the study. Cervical evaluation with the Smart Scope® identified 17.5% (n = 47) cervices with pre-cancerous/cancerous lesions, 19.4% (n = 52) with high-risk lesions, 14.2% (n = 38) with inflammatory/benign lesions and 48.9% (n = 131) cervices as normal. Taking cervical biopsy as the reference standard, sensitivity, specificity, PPV and NPV were 68.4%, 65.5%, 13.1%, and 96.4% respectively. In comparison, the sensitivity, specificity, PPV and NPV of cervical cytology were 43.8%, 93.3%, 46.7%, and 92.5% respectively, while that of assessment of magnified digital images by trained observer was 89.5%, 49.1%, 22.4%, and 96.6% respectively. Smart Scope®-based evaluation in conjunction with the assessment of magnified digital images by a trained observer can be an effective tool for cervical cancer screening. Further improvement of AI-based diagnosis can make it an effective tool for community-based screening.

Pathology and epidemiology of HPV infection in females

Human immunodeficiency virus (HIV)-positive women may represent one of the fastest-growing populations at risk for acquiring cervical cancer and thus require frequent screening. The purpose of the present studies was to validate a PCR-based urine assay by comparing detection and genotyping of human papillomavirus (HPV) DNA in urine samples and matching cervical swab specimens of HIV-positive women. Despite a difference in amplifiability, the prevalence of any HPV genotype (58% for the cervical swab specimens and 48% for the urine specimens) was not significantly different in this population. The levels of concordance were 70, 71, and 78% for detection of any HPV type, any high-risk HPV type, or any low-risk HPV type in the two specimen types, respectively. While instances of discordant detection were greater for the cervical swab specimens than for the urine specimens, this was not statistically significant. The distributions of HPV genotypes were similar in the cervix and the urine for the majority of types examined. Importantly, detection of HPV DNA in urine was associated with an abnormal Papanicolaou smear to the same extent that detection of HPV DNA in a cervical swab specimen was. These data provide preliminary support for the proposal to use urine testing as a primary or secondary screening tool for cervical cancer in HIV-positive women or as an epidemiological tool. Additional studies with larger sample sizes must be conducted in order to further verify these findings.