-
Scientific Reports May 2024Cervical cancer, the second most prevalent cancer affecting women, arises from abnormal cell growth in the cervix, a crucial anatomical structure within the uterus. The...
Cervical cancer, the second most prevalent cancer affecting women, arises from abnormal cell growth in the cervix, a crucial anatomical structure within the uterus. The significance of early detection cannot be overstated, prompting the use of various screening methods such as Pap smears, colposcopy, and Human Papillomavirus (HPV) testing to identify potential risks and initiate timely intervention. These screening procedures encompass visual inspections, Pap smears, colposcopies, biopsies, and HPV-DNA testing, each demanding the specialized knowledge and skills of experienced physicians and pathologists due to the inherently subjective nature of cancer diagnosis. In response to the imperative for efficient and intelligent screening, this article introduces a groundbreaking methodology that leverages pre-trained deep neural network models, including Alexnet, Resnet-101, Resnet-152, and InceptionV3, for feature extraction. The fine-tuning of these models is accompanied by the integration of diverse machine learning algorithms, with ResNet152 showcasing exceptional performance, achieving an impressive accuracy rate of 98.08%. It is noteworthy that the SIPaKMeD dataset, publicly accessible and utilized in this study, contributes to the transparency and reproducibility of our findings. The proposed hybrid methodology combines aspects of DL and ML for cervical cancer classification. Most intricate and complicated features from images can be extracted through DL. Further various ML algorithms can be implemented on extracted features. This innovative approach not only holds promise for significantly improving cervical cancer detection but also underscores the transformative potential of intelligent automation within the realm of medical diagnostics, paving the way for more accurate and timely interventions.
Topics: Humans; Uterine Cervical Neoplasms; Female; Deep Learning; Early Detection of Cancer; Neural Networks, Computer; Algorithms; Papanicolaou Test; Colposcopy
PubMed: 38734714
DOI: 10.1038/s41598-024-61063-w -
Cancers Apr 2024In 2020, the World Health Organization (WHO) reported 604,000 new diagnoses of cervical cancer (CC) worldwide, and over 300,000 CC-related fatalities. The vast majority... (Review)
Review
In 2020, the World Health Organization (WHO) reported 604,000 new diagnoses of cervical cancer (CC) worldwide, and over 300,000 CC-related fatalities. The vast majority of CC cases are caused by persistent human papillomavirus (HPV) infections. HPV-related CC incidence and mortality rates have declined worldwide because of increased HPV vaccination and CC screening with the Papanicolaou test (PAP test). Despite these significant improvements, developing countries face difficulty implementing these programs, while developed nations are challenged with identifying HPV-independent cases. Molecular and proteomic information obtained from blood or tumor samples have a strong potential to provide information on malignancy progression and response to therapy in CC. There is a large amount of published biomarker data related to CC available but the extensive validation required by the FDA approval for clinical use is lacking. The ability of researchers to use the big data obtained from clinical studies and to draw meaningful relationships from these data are two obstacles that must be overcome for implementation into clinical practice. We report on identified multimarker panels of serum proteomic studies in CC for the past 5 years, the potential for modern computational biology efforts, and the utilization of nationwide biobanks to bridge the gap between multivariate protein signature development and the prediction of clinically relevant CC patient outcomes.
PubMed: 38730581
DOI: 10.3390/cancers16091629 -
Computer Methods and Programs in... Jun 2024In cervical cell diagnostics, autonomous screening technology constitutes the foundation of automated diagnostic systems. Currently, numerous deep learning-based...
BACKGROUND AND OBJECTIVES
In cervical cell diagnostics, autonomous screening technology constitutes the foundation of automated diagnostic systems. Currently, numerous deep learning-based classification techniques have been successfully implemented in the analysis of cervical cell images, yielding favorable outcomes. Nevertheless, efficient discrimination of cervical cells continues to be challenging due to large intra-class and small inter-class variations. The key to dealing with this problem is to capture localized informative differences from cervical cell images and to represent discriminative features efficiently. Existing methods neglect the importance of global morphological information, resulting in inadequate feature representation capability.
METHODS
To address this limitation, we propose a novel cervical cell classification model that focuses on purified fusion information. Specifically, we first integrate the detailed texture information and morphological structure features, named cervical pathology information fusion. Second, in order to enhance the discrimination of cervical cell features and address the data redundancy and bias inherent after fusion, we design a cervical purification bottleneck module. This model strikes a balance between leveraging purified features and facilitating high-efficiency discrimination. Furthermore, we intend to unveil a more intricate cervical cell dataset: Cervical Cytopathology Image Dataset (CCID).
RESULTS
Extensive experiments on two real-world datasets show that our proposed model outperforms state-of-the-art cervical cell classification models.
CONCLUSIONS
The results show that our method can well help pathologists to accurately evaluate cervical smears.
Topics: Humans; Female; Papanicolaou Test; Cervix Uteri; Uterine Cervical Neoplasms; Deep Learning; Image Processing, Computer-Assisted; Neural Networks, Computer; Algorithms; Vaginal Smears
PubMed: 38728830
DOI: 10.1016/j.cmpb.2024.108199 -
Cytopathology : Official Journal of the... Jul 2024We offer a comprehensive depiction of the cytomorphological characteristics of lobular endocervical glandular hyperplasia (LEGH) as observed in SurePath™ liquid-based...
We offer a comprehensive depiction of the cytomorphological characteristics of lobular endocervical glandular hyperplasia (LEGH) as observed in SurePath™ liquid-based cytology (LBC), subsequently confirmed on cone biopsy. Lobular endocervical glandular hyperplasia (LEGH), a precursor to gastric-type adenocarcinoma (GAE) of the endocervix, is rare and reports of it in cervical cytology are scarce. We provide a thorough description of the cytomorphological features of LEGH observed in SurePath™ liquid-based cytology (LBC), later confirmed by cone biopsy. To the best of our knowledge, this is the first report documenting cytology of LEGH in LBC of a Pap sample.
Topics: Humans; Female; Cervix Uteri; Uterine Cervical Neoplasms; Vaginal Smears; Papanicolaou Test; Hyperplasia; Cytodiagnosis; Adenocarcinoma; Adult; Cytology
PubMed: 38712698
DOI: 10.1111/cyt.13385 -
Cureus Apr 2024Objectives Human papillomavirus (HPV) and (TV) infections have been proposed as risk factors for cervical cancer. This study has been conducted with the aim of...
Objectives Human papillomavirus (HPV) and (TV) infections have been proposed as risk factors for cervical cancer. This study has been conducted with the aim of investigating the prevalence of TV and its relationship with HPV in women who underwent Pap smear testing as part of cancer screenings. Materials and methods The sampling of liquid-based cervical tissue was conducted among 500 women referred to the women's clinic of Shahid Sadoughi Hospital in Yazd, Iran. The studied samples were examined for Pap smear tests and microscopic identification of TV, as well as HPV-DNA detection and the determination of high-risk and low-risk HPV types by the polymerase chain reaction (PCR) method. The results were analyzed using the IBM SPSS Statistics for Windows, Version 24 (Released 2016; IBM Corp., Armonk, New York) software. Results The individuals included in the study were 16-72 years old. The prevalence rate of TV infection in this population was found to be 29.2%, and the frequency rate of HPV was reported to be approximately 19.4%, with high-risk HPV, including HPV-56, having the highest frequency. The Pap smear test results were reported as abnormal in 20.2%, and a significant correlation was observed between HPV infection and an abnormal Pap smear test (P < 0.05). In addition, a notable correlation was detected between TV infection and high-risk and low-risk HPV (P < 0.05). Conclusion According to the significant relationship found between the two pathogens, TV and HPV, in the abnormal Pap smear test results, TV infection can be considered a risk factor for HPV infection, as well as uterine lesions and cancer.
PubMed: 38711704
DOI: 10.7759/cureus.57701 -
JAMA Network Open May 2024Lesbian, gay, and bisexual populations face barriers accessing health care in Chicago, Illinois.
IMPORTANCE
Lesbian, gay, and bisexual populations face barriers accessing health care in Chicago, Illinois.
OBJECTIVE
To describe the prevalence of up-to-date cervical cancer screening among lesbian, gay, and bisexual vs heterosexual cisgender women in Chicago.
DESIGN, SETTING, AND PARTICIPANTS
This retrospective, cross-sectional, population-based study of cisgender women residing in Chicago was completed from 2020 to 2022 using data from the Healthy Chicago Survey, which is conducted annually by the Chicago Department of Public Health. Participants included cisgender women aged 25 to 64 years with no history of hysterectomy. Respondents who self-identified as lesbian, gay, or bisexual or other than straight, lesbian, or bisexual were coded as lesbian, gay, or bisexual (LGB). Respondents who self-identified as straight were coded as heterosexual. Those who reported having a Papanicolaou test within the past 3 years were considered up-to-date with cervical cancer screening. Data analysis was performed from June to October 2023.
EXPOSURES
The primary exposure was sexual orientation. Covariates included age, income level, race, ethnicity, having a primary care practitioner (PCP), and insurance coverage.
MAIN OUTCOMES AND MEASURES
Prevalence ratios (PRs), log-based regression models, and interaction analysis were used to describe the association of sexual orientation with up-to-date screening.
RESULTS
The sample included 5167 cisgender women (447 LGB and 4720 heterosexual), aged 25 to 64 years, with no history of hysterectomy. Among LGB cisgender women, 318 (71.14%) reported previous cervical cancer screening compared with 3632 (76.95%) heterosexual cisgender women. The prevalence of up-to-date screening was 10% lower in the LGB group compared with the heterosexual group (PR, 0.90; 95% CI, 0.82-1.00). In regression analysis, having a PCP (PR, 1.43; 95% CI, 1.29-1.59) was associated with up-to-date screening. In interaction analysis, LGB cisgender women with a PCP were 93% more likely to be up-to-date compared with those without a PCP (PR, 1.93; 95% CI, 1.37-2.72).
CONCLUSIONS AND RELEVANCE
In this cross-sectional study of cervical cancer screening rates between the heterosexual and LGB populations in Chicago, up-to-date cervical cancer screening was associated with having a PCP, regardless of sexual orientation, but this association was greater for LGB individuals. Although LGB populations were less likely to be screened, this disparity may be reduced with more consistent health care access and established care with PCPs.
Topics: Humans; Female; Uterine Cervical Neoplasms; Middle Aged; Adult; Cross-Sectional Studies; Early Detection of Cancer; Retrospective Studies; Chicago; Papanicolaou Test; Sexual Behavior; Sexual and Gender Minorities
PubMed: 38709536
DOI: 10.1001/jamanetworkopen.2024.8886 -
Heliyon May 2024Cervical cancer is the third most common cancer in women both in developed and developing countries. This study aimed to determine the prevalence of cervical cancer and...
INTRODUCTION
Cervical cancer is the third most common cancer in women both in developed and developing countries. This study aimed to determine the prevalence of cervical cancer and the trends of cervical cancer screening among women who had cervical cancer screening in Suva, Fiji between 2014 and 2018.
MATERIALS AND METHOD
This study applied a 5-year retrospective electronic chart review of data from all women attending the Women's Wellness Clinic (WWC) in Suva, Fiji. The women who were selected for this study and screened for cervical cancer were Fijian citizens above 18 years of age and were registered in 2014-2018. A data collection form was used to collect data. The data was analyzed using Statistical Package for Social Sciences (SPSS) version 24; p <0.05 % was considered as the level of significance.
RESULTS
Among the 39,579 women who attended WWC for other family planning services, 12,074 women screened for cervical cancer with a prevalence of 30.5 %. The overall mean age for women screened for cervical cancer was 37.6 (SD ± 11.2). Two-thirds (76.4 %) of the women screened for cervical cancer were less than 46 years of age and 53.9 % were I-taukei. The number of women who came for Pap smear increased in 2015, however, a slight decline was observed in 2016 which was later improved to 35.1 % in 2018. Malignancy was more common in the age range of 42-49 respectively. In this study, women of 46 years and above had an OR of 0.51 (95 % CI: 0.36, 0.72), other ethnicity OR was 1.73 (95 % CI: 1.27, 2.35), and the Muslim religion OR recorded was 1.44 (95 % CI: 1.03, 2.01) which was comparatively considered a high-risk group. Women who are widowed 1.57 (95 % CI: 0.798, 3.11), single 1.29 (95 % CI: 0.87, 1.92) or divorced 1.08 (95 % CI: 0.59, 1.99), employed 1.01 (95 % CI: 0.83, 1.24) and are living in rural areas 1.19 (95 % CI: 0.82, 1.73) are also associated with higher odds of having abnormal results.
CONCLUSION
Cervical cancer is listed as the first and most common type of cancer in women which is noticeably increasing in Fiji. Even though cervical cancer screening has improved over the years, adequate surveillance systems and ongoing programs should be designed and implemented to increase awareness and monitor the trend of cervical cancer screening in order to reduce cervical cancer prevalence and mortality rates.
PubMed: 38707371
DOI: 10.1016/j.heliyon.2024.e30220 -
Journal of the American Society of... 2024Effective feedback on cytology performance relies on navigating complex laboratory information system data, which is prone to errors and lacks flexibility. As a...
INTRODUCTION
Effective feedback on cytology performance relies on navigating complex laboratory information system data, which is prone to errors and lacks flexibility. As a comprehensive solution, we used the Python programming language to create a dashboard application for screening and diagnostic quality metrics.
MATERIALS AND METHODS
Data from the 5-year period (2018-2022) were accessed. Versatile open-source Python libraries (user developed program code packages) were used from the first step of LIS data cleaning through the creation of the application. To evaluate performance, we selected 3 gynecologic metrics: the ASC/LSIL ratio, the ASC-US/ASC-H ratio, and the proportion of cytologic abnormalities in comparison to the total number of cases (abnormal rate). We also evaluated the referral rate of cytologists/cytotechnologists (CTs) and the ratio of thyroid AUS interpretations by cytopathologists (CPs). These were formed into colored graphs that showcase individual results in established, color-coded laboratory "goal," "borderline," and "attention" zones based on published reference benchmarks. A representation of the results distribution for the entire laboratory was also developed.
RESULTS
We successfully created a web-based test application that presents interactive dashboards with different interfaces for the CT, CP, and laboratory management (https://drkvcsstvn-dashboards.hf.space/app). The user can choose to view the desired quality metric, year, and the anonymized CT or CP, with an additional automatically generated written report of results.
CONCLUSIONS
Python programming proved to be an effective toolkit to ensure high-level data processing in a modular and reproducible way to create a personalized, laboratory specific cytology dashboard.
Topics: Humans; Quality Assurance, Health Care; Programming Languages; Female; Cytodiagnosis; Software; Cytology
PubMed: 38702208
DOI: 10.1016/j.jasc.2024.03.007 -
Preventive Medicine Jun 2024The fight against cervical cancer requires effective screening together with optimal and on-time treatment along the care continuum. We examined the impact of cervical...
OBJECTIVE
The fight against cervical cancer requires effective screening together with optimal and on-time treatment along the care continuum. We examined the impact of cervical cancer testing and treatment guidelines on testing practices, and follow-up adherence to guidelines.
METHODS
Data from Estonian electronic health records and healthcare provision claims for 50,702 women was used. The annual rates of PAP tests, HPV tests and colposcopies during two guideline periods (2nd version 2012-2014 vs 3rd version 2016-2019) were compared. To assess the adherence to guidelines, the subjects were classified as adherent, over- or undertested based on the timing of the appropriate follow-up test.
RESULTS
The number of PAP tests decreased and HPV tests increased during the 3rd guideline period (p < 0.01). During the 3rd guideline period, among 21-29-year-old women, the adherence to guidelines ranged from 38.7% (44.4…50.1) for ASC-US to 73.4% (62.6…84.3) for HSIL and among 30-59-year-old from 49.0% (45.9…52.2) for ASC-US to 65.7% (58.8…72.7) for ASCH. The highest rate of undertested women was for ASC-US (21-29y: 25.7%; 30-59y: 21.9%). The rates of over-tested women remained below 12% for all cervical pathologies observed. There were 55.2% (95% CI 49.7…60.8) of 21-24-year-olds and 57.1% (95% CI 53.6…60.6) of 25-29-year-old women who received HPV test not adherent to guidelines.
CONCLUSIONS
Our findings highlighted some shortcomings in guideline adherence, especially among women under 30. The insights gained from this study help to improve the quality of care and, thus, reduce cervical cancer incidence and mortality.
Topics: Humans; Female; Uterine Cervical Neoplasms; Cross-Sectional Studies; Guideline Adherence; Adult; Electronic Health Records; Middle Aged; Early Detection of Cancer; Papanicolaou Test; Vaginal Smears; Estonia; Colposcopy; Papillomavirus Infections; Mass Screening
PubMed: 38701952
DOI: 10.1016/j.ypmed.2024.107982 -
The New Microbiologica May 2024Human papilloma virus (HPV) is the most common sexually transmitted viral agent in the world and the most common cause of cervical cancer. HPV prevalence and genotype...
Human papilloma virus (HPV) is the most common sexually transmitted viral agent in the world and the most common cause of cervical cancer. HPV prevalence and genotype distribution vary by region and demographic data. In a province in the south of Turkey that constantly receives immigration, we aimed to determine the prevalence of high-risk HPV (HR-HPV) genotypes, evaluate the compatibility between cervical Pap smear cytology results patients and HR-HPVs, and make an up-to-date contribution to the elucidation of epidemiological data. In this single-centre study, a total of 12,641 women aged 18 and over were evaluated retrospectively from January 2019 to July 2022. HPV detection and genotyping were analysed by the PCR method. Bethesda scoring was used for Pap smear cytological evaluation. The overall prevalence of HR-HPV was 12.6% (12.7% in Turkish women, 11.2% in foreign women). Among the typed HPVs that were detected, HPV-16 (31%) was found first, followed by HPV-18 (8%). The prevalence of HR-HPV was higher in women with abnormal cytology (977/1762, 55.4%) than in women with normal cytology (620/10879, 5.7%) (p<0.001). Turkey doesn't yet have a national HPV immunisation program. We think that determining the specific regional frequency of other HR-HPVs separately will be useful in the follow-up of the natural course of the type-specific infection and in vaccine studies in the future.
Topics: Humans; Female; Turkey; Adult; Papillomavirus Infections; Papillomaviridae; Middle Aged; Genotype; Emigrants and Immigrants; Young Adult; Retrospective Studies; Adolescent; Cervix Uteri; Prevalence; Aged; Vaginal Smears; Papanicolaou Test; Uterine Cervical Neoplasms; Human Papillomavirus Viruses
PubMed: 38700888
DOI: No ID Found