Enhancing cervical cancer detection and robust classification through a fusion of deep learning models.

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.

Correlation between high-risk HPV infection and p16/Ki-67 abnormalities in Pap samples in a South Eastern Europe cohort.

Cervical cancer (CC) is the fourth most common cause of cancer-related deaths amongst women worldwide. CC represents a major global healthcare issue, and Romania ranks the worst in mortality rates amongst EU countries. However, the early detection of CC can be lifesaving. To understand the testing process undergone by women in Romania, we performed a retrospective study, and investigated a cohort of 83 785 cervical cases from Romanian women aged 15-70, obtained in private-based opportunistic screening. We examined the correlation between Pap smear results, human papilloma virus (HPV) genotyping, and the expression of cell cycle markers p16 and Ki-67. Analysis of Pap results revealed approximately 10% abnormal cases, of which high-grade squamous intraepithelial lesions constituted 4.9%. HPV genotyping of 12 185 cases with available Pap results unveiled a range of high-risk HPV (hrHPV) types associated with cervical abnormalities. Notably, 26% of hrHPV-positive cases showed no observable abnormalities. In a subset of cases with abnormal Pap and a type of hrHPV, P16/Ki-67 double-staining was also positive. This study suggests the importance of an integrated diagnostic algorithm that should consider the HPV genotype, Pap smear, and p16/Ki-67 staining. This algorithm should enhance the CC screening accuracy and its management strategies, particularly in those regions with a high disease burden, such as Romania.

Improving cervical cancer classification in PAP smear images with enhanced segmentation and deep progressive learning-based techniques.

OBJECTIVE: Cervical cancer, a prevalent and deadly disease among women, comes second only to breast cancer, with over 700 daily deaths. The Pap smear test is a widely utilized screening method for detecting cervical cancer in its early stages. However, this manual screening process is prone to a high rate of false-positive outcomes because of human errors. Researchers are using machine learning and deep learning in computer-aided diagnostic tools to address this issue. These tools automatically analyze and sort cervical cytology and colposcopy images, improving the precision of identifying various stages of cervical cancer. METHODOLOGY: This article uses state-of-the-art deep learning methods, such as ResNet-50 for categorizing cervical cancer cells to assist medical professionals. The method includes three key steps: preprocessing, segmentation using k-means clustering, and classifying cancer cells. The model is assessed based on performance metrics viz; precision, accuracy, kappa score, precision, sensitivity, and specificity. In the end, the high success rate shows that the ResNet50 model is a valuable tool for timely detection of cervical cancer. OUTPUTS: In conclusion, the infected cervical region is pinpointed using spatial K-means clustering and preprocessing operations. This sequence of actions is followed by a progressive learning technique. The Progressive Learning technique then proceeded through several stages: Stage 1 with 64 × 64 images, Stage 2 with 224 × 224 images, Stage 3 with 512 × 512 images, and the final Stage 4 with 1024 × 1024 images. The outcomes show that the suggested model is effective for analyzing Pap smear tests, achieving 97.4% accuracy and approx. 98% kappa score.

Atypical glandular cells in Pap tests: cytology-histology correlation and risk assessment with human papillopmavirus (HPV) testing.

INTRODUCTION: Atypical glandular cells (AGC) represent less than 1% of Pap test cases and include a variety of lesions in both the cervix and endometrium. The study aimed to investigate the cytology-histology correlation in AGC patients and to evaluate the clinical utility of hrHPV testing in this diagnostic context. MATERIALS AND METHODS: We identified 491 atypical glandular cells (AGC) cases in our quality analysis (QA) database of 336,064 Pap tests interpreted between March 1, 2013 and July 12, 2016. Of these, 251 cases had follow-up biopsies with hrHPV tests in 148 cases. RESULTS: The most common histologic diagnosis associated with AGC was normal/benign or low-grade lesions, comprising 55% of cervical biopsies and 24% of endometrial biopsies. High-grade lesions were identified in 21% of follow-up biopsies. In patients with AGC cytology, a positive hrHPV test significantly increased the likelihood of cervical HSIL or above lesions on biopsy by 26.4 times (OR = 26.4, 95% CI: 5.8-119.4, P < 0.0001). A positive genotyping result for HPV 16 dramatically increased the likelihood of cervical HSIL or above lesions on biopsy (OR = 84, 95% CI: 12.0-590.5, P < 0.0001). The HPV test had a negative predictive value of 97% (CI: 85%-100%). CONCLUSIONS: Our study confirms that AGC is a significant diagnosis with an overall risk for high-grade cervical or endometrial lesions as high as 21%. hrHPV testing with genotyping is an effective tool for identifying high-risk individuals within the AGC population, with excellent positive and negative predictive values. This approach is valuable for clinical risk stratification and differential diagnosis in patients with AGC cytology.

Overlapping cytoplasms segmentation via constrained multi-shape evolution for cervical cancer screening.

Segmenting overlapping cytoplasms in cervical smear images is a clinically essential task for quantitatively measuring cell-level features to screen cervical cancer This task, however, remains rather challenging, mainly due to the deficiency of intensity (or color) information in the overlapping region Although shape prior-based models that compensate intensity deficiency by introducing prior shape information about cytoplasm are firmly established, they often yield visually implausible results, as they model shape priors only by limited shape hypotheses about cytoplasm, exploit cytoplasm-level shape priors alone, and impose no shape constraint on the resulting shape of the cytoplasm In this paper, we present an effective shape prior-based approach, called constrained multi-shape evolution, that segments all overlapping cytoplasms in the clump simultaneously by jointly evolving each cytoplasm's shape guided by the modeled shape priors We model local shape priors (cytoplasm-level) by an infinitely large shape hypothesis set which contains all possible shapes of the cytoplasm In the shape evolution, we compensate intensity deficiency for the segmentation by introducing not only the modeled local shape priors but also global shape priors (clump-level) modeled by considering mutual shape constraints of cytoplasms in the clump We also constrain the resulting shape in each evolution to be in the built shape hypothesis set for further reducing implausible segmentation results We evaluated the proposed method in two typical cervical smear datasets, and the extensive experimental results confirm its effectiveness.

Predictive Value of Various Atypical Cells for the Detection of Human Papillomavirus in Cervical Smears.

It is thought that numerous genotypes of human papillomavirus (HPV) are associated with various atypical cells, such as multinucleated cells, koilocytes, binucleated cells, parakeratotic cells, and giant cells, in the cervix. We previously showed the specificity of HPV genotypes for koilocytes and multinucleated cells. Therefore, in this study, we analyzed the association among HPV genotypes and binucleated cells, parakeratotic cells, and giant cells in Papanicolaou (Pap) smears. We detected HPV genotypes and atypical cells in 651 cases of liquid-based cytology with an abnormal Pap smear. The HPV genotypes associated with atypical cells were evaluated using stepwise logistic regression with backward elimination and a likelihood ratio test for model construction. Polymerase chain reaction was used to determine the HPV genotypes in whole liquid-based cytology samples and microdissected cell samples from Pap smear slides. Binucleated cells were significantly associated with HPV genotype 42. Moreover, parakeratotic cells were significantly associated with certain HPV genotypes, such as HPV40. However, it was difficult to detect specific HPV genotypes by the manual microdissection-polymerase chain reaction method despite the presence of binucleated cells and parakeratotic cells. Thus, the presence of binucleated cells, parakeratotic cells, and giant cells in Pap smears may not be predictive of cervical lesions above low-grade squamous intraepithelial lesions or infection with highly carcinogenic HPV genotypes.

Navigating Practice Issues Related to the Unsatisfactory Cervicovaginal Papanicolaou Test: Survey Results of Laboratories Participating in the 2020 College of American Pathologists PAP Education Program.

CONTEXT.­: Unsatisfactory Papanicolaou (Pap) tests pose a unique set of challenges to the laboratory with regard to their processing, review, reporting, and performance of human papillomavirus (HPV) testing. There are no standardized guidelines for the review process and handling of unsatisfactory Pap tests. OBJECTIVE.­: To assess the current practice patterns regarding various aspects of the unsatisfactory Pap test, from processing to reporting, across laboratories worldwide. DESIGN.­: A supplemental questionnaire was mailed to laboratories participating in the 2020 College of American Pathologists (CAP) Gynecologic Cytopathology (PAP Education) Program, requesting data regarding the unsatisfactory Pap test. RESULTS.­: Of 1520 participating laboratories, 619 (40.7%) responded, and the responses of 577 laboratories were included for further analysis. Only 64.6% (373 of 577) laboratories used the unsatisfactory Pap test criteria as specified by the 2014 Bethesda System. About three-quarters of the respondents (433 of 576; 75.2%) routinely rescreened unsatisfactory Pap tests. Routine repreparation of such Pap tests was performed by 54.9% (316 of 576) of laboratories, and 52.0% (293 of 563) used glacial acetic acid for repreparing excessively bloody specimens. HPV test results were reported for unsatisfactory Pap tests, always or sometimes, by 62.4% (353 of 566) of respondents. CONCLUSIONS.­: This CAP survey reveals important information regarding the practice patterns pertaining to several aspects of the unsatisfactory Pap test. It also provides valuable insight into the quality assurance measures that can be implemented for such tests. Future studies can further aid in the standardization of all components of the handling of unsatisfactory Pap tests for overall quality improvement.

Cervical Cancer Classification From Pap Smear Images Using Deep Convolutional Neural Network Models.

As one of the most common female cancers, cervical cancer often develops years after a prolonged and reversible pre-cancerous stage. Traditional classification algorithms used for detection of cervical cancer often require cell segmentation and feature extraction techniques, while convolutional neural network (CNN) models demand a large dataset to mitigate over-fitting and poor generalization problems. To this end, this study aims to develop deep learning models for automated cervical cancer detection that do not rely on segmentation methods or custom features. Due to limited data availability, transfer learning was employed with pre-trained CNN models to directly operate on Pap smear images for a seven-class classification task. Thorough evaluation and comparison of 13 pre-trained deep CNN models were performed using the publicly available Herlev dataset and the Keras package in Google Collaboratory. In terms of accuracy and performance, DenseNet-201 is the best-performing model. The pre-trained CNN models studied in this paper produced good experimental results and required little computing time.

Genomic instability analysis in DNA from Papanicolaou test provides proof-of-principle early diagnosis of high-grade serous ovarian cancer.

Late diagnosis and the lack of screening methods for early detection define high-grade serous ovarian cancer (HGSOC) as the gynecological malignancy with the highest mortality rate. In the work presented here, we investigated a retrospective and multicentric cohort of 250 archival Papanicolaou (Pap) test smears collected during routine gynecological screening. Samples were taken at different time points (from 1 month to 13.5 years before diagnosis) from 113 presymptomatic women who were subsequently diagnosed with HGSOC (pre-HGSOC) and from 77 healthy women. Genome instability was detected through low-pass whole-genome sequencing of DNA derived from Pap test samples in terms of copy number profile abnormality (CPA). CPA values of DNA extracted from Pap test samples from pre-HGSOC women were substantially higher than those in samples from healthy women. Consistently with the longitudinal analysis of clonal pathogenic TP53 mutations, this assay could detect HGSOC presence up to 9 years before diagnosis. This finding confirms the continual shedding of tumor cells from fimbriae toward the endocervical canal, suggesting a new path for the early diagnosis of HGSOC. We integrated the CPA score into the EVA (early ovarian cancer) test, the sensitivity of which was 75% (95% CI, 64.97 to 85.79), the specificity 96% (95% CI, 88.35 to 100.00), and the accuracy 81%. This proof-of-principle study indicates that the early diagnosis of HGSOC is feasible through the analysis of genomic alterations in DNA from endocervical smears.

Privacy Preserved Cervical Cancer Detection Using Convolutional Neural Networks Applied to Pap Smear Images.

Image processing has enabled faster and more accurate image classification. It has been of great benefit to the health industry. Manually examining medical images like MRI and X-rays can be very time-consuming, more prone to human error, and way more costly. One such examination is the Pap smear exam, where the cervical cells are examined in laboratory settings to distinguish healthy cervical cells from abnormal cells, thus indicating early signs of cervical cancer. In this paper, we propose a convolutional neural network- (CNN-) based cervical cell classification using the publicly available SIPaKMeD dataset having five cell categories: superficial-intermediate, parabasal, koilocytotic, metaplastic, and dyskeratotic. CNN distinguishes between healthy cervical cells, cells with precancerous abnormalities, and benign cells. Pap smear images were segmented, and a deep CNN using four convolutional layers was applied to the augmented images of cervical cells obtained from Pap smear slides. A simple yet efficient CNN is proposed that yields an accuracy of 0.9113% and can be successfully used to classify cervical cells. A simple architecture that yields a reasonably good accuracy can increase the speed of diagnosis and decrease the response time, reducing the computation cost. Future researchers can build upon this model to improve the model's accuracy to get a faster and more accurate prediction.

Changes over time in papanicolaou cytology test and HPV test in a large women's academic center laboratory.

INTRODUCTION: In the past 2 decades, cervical cancer screening guidelines in the United States have undergone numerous revisions with recent greater emphasis on primary high-risk human papillomavirus (hrHPV) testing. MATERIALS AND METHODS: We examine the trends of Papanicolaou test and hrHPV testing at our large academic center across 4 years (2006, 2011, 2016, and 2021) over a 15-year period. The number of ThinPrep Papanicolaou and hrHPV tests, as well as the triggers for HPV testing, were retrospectively analyzed. RESULTS: A total of 308,355 Papanicolaou tests and 117,477 hrHPV tests were reported across the 4 years. The number of Papanicolaou tests performed decreased nearly 3-fold over the study period, with only 43,230 Papanicolaou tests performed in 2021. The HPV test to Papanicolaou test ratio increased: 17% of Papanicolaou tests had an associated HPV test in 2006, whereas 72% of Papanicolaou tests ordered in 2021 had a companion hrHPV. The use of co-testing also increased. Overall, 73% were co-tests and 27% were reflexively ordered in the 4 one-year time periods. Co-tests constituted only 46% of HPV tests in 2006, but this increased to 93% in 2021. The percentage of positive hrHPV results decreased; in 2006, 18.3% of cases were positive, dropping to 8.6% in 2021 due to the marked increase in co-testing. Stratifying by diagnostic category, hrHPV results have remained relatively constant. CONCLUSION: With the numerous recent revisions of cervical screening guidelines, screening strategies at our institution reflected these changes in clinical practice. Papanicolaou and HPV co-testing became the most common screening method for women 30 to 65 years of age in our cohort.

HDFCN: A Robust Hybrid Deep Network Based on Feature Concatenation for Cervical Cancer Diagnosis on WSI Pap Smear Slides.

Cervical cancer is a critical imperilment to a female's health due to its malignancy and fatality rate. The disease can be thoroughly cured by locating and treating the infected tissues in the preliminary phase. The traditional practice for screening cervical cancer is the examination of cervix tissues using the Papanicolaou (Pap) test. Manual inspection of pap smears involves false-negative outcomes due to human error even in the presence of the infected sample. Automated computer vision diagnosis revamps this obstacle and plays a substantial role in screening abnormal tissues affected due to cervical cancer. Here, in this paper, we propose a hybrid deep feature concatenated network (HDFCN) following two-step data augmentation to detect cervical cancer for binary and multiclass classification on the Pap smear images. This network carries out the classification of malignant samples for whole slide images (WSI) of the openly accessible SIPaKMeD database by utilizing the concatenation of features extracted from the fine-tuning of the deep learning (DL) models, namely, VGG-16, ResNet-152, and DenseNet-169, pretrained on the ImageNet dataset. The performance outcomes of the proposed model are compared with the individual performances of the aforementioned DL networks using transfer learning (TL). Our proposed model achieved an accuracy of 97.45% and 99.29% for 5-class and 2-class classifications, respectively. Additionally, the experiment is performed to classify liquid-based cytology (LBC) WSI data containing pap smear images.

HPV Cotesting of Unsatisfactory Papanicolaou Tests: Implications for Follow-up Intervals.

OBJECTIVES: The 2019 American Society of Colposcopy and Cervical Pathology management guidelines recommend that patients with an unsatisfactory Papanicolaou (Pap) test (UPT) and negative human papillomavirus (HPV) cotest undergo repeat age-based screening in 2 to 4 months. The rationale is that a negative HPV test in the setting of an UPT may reflect an inadequate sample and therefore should not be interpreted as truly "negative." For patients 25 years and older who are cotested, if HPV is positive for the 16 or 18 genotypes, direct referral for colposcopy is recommended. Our study aimed to determine if a negative HPV cotest result is predictive of the absence of a high-grade squamous intraepithelial lesion (HSIL) and whether these patients may be called back for repeat testing at an interval longer than 2 to 4 months. METHODS: Follow-up cervical cytology and biopsy results in women with UPT and HPV cotests from January 2017 to December 2021 were collected. Original UPT and HPV cotest results were correlated with the follow-up Pap and biopsy results. RESULTS: There were 1,496 (2.28%) UPT cases out of 65,641 total Pap tests. Among the 1,496 UPT cases, 1,010 (67.5%) had HPV cotesting; 676 (45.1%) were followed by repeat Pap or biopsy within 4 months and 850 (56.8%) within 12 months. The total follow-up rate was 81%, with a range of 3 days to 36 months. The HSIL rate in HPV-positive cases was 5.7% (3/53) vs 0.4% (2/539) (P = .006) in HPV-negative cases. In UPT, HPV cotesting showed negative predictive values for low-grade and high-grade squamous intraepithelial lesion detection of 98.5% and 99.6%, respectively, while positive predictive values were 19% and 5.7%. CONCLUSIONS: A negative HPV cotest in individuals with UPT predicted the lack of HSIL in our study. Compliance with the recommended follow-up time of 2 to 4 months for women with UPT was low (45.1%). Our study suggests that women with UPT and negative HPV cotest may be safely called back at an interval longer than 4 months.

Artificial Intelligence-driven Digital Cytology-based Cervical Cancer Screening: Is the Time Ripe to Adopt This Disruptive Technology in Resource-constrained Settings? A Literature Review.

Cervical cancer is still a public health scourge in the developing countries due to the lack of organized screening programs. Though liquid-based cytology methods improved the performance of cervical cytology, the interpretation still suffers from subjectivity. Artificial intelligence (AI) algorithms have offered objectivity leading to better sensitivity and specificity of cervical cancer screening. Whole slide imaging (WSI) that converts a glass slide to a virtual slide provides a new perspective to the application of AI, especially for cervical cytology. In the recent years, there have been a few studies employing various AI algorithms on WSI images of conventional or LBC smears and demonstrating differing sensitivity/specificity or accuracy at detection of abnormalities in cervical smears. Considering the interest in AI-based screening modalities, this well-timed review intends to summarize the progress in this field while highlighting the research gaps and providing future research directions.

Knowledge, attitudes, and practice of the Pap smear test in female college students attending a global university in the United States.

BACKGROUND: According to the World Health Organization, every minute, one woman is diagnosed with cervical cancer, and every 2 minutes, one woman dies of cervical cancer globally (World Health Organization, 2022). The biggest tragedy is 99% of cervical cancer is caused by a preventable sexually transmitted infection known as human papilloma virus (World Health Organization, 2022). LOCAL PROBLEM: Many US universities indicate approximately 30% of their admissions are international students. The lack of Pap smear screening in this population has not been clearly identified by college health care providers. METHODS: Fifty-one participants from a university located in the northeastern United States completed an online survey between September and October 2018. The survey was designed to identify disparities between United States residents and internationally admitted female students in their knowledge, attitudes, and practice of the Pap smear test. INTERVENTIONS: One hundred percent of US students had heard of the Pap smear test as compared with 72.7% of international students ( p = .008); 86.8% of US students considered a Pap smear as opposed to 45.5% of international students ( p = .002), and 65.8% of US students previously had a Pap smear test as opposed to 18.8% of international students ( p = .007). RESULTS: Results revealed statistically significant differences between US and internationally admitted female college students in knowledge, attitudes, and practice of the Pap smear test. CONCLUSIONS: This project helps to bring awareness to college health clinicians the need for cervical cancer education and Pap smear screening for our college age international female population.

Atitudes e crenças de médicos ginecologistas- -obstetras e de pacientes do Hospital Universitário de Brasília sobre o rastreamento cervical e o exame pélvico / Attitudes and beliefs of obstetrician-gynecologists and patients at the University Hospital of Brasília about cervical screening and pelvic examination

Objetivo: Avaliar as atitudes e crenças de pacientes e médicos ginecologistas-obstetras sobre o rastreamento cervical e o exame pélvico no Hospital Universitário de Brasília (HUB). Métodos: Foram realizadas entrevistas com pacientes que aguardavam por uma consulta previamente agendada no ambulatório de ginecologia e com médicos ginecologistas-obstetras que atuavam no HUB. Cada grupo respondeu a um questionário que enfocava a realização do rastreamento cervical e do exame pélvico (EP). Resultados: No total, 387 pacientes responderam ao questionário. Dessas, apenas 4,13% sabiam que, de acordo com as diretrizes brasileiras, o rastreamento cervical deveria ser iniciado aos 25 anos de idade, 5,17% sabiam que ele deveria ser encerrado aos 64 anos e 97,93% esperavam um intervalo menor do que o trienal recomendado. Após serem informadas sobre as diretrizes, 66,93% acreditavam que o início aos 25 anos é tardio, 61,5%, que o encerramento aos 64 anos é precoce, 88,37%, que o intervalo trienal é muito longo e 94,06% ficaram com receio de que problemas de saúde pudessem aparecer nesse intervalo. Dos 44 médicos que responderam ao questionário, embora a maioria concordasse com as diretrizes, somente 31,82%, 38,64% e 34,1% as seguia com relação à frequência, à idade de início e à idade de encerramento, respectivamente. Quanto ao EP, aproximadamente metade dos participantes de cada grupo considerava que o exame deveria ser realizado nas consultas regulares com o ginecologista. Conclusão: Foi observada uma discrepância entre as expectativas das pacientes e as diretrizes para o rastreamento de câncer cervical. A maior parte das pacientes não as conhecia e, quando informadas, não concordava com elas. Quanto aos médicos ginecologistas- obstetras, a maioria não as seguia, apesar de conhecê-las. Quanto ao EP, grande parte dos médicos e pacientes considerava-o importante e acreditava que ele deveria ser realizado de forma rotineira nas consultas ginecológicas.

Objective: Evaluate the attitudes and beliefs of patients and obstetrician-gynecologists about cervical screening and pelvic examination in the University Hospital of Brasília (HUB). Methods: Face-to-face interviews with patients waiting for a previously scheduled consultation at the gynecology outpatient clinics and attending obstetrician-gynecologists at the HUB. Each group answered a questionnaire addressing cervical screening and pelvic examination (PE). Results: 387 patients answered the questionnaire. Of these, only 4.13% were aware that, according to Brazilian guidelines, cervical screening should begin at age 25, 5.17% that it should stop at age 64 and 97.93% expected a shorter interval than the recommended triennial. After being informed of the guidelines, 66.93% believed that starting at age 25 is late, 61.5% that stopping at 64 is early, 88.37% that the triennial interval is too long, and 94.06% would be afraid that health problems could appear during the interval. Of the 44 participating physicians, although most agreed with the guidelines, only 31.82%, 38.64% and 34.1% followed them regarding frequency, starting and stopping age, respectively. As for EP, approximately half of the participants in each group believed that it should be performed in regular consultations with the gynecologist. Conclusion: There was a discrepancy between patients' expectations and cervical screening guidelines. Most patients didn't know and, when informed, didn't agree with them. As for Ob-Gyn physicians, most did not follow these guidelines, despite knowing them. As for pelvic exam, most physicians and patients considered it important and believed it should be routinely performed during gynecological consultations.

Nucleus segmentation and classification using residual SE-UNet and feature concatenation approach incervical cytopathology cell images.

Introduction: Pap smear is considered to be the primary examination for the diagnosis of cervical cancer. But the analysis of pap smear slides is a time-consuming task and tedious as it requires manual intervention. The diagnostic efficiency depends on the medical expertise of the pathologist, and human error often hinders the diagnosis. Automated segmentation and classification of cervical nuclei will help diagnose cervical cancer in earlier stages. Materials and Methods: The proposed methodology includes three models: a Residual-Squeeze-and-Excitation-module based segmentation model, a fusion-based feature extraction model, and a Multi-layer Perceptron classification model. In the fusion-based feature extraction model, three sets of deep features are extracted from these segmented nuclei using the pre-trained and fine-tuned VGG19, VGG-F, and CaffeNet models, and two hand-crafted descriptors, Bag-of-Features and Linear-Binary-Patterns, are extracted for each image. For this work, Herlev, SIPaKMeD, and ISBI2014 datasets are used for evaluation. The Herlev datasetis used for evaluating both segmentation and classification models. Whereas the SIPaKMeD and ISBI2014 are used for evaluating the classification model, and the segmentation model respectively. Results: The segmentation network enhanced the precision and ZSI by 2.04%, and 2.00% on the Herlev dataset, and the precision and recall by 0.68%, and 2.59% on the ISBI2014 dataset. The classification approach enhanced the accuracy, recall, and specificity by 0.59%, 0.47%, and 1.15% on the Herlev dataset, and by 0.02%, 0.15%, and 0.22% on the SIPaKMed dataset. Conclusion: The experiments demonstrate that the proposed work achieves promising performance on segmentation and classification in cervical cytopathology cell images..

Interpretable pap-smear image retrieval for cervical cancer detection with rotation invariance mask generation deep hashing.

Cervical cancer is a common disease in women, affecting their lives negatively and often resulting in death. Pap-smear tests are preferred by doctors as the primary tool in the early diagnosis and treatment of the disease. Physicians can be facilitated in the detection of five different categories of cervical cancer and similar cellular disease cases with the Pap-smear image retrieval technology. In this study, an algorithm for retrieval of cervical cancer images using hash coding with a Convolutional Neural Network (CNN) has been implemented. A sensitive deep hashing method combining interpretable mask generation and rotation invariance is proposed for cervical cancer detection. The distinctive features of cervical cancer cells with complex morphological features are focused on with the proposed hybrid dilated convolution spatial attention module and insignificant features are eliminated. Moreover, the loss function of Cauchy rotation invariance in terms of cervical cancer cell target is presented. In this way, the differences in the input samples are revealed, allowing the CNN to learn from different angles and achieve certain rotation invariance. The versatility and performance of the proposed method, as well as the efficiency of the loss function, have been tested on the SIPaKMeD and Mendeley LBC datasets consisting of cervical cancer images. In the experimental results obtained, it is shown that the proposed spatial attention module and rotational invariance deep hashing network generate high performance in cervical cancer image retrieval problems.

Human papillomavirus 16/18/45 are not the most frequent genotypes in African American women: analysis in cervical Papanicolaou smears of women in an inner-city hospital.

INTRODUCTION: Cervical cancer is considered the most common human papillomavirus (HPV)-associated disease in women. Primary and secondary prevention methods have been established through Pap tests, HPV molecular testing, and vaccines. Although the most common high-risk HPV (HR-HPV) genotypes in the United States are 16, 18, and 45, there is reported ethnic disparity in the distribution of these genotypes. MATERIALS AND METHODS: Data analysis of HPV genotype results on cervical pap tests in our institution between late 2018 and early 2020 was performed. The distribution of HPV genotypes in each Bethesda category was evaluated. RESULTS: A total of 13,160 smears were evaluated; 75.5% were from African American women. Of those tested for HR-HPV (10,060), 1412 (14%) were HR-HPV positive. In all diagnostic categories of the Bethesda classification system, non-16/18/45 HR-HPV genotypes were more prevalent, ranging from 60.8% even in high-grade squamous intraepithelial lesion to 90.4% in negative for intraepithelial lesion or malignancy. CONCLUSIONS: In this study with a predominantly African American population, non-16/18/45 HR-HPV genotypes were prevalent in the majority (60.8%) of high-grade squamous intraepithelial lesion cases. Ethnic variability should be considered when deciding which HPV genotypes to integrate into the HPV vaccine.