Diagnostics Of Cervical Cancer Research Articles

The Prominence of the Broad-Spectrum Protease inhibitor gene A2ML1 as a potential biomarker in cervical cancer diagnostics using Immunotherapeutic and Multi-Omics approaches

One of the venereal tumors that threaten human life is cervical cancer. A2ML1 is detected in advanced-stage cancer patients and is found to be strongly associated with cervical cancer. A2ML1 was shown to be substantially expressed in cervical cancer in this study, which used data from the TCGA database. Those with high A2ML1 expression had a lower chance of survival than patients with low A2ML1 expression. Both univariate and multivariate Cox regression analyses were utilized to investigate the relationship between clinical variables and overall survival rates. An investigation into the link between A2ML1 and immune infiltration was subsequently conducted. Utilizing the immune cell database, research was conducted to investigate the dispersion of 24 immune cells and their correlation to A2ML1 expression. In addition to this, the favorable correlation between immune cells and A2ML1 was validated using all three immune cell methodologies. The Genomics of Drug Sensitivity in Cancer database was used to confirm the idea that there is a link between A2ML1 expression and the efficacy of chemotherapy or immunotherapy. The findings demonstrated that A2ML1 is a potential biomarker for cervical cancer diagnostics. This biomarker may be used to chaperone immunotherapy, as well as to explain the elucidates of cervical cancer caused by the immunological microenvironment.

CINNAMON-GUI: Revolutionizing Pap Smear Analysis with CNN-Based Digital Pathology Image Classification

Background Medical imaging has seen significant advancements through machine learning, particularly convolutional neural networks (CNNs). These technologies have transformed the analysis of pathological images, enhancing the accuracy of diagnosing and classifying cellular anomalies. Digital pathology methodologies, including image analysis, have improved cervical cancer diagnostics. However, existing commercial platforms are often costly and restrictive, limiting customization and scalability. Methods CINNAMON-GUI is an open-source digital pathology tool based on CNNs for classifying Pap smear images. Transitioning to a Shiny app in Python, it offers enhanced user interface and interactivity. The application supports dynamic web interactions, advanced features for image analysis, and state-of-the-art CNN models tailored for digital pathology. Key features include intuitive UI components, real-time image and plot generation, memory-efficient data handling, and robust training capabilities with customizable CNN architectures. The tool also integrates with Labelme for defining regions of interest and allows testing on external biospecimens. Results Model A (seed 42, 100 epochs) and Model B (same architecture with adjusted augmentation parameters) were compared. Model A stabilized with training accuracy around 0.88 and validation accuracy around 0.913. Model B showed improved performance with training accuracy around 0.91 and validation accuracy around 0.95. Feature mapping highlighted critical morphological aspects, improving classification accuracy. Model B reduced misclassification errors significantly compared to Model A. Conclusions CINNAMON-GUI demonstrates the potential of an open-source platform in digital pathology, providing transparency and collaborative opportunities. The tool enhances diagnostic accuracy through feature map analysis and optimized CNN training. Future development aims to extend its application to other cancer types, leveraging its dynamic and user-friendly interface for broader use in diagnostics.

Simultaneous immunodetection of multiple cervical cancer biomarkers based on a signal-amplifying redox probes/polyethyleneimine-coated gold nanoparticles/2D tungsten disulfide/graphene oxide nanocomposite platform

To advance cervical cancer diagnostics, we propose a state-of-the-art label-free electrochemical immunosensor designed for the simultaneous detection of multiple biomarker proteins (p16INK4a, p53, and Ki67). This immunosensor is constructed using a polyethyleneimine-coated gold nanoparticles/2D tungsten disulfide/graphene oxide (PEI-AuNPs/2D WS2/GO) composite-modified three-screen-printed carbon electrode (3SPCE) array. The 2D WS2/GO hybrid provides a large specific surface area for supporting well-dispersed PEI-AuNPs and adsorbed redox-active species, enhancing overall performance. The PEI-AuNPs-decorated 2D WS2/GO composite not only improves electrode conductivity but also increases the antibody loading capacity. Redox-active species, including Cd2+ ions, 2,3-diaminophenazine (DAP), and methylene blue (MB), serve as distinct signaling compounds to quantitatively detect the cervical cancer biomarkers p16INK4a, p53, and Ki67, respectively. Additionally, the immunosensor demonstrates the detection with high sensitivity, good storage stability, high selectivity, and acceptable reproducibility. This immunosensor demonstrates a good linear relationship with the logarithm of protein concentrations. Additionally, the immunosensor also demonstrates high sensitivity, good storage stability, high selectivity, and acceptable reproducibility. Our promising results and the successful application of the immunosensor in detecting three tumor markers in human serum highlight its potential for clinical diagnosis of cervical cancer.

Revolutionizing HPV Detection: Unveiling a Novel Electrochemical Immunosensor for Ultra-Sensitive HPV16 E7 Oncoprotein Detection Based on Gold-Graphitic Carbon Nitride Nanocomposite

Cervical cancer (CC), a significant contributor to the mortality of females globally, manifests an annual incidence of 500,000 cases and is predominantly linked to the human papillomavirus (HPV) infection. The pressing demand for affordable and user-friendly assays for CC detection is highlighted by the limited availability and dependability of diagnostic screening tools, especially in developing countries. In response to the critical need for enhanced cervical cancer diagnostics, we present an innovative electrochemical immunosensor designed for the selective detection of the HPV 16-E7 oncoprotein. The immunosensing platform is constructed from a gold-graphitic carbon nitride (Au-g-C3N4) nanocomposite, with antibodies immobilized through a physical adsorption process onto the sensing platform. Employing Square Wave Voltammetry (SWV), we systematically evaluated the antigen-antibody interaction, achieving ultrasensitive detection of E7 with ferric/ferrocyanide. The linear detection range of the proposed sensor for E7 antigen is 0.01 fg ml−1 to 1 ng ml−1, assuming ideal conditions and an impressive Limit of Detection (LOD) of 0.0065 fg ml−1. The accuracy of the proposed immunosensor was effectively evaluated in contrast to Enzyme linked immunosorbent assay (ELISA). Finally, the proposed immunosensor exhibited favourable selectivity, sensitivity, and reproducibility upon introduction to clinical samples, thereby validating its potential suitability for point-of-care testing aimed at the timely detection of CC.

Fabrication of cervical squamous cell carcinoma antigen immunosensor using graphene-polymer composites

An ultrasensitive electrochemical immunosensor was developed for detection of the cervical squamous cell carcinoma antigen (SCCA) biomarker using graphene-chitosan nanocomposites. Graphene oxide (GO) synthesized by a modified Hummer’s method was functionalized with chitosan biopolymer (CS) to produce CS-GO nanocomposites. Characterization by SEM, FTIR, Raman, XPS confirmed successful grafting of CS onto GO by electrostatic interactions. The CS-GO composite exhibited improved conductivity and biocompatibility. After optimizing the GO:CS ratio to 1:1, the nanocomposite was deposited on glassy carbon electrodes (GCE). Anti-SCCA antibodies were then immobilized covalently using pyrenebutyric acid crosslinker. The immunosensor fabrication was analyzed by EIS, CV, and DPV electrochemical techniques. The conditions including CS-GO ratio, antibody concentration, incubation time, pH, and voltage parameters were systematically optimized using orthogonal experimental design. Under optimal conditions, the immunosensor showed a linear detection range from 1 pg/mL to 100 ng/mL with a sensitivity of 196 μA/(ng/mL/cm2). The low limit of detection of 1 pg/mL was attributed to the high surface area and conductivity of the CS-GO transducer. Analysis of human serum samples spiked with SCCA demonstrated the reliability of the immunosensor for clinical applications. The graphene-nanocomposite electrochemical biosensing platform provides a rapid, low-cost, and ultrasensitive alternative to ELISA for SCCA detection in cervical cancer diagnostics.

Magnetic resonance imaging in cervical cancer: current opportunities of radiomics analysis and prospects for its further developmen

Introduction. Due to the dynamic development of modern imaging technologies in recent years, much attention has been paid to radiomics particularly texture analysis. The complexity of clinically evaluated tumor procession in cervical cancer (CC) accounts for a need to expand knowledge on applying medical imaging technologies in oncologic diagnostics spanning from predominantly qualitative analysis to a multiparametric approach, including a quantitative assessment of study parameters.Aim: to analyze the literature data on the use of radiomics and image texture analysis in diagnostics and prediction of aggressiveness of oncogynecological diseases including СС.Materials and Methods. A 2016–2023 systematic literature search was carried out in the PubМed/MEDLINE, eLibrary, Scopus databases, NCCN, ESUR, ACR resources. All publications on radiomics and image texture analysis used in CC diagnostics and prediction were investigated, with queries for key words and phrases in Russian and English: «cervical cancer», «radiomics»,«texture analysis», «oncology». The study included full-text sources and literature reviews on the study subject. Duplicate publications were excluded.Results. The features and advantages of using radiomics and image texture analysis in CC diagnostics were summarized. The introduction of the radiomic approach has expanded the views on interpretation of medical imaging data. The radiomics-based parameters extracted from digital images revealed high informativeness in some studies that contribute to improving diagnostic accuracy as well as expanding opportunities for predicting therapeutic effectiveness in CC patients.Conclusion. Radiomics used in diagnostics of oncogynecologic diseases including СС is one of the promising actively developing areas of analysis in radiology that requires to be further investigated.

Cervical Cancer Diagnostics Using Machine Learning Algorithms and Class Balancing Techniques

Objectives: Cervical cancer is present in most cases of squamous cell carcinoma. In most cases, it is the result of an infection with human papillomavirus or adenocarcinoma. This type of cancer is the third most common cancer of the female reproductive organs. The risk groups for cervical cancer are mostly younger women who frequently change partners, have early sexual intercourse, are infected with human papillomavirus (HPV), and who are nicotine addicts. In most cases, the cancer is asymptomatic until it has progressed to the later stages. Cervical cancer screening rates are low, especially in developing countries and in some minority groups. Due to these facts, the introduction of a tentative cervical cancer screening based on a questionnaire can enable more diagnoses of cervical cancer in the initial stages of the disease. Methods: In this research, publicly available cervical cancer data collected on 859 female patients are used. Each sample consists of 36 input attributes and four different outputs Hinselmann, Schiller, cytology, and biopsy. Due to the significant unbalance of the data set, class balancing techniques were used, and these are the Synthetic Minority Oversampling Technique, the ADAptive SYNthetic algorithm (ADASYN), SMOTEEN, random oversampling, and SMOTETOMEK. To obtain the mentioned target outputs, multiple artificial intelligence (AI) and machine learning (ML) methods are proposed. In this research, multiple classification algorithms such as logistic regression, multilayer perceptron (MLP), support vector machine (SVM), K-nearest neighbors (KNN), and several naive Bayes methods were used. Results: From the achieved results, it can be seen that the highest performances were achieved if MLP and KNN are used in combination with Random oversampling, SMOTEEN, and SMOTETOMEK. Such an approach has resulted in mean area under the receiver operating characteristic curve (AUC¯) and mean Matthew’s correlation coefficient (MCC¯) scores of higher than 0.95, regardless of which diagnostic method was used for output vector construction. Conclusions: According to the presented results, it can be concluded that there is a possibility for the utilization of artificial intelligence (AI) and machine learning (ML) techniques for the development of a tentative cervical cancer screening method, which is based on a questionnaire and an AI-based algorithm. Furthermore, it can be concluded that by using class balancing techniques, a certain performance boost can be achieved.

The Expression of Testin, Ki-67 and p16 in Cervical Cancer Diagnostics.

Testin is a protein expressed in normal human tissues, being responsible, with other cytoskeleton proteins, for the proper functioning of cell−cell junction areas and focal adhesion plaques. It takes part in the regulation of actin filament changes during cell spreading and motility. Loss of heterozygosity in the testin-encoding gene results in altered protein expression in many malignancies, as partly described for cervical cancer. The aim of our study was the assessment of the immunohistochemical (IHC) expression of testin in cervical cancer and its analysis in regard to clinical data as well the expression of the Ki-67 antigen and p16 protein. Moreover, testin expression was assessed by Western blot (WB) in commercially available cell lines. The IHC analysis disclosed that the expression of testin inversely correlated with p16 (r = −0.2104, p < 0.0465) and Ki-67 expression (r = −0.2359, p < 0.0278). Moreover, weaker testin expression was observed in cancer cases vs. control ones (p < 0.0113). The WB analysis of testin expression in the cervical cancer cell lines corresponded to the IHC results and showed a weaker expression compared to that in the control cell line. When we compared the expression of testin in cervical cancer cell lines, we found a weaker expression in HPV-negative cell lines. In summary, we found that the intensity of testin expression and the number of positive cells inversely correlated with the expression of Ki-67 (a marker of proliferation) and p16 (a marker of cell cycle dysregulation). This study shows that the combined assessment of testin, Ki-67 and p16 expression may improve cervical cancer diagnostics.

From bioinformatic screening of genetic markers to low invasive lymph node metastases diagnosis in patients with cervical cancer

Background. The problem of lymph nodes metastases diagnosing in cervical cancer remains relevant and not fully resolved. The last decade studies results have shown the great potential of molecular markers in lymph nodes metastasis prediction, however, additional studies for their implementation in clinical practice are required.&#x0D; Aim. Bioinformatic and laboratory screening of molecular markers of cervical tumors regional metastasis for its low invasive diagnosis.&#x0D; Material and methods. The study was performed on 400 patients with cervical cancer and 40 donors without oncological pathology. To identify potential molecular markers of lymph node metastatic lesions, the Cancer Genome Atlas database was initially analyzed. The identified markers were validated by the Real-Time-polymerase chain reaction in tumor cell samples (extracted using laser microdissection) and extracellular deoxyribonucleic acid (DNA). The MannWhitney test was used to assess the differences; the Bonferroni correction was used to account for multiple comparisons.&#x0D; Results. At the bioinformation stage, the change in the copy number of 5493 genes was analyzed, of which 79 genes were selected that most often change their copy number. During the data validation, it was found that primary tumor cells and tumor cells of metastases from the lymph nodes differ from normal cervix cells in the level of gene copies. The copy number of the CCND1 and PPARGC1A genes has the highest potential for regional lymph nodes metastases diagnosing in patients with cervical cancer; the PIK3CA, SPEN, ERBB3, APC, MUC4, CASP8, HLA-A, IGSF1 and TMTC1 loci have a lower potential. The EP300, TTN, DMD, DST, LAMP3, TORC2, TP53 and FOXO3 genes can be used to diagnose cervical cancer, whether metastatic or not. Additional validation of markers was carried out on extracellular DNA of blood plasma of cervical cancer patients and conditionally healthy donors. The presence of a differential copy number of PIK3CA, SPEN, ERBB3, APC, CCND1, HLA-A, TTN, MUC4, DST, PPARGC1A genes was found in two groups of patients with cervical cancer with and without metastatic lesions of the lymph nodes.&#x0D; Conclusion. The study made it possible to form a list of potential molecular markers for low invasive diagnostics of cervical cancer in general (EP300, LAMP3, TORC2, FOXO3, TP53) and cervical cancer with metastatic lesions of regional lymph nodes (PIK3CA/DST, APC/PPARGC1A, ERBB3/HLA-A and LAMP3/MUC4).

Impact of COVID-19 on the epidemiological situation of cervical cancer in Irkutsk region and Irkutsk city (2010–2020)

Background. The increasing incidence of cervical cancer in Irkutsk region causes a growing workload for healthcare institutions of all levels. Therefore, we considered it necessary to analyze the quality of cancer care in Irkutsk region and its administrative center (Irkutsk city).Objective: to analyze the epidemiological situation of cervical cancer in Irkutsk region and Irkutsk city with the consideration of COVID-19 impact.Materials and methods. We used annual forms of federal statistical surveillance No. 7 “Information on malignant tumors” and No. 35 “Information on patients with malignant tumors” for Irkutsk region and Irkutsk city, as well as the information from the Federal State Statistics Service of the Russian Federation on the age-sex structure of population for 2010–2020. All calculations were performed in accordance with the methodological recommendations of P.A. Herzen Moscow Oncology Research Institute. Results. A total of 4,190 women were diagnosed with cervical cancer in Irkutsk region in 2010–2020; of them, 780 were from Irkutsk. We observed a 3.5 % and a 25 % decrease in the absolute number of new cases in Irkutsk region and Irkutsk city, respectively. Such a difference between the region and the city can be explained by a stricter adherence to the measures aimed at prevention of new coronavirus infection with suspended screening of certain groups of the adult population, as well as infection of healthcare professionals and their mobilization to COVID-19 hospitals, which had a negative impact on cancer care and, first of all, primary diagnostics of cervical cancer. There was an increase in the incidence of cervical cancer before the pandemic in both Irkutsk region and Irkutsk city up to 2019. The effectiveness of early diagnosis (active and early detection) increased significantly from 2010 to 2019; however, it became lower in 2020, due to transformation of many inpatient settings into COVID-19 hospitals and restrictive measures for preventive medical examination. Our findings suggest underdiagnosis of diseases during screening: we observed an increasing proportion of patients with late diagnosis (from 47.1 % in 2019 to 53.8 % in 2020), and, as a result, an increase in one-year mortality (from 16.9 to 17.9 %).Conclusion. Preventive measures for COVID-19 had a negative impact on the epidemiological situation of cancer in Irkutsk region in 2020 and worsened the quality of cancer care.

Cervical Cancer Diagnostics Healthcare System Using Hybrid Object Detection Adversarial Networks.

Cervical cancer is one of the common cancers among women and it causes significant mortality in many developing countries. Diagnosis of cervical lesions is done using pap smear test or visual inspection using acetic acid (staining). Digital colposcopy, an inexpensive methodology, provides painless and efficient screening results. Therefore, automating cervical cancer screening using colposcopy images will be highly useful in saving many lives. Nowadays, many automation techniques using computer vision and machine learning in cervical screening gained attention, paving the way for diagnosing cervical cancer. However, most of the methods rely entirely on the annotation of cervical spotting and segmentation. This paper aims to introduce the Faster Small-Object Detection Neural Networks (FSOD-GAN) to address the cervical screening and diagnosis of cervical cancer and the type of cancer using digital colposcopy images. The proposed approach automatically detects the cervical spot using Faster Region-Based Convolutional Neural Network (FR-CNN) and performs the hierarchical multiclass classification of three types of cervical cancer lesions. Experimentation was done with colposcopy data collected from available open sources consisting of 1,993 patients with three cervical categories, and the proposed approach shows 99% accuracy in diagnosing the stages of cervical cancer.

Epidemiology and diagnosis of cervical cancer

The data of populational and hospital cancer registers, cytological and immunological laboratories of Saint-Petersburg are examined. More than 350 new invasive cervical cancer cases are registered annually. Since 1970 up to 1991 oncological morbidity decreased from 14,7 to 8,1 per 100000 women, but then we witness steady rise of standardized indeces up to 9,9 in 1999. Increasingrate of so called neglectedforms of cervical cancer (III-IV stages), especially amongyoung women, is a disturbing fact. The issues of prophylaxis and early diagnostics of cervical cancer are discussed in the article. The results of cytological and virological examination of women of different contingents are drawn.

The condition and tendencies of cervical carcinoma diagnostic in the Russian Federation

The elimination of cervical cancer is one of the leading international public health problems that is associated with corresponding high morbidity and mortality among women of able-bodied and reproductive age. In the Russian Federation, in 2018, in more than 17.5 thousand women cervix malignant neoplasms were diagnosed and more than 6 thousand of them died. Cervical cancer is preventable disease that can be eliminated if the targets of the WHO Global Strategy to Eliminate Cervical Cancer as Public Health Issue will be achieved. The purpose of the study is to analyze indices of timely cervical cancer diagnostics in the Russian Federation and in its subjects in 2007-2018. Despite favorable trend of increasing of active detection of cervical cancer, this indicator (41.8%) continues to be low, both in the country in whole and in most of the subjects of the Russian Federation. The cervical cancer in situ stage is detected only in 25.3 cases per 100 cases of cervix cancer and stages I and II of disease are detected in 66.1% of cases. More than a third of all cases of cervical cancer (32.6%) are detected at III-IV stages of oncologic process. The percentage of patients died within the first year after cervical cancer was diagnosed decreased significantly from 19.0% in 2007 to 13.8% in 2018.

Neural network analysis of some molecular parameters of the cervical epithelium for cervical cancer diagnostics

Background.A personalized approach is the basis for the specialized care for cancer patients. The relevance of cervical cancer (CC) is still high. The searches for diagnostic criteria of cervical epithelium malignancy are continuing. The application ohm technologies has led to a big number results, the analysis of which is often difficult. The neural network data analysis allows to solve these problems.Objective: to create a technology for diagnosing cervical intraepithelial neoplasia (CIN) and CC, based on a neural network analysis of some molecular parameters.Materials and methods. The research carried out among patients with CIN III (n = 15), patients with CC stages I–IV (n = 49). The control group consisted of female volunteers without cervical pathology (n = 15). Studied molecular parameters: the spectrum of fatty acids was determined in cervical biopsies, proteins OPN, ICAM-1 were studied in blood serum, proteins of the immune cycle sCD25, sCD27 – in the cervical epithelium. Research methods: gas-liquid chromatography, flow cytometry.Results.Significant differences of fatty acids spectrum, local level sCD27 were revealed in among the studied groups. The multilayer perceptron included C18:2ω6, OPN, ICAM-1, sCD25, sCD27. The performed neural network analysis of the molecular data allows to diagnose CIN III (Se = 0.92; Sp = 0.87; AUC = 0.94; p˂0.001) and CC (Se = 1.00; Sp = 1.00; AUC = 1.00; p˂0.001).Conclusion.The created model makes it possible to diagnose CIN III and CC with high accuracy. The configuration of the multilayer perceptron allows confirming the pathophysiological relationships between the studied molecular parameters, to expand the understanding of the mechanisms of cervical carcinogenesis.

Exosomal HPV oncogene and PD-L1 in cervical cancer: potential biomarkers for monitoring disease progression and treatment response

<h3>Objectives:</h3> Exosomes are nanosized extracellular vehicles released from cells as messengers for cell-cell communication. Growing evidence shows tumor-derived exosomes (TEXs) carry malignant materials from tumors contributing to metastasis and influencing tumor growth regulation. TEXs can be obtained from biofluids, thus, characterizing TEXs in serum and understanding the information they carry opens up the possibility of using TEXs as a valuable diagnostic and prognostic tool. While this potential has been demonstrated in other solid tumor cancers such as breast, lung, and liver, the role of exosomes in gynecologic malignancies remains largely unexplored. Breakthroughs in cervical cancer have revealed the importance of HPV in oncologic transformation of cervical cells and the roll of PD-1/PD-L1 immune checkpoint in evading regulatory pathways to allow for tumor cell growth. Exosomal PD-L1 has also been shown to contribute to tumor growth and correlate with disease progression in melanoma and head and neck cancers. This study aims to determine whether HPV and PD-L1 can be detected in cervical TEXs to further investigate what diagnostic and prognostic implications their presence may have. <h3>Methods:</h3> The cervical cancer cell lines C-33-A, Ca-Ski, and SiHa were used to demonstrate successful cervical cancer-derived exosome extraction and detect exosomal molecular and genetic material. For each cell line, PCR was used to confirm HPV presence in the cells and exosomes, and Western Blot was used to determine the presence of PD-L1. To collect exosomes, the cells were cultured in growth medium with exosome-depleted FBS for 72 hours. Then, differential ultracentrifugation was used to isolate the exosomes. The exosomes were collected and tested for presence of HPV transcript and PD-L1 protein using PCR and Western Blot, respectively. The presence of CD9, a universal surface marker of exosomes, was also tested on the exosomes as an internal control. <h3>Results:</h3> PCR confirmed that C-33-A is HPV negative while Ca-Ski and SiHa are HPV positive. Western Blot revealed that only Ca-Ski expresses PD-L1, while both Si-Ha and C-33-A are negative for PD-L1. Notably, the expression of HPV and PD-L1 in exosomes was consistent with the host cells. Ca-Ski-derived exosome expressed both HPV and PD-L1. SiHa-derived exosomes expressed HPV but not PD-L1, and C-33-A was negative for both HPV and PD-L1. CD9 expression was seen in all exosome samples from all 3 cell lines. <h3>Conclusions:</h3> As postulated, the presence of HPV and PD-L1 in cervical TEXs was correlated with their presence in the host cell, suggesting that the genetic and molecular information carried in the exosomes can be used to provide valuable information regarding primary and metastatic tumors. This has promising implications for the use of TEXs in diagnostics and monitoring treatment response in patients with cervical cancer. Future steps in realizing the potential of this discovery in cervical cancer diagnostics and management of the disease include demonstrating that HPV and PD-L1 are also present in exosomes isolated from serum of patients with cervical cancer.

Imaging based cervical cancer diagnostics using small object detection - generative adversarial networks

Cervical cancer is one of the curable cancers when it is diagnosed in the early stages. Pap smear test and visual inspection using acetic acid are the most common screening mechanism for the cervical lesion to categorize the cervical cells as normal, precancerous, or cancerous. However, most of the classification methods success depends on the accurate spotting and segmenting of cervical location. These challenges pave the way for sixty years of research in cervical cancer diagnosis, but still, accurate spotting of the cervical cell remains an open challenge. Moreover, state-of-the-art classification methods are developed based upon the extraction of manual annotations of features. In this paper, an effective hybrid deep learning technique using Small-Object Detection-Generative Adversarial Networks (SOD-GAN) with Fine-tuned Stacked Autoencoder (F-SAE) is developed to address the shortcomings mentioned above. The generator and discriminator of the SOD-GAN are developed using Region-based Convolutional Neural Network (RCNN). The model parameters are fine-tuned using F-SAE, and the hyperparameters of the SOD-GAN are normalized and optimized to make the lesion detection faster. The proposed approach automatically detects and classifies the cervical premalignant and malignant conditions based on deep features without any preliminary classification and segmentation assistance. Extensive experimentation has also been done with multivariate heterogeneous data, and the proposed approach has shown promising improvement in efficiency and reduces the time complexity.

Dual-Illumination Ultrasound/ Photoacoustic System for Cervical Cancer imaging.

Early stage cancer detection technologies can provide functional information and potentially decrease the mortality rate caused by cervical cancer. In our previous work, a miniaturized ultrasound and photoacoustic endoscopic system has been developed to image the cervical tissue through the cervical canal to fulfills the need for a safe, low-cost, and high-resolution functional diagnostic system. However, the miniaturized size of endoscope and American National Standards Institute safety limits cause constraints of using high-intensity illumination during imaging. In addition, the strong light scattering of tissues limits the light penetration depth. Fortunately, the cervix anatomy allows for the delivery of additional light from the ectocervix by using an external illumination system. Here we propose a dual, co-planar illumination system, which can provide adequate illumination to the cervical tissue via combined internal and external light delivery strategies. Therefore, an increase in the area of light-tissue interaction allows us to raise the laser light energy while keeping fluence under safety limits. Thus, a reliable PA imaging can be obtained for the whole cervical tissue thickness. The system performance was tested using a Monte Carlo simulation, and laser-light fluence was calculated and compared at different depths within a simulated cervical-tissue model. The results indicated a higher and more uniform fluence in the Monte Carlo simulations. In addition, the photoacoustic imaging of the proposed system was evaluated by two cervical tissue-mimicking phantoms with human blood and graphite rods as inclusions inside it. In accordance with the simulations, the phantom study revealed a more reliable photoacoustic signal for the entire depth of the phantoms with an improved contrast to noise ratio and signal to noise ratio, and a higher coverage ratio of the imaging field of view. In summary, the dual-mode illumination system can provide more realistic information of inclusions within the tissue while considering safety limits, which can lead to more accuracy in biomarker detection for cervical cancer diagnostics.

PAPILLOMAVIRAL CARCINOGENESIS. SIGNIFICANT ACHIEVEMENTS AND SPECIFIC CHALLENGES. PART 3. THREE LEVELS OF CERVICAL CANCER PREVENTION AND TREATMENT

Efficient prophylactic vaccines have been developed to prevent cervical cancer, a frequent female oncological disease caused by carcinogenic human papillomaviruses. World Health Organization worked out the program for prophylaxis of cervical cancer and control of the disease. It includes preventive adolescent vaccinations, screening of precancerous cervical lesions in women as well as cervical cancer treatment if originated. Cervical cancer diagnostics is being improved, development of therapeutic human papillomaviruses vaccines is in progress. The review deals with major achievements and certain challenges in the field of cervical cancer prevention.Part I see: Volgareva G.M. Papillomaviral carcinogenesis. Major achievements and certain challenges. Part I. General notions of papillomaviruses. Human papillomavirusesassociated cancers. Russian Journal of Biotherapy 2020;19(1):6–12.Part 2 see: Volgareva G.M. Papillomaviral carcinogenesis. Major achievements and certain challenges. Part 2. HPV-associated cancers in Russia. Preventive HPV vaccines. Russian Journal of Biotherapy 2020;19(2):31–8.

High Detection Rate for Non-Muscle-Invasive Bladder Cancer Using an Approved DNA Methylation Signature Test.

Cystoscopy and transurethral resection are the current reference standard tests to diagnose and histologically confirm non-muscle-invasive bladder cancer (NMIBC). In other tumor entities (ie, colon carcinoma, cervical cancer), DNA methylation markers have been approved as diagnostic tests with high diagnostic power. In our case-control study, we used an approved molecular cervical cancer diagnostics test that includes 6 DNA methylation markers (GynTect) for the detection of bladder cancer. We included samples from 40 patients with bladder cancer and 34 control subjects. In a pilot study, we analyzed DNA methylation in 38 tumor tissues and 4 healthy ureters using methylation-specific polymerase chain reaction. Subsequently, we determined the sensitivity and specificity of the GynTect for the detection of bladder cancer in urine sediments from 40 patients with bladder cancer and 30 control subjects with benign prostatic hyperplasia or urolithiasis. The markers showed very different methylation rates in the NMIBC tissues, ranging from 2.6% to 78.9%. No methylation of any of the markers was detectable in the healthy ureters. Using the urine sediments from the patients with cancer and control subjects, we found surprisingly high sensitivity and specificity for the GynTect assay (60% and 96.7%, respectively). The application of different algorithms for evaluation of the markers included in GynTect resulted in a sensitivity of≤ 90% and specificity of≤ 100%. The GynTect assay, originally designed for cervical cancer diagnostics, showed unexpectedly high diagnostic accuracy for bladder cancer detection. The inclusion of additional methylation markers might allow for the development of a suitable diagnostic marker set based on the GynTect test for NMIBC diagnostics.

The role of miR-409-3p in regulation of HPV16/18-E6 mRNA in human cervical high-grade squamous intraepithelial lesions

Cervical cancer is one of the most common malignancies in women. MicroRNAs (miRNAs) are involved in a variety of fundamental cellular processes, including carcinogenesis. The potential utilization of aberrantly expressed miRNAs as novel biomarkers in cervical cancer diagnostics is growing. We investigated miRNA expression profiles during the progression of dysplasia in cervical epithelium to identify aberrantly expressed miRNAs. High-throughput miRNA profiling of high-grade precancerous lesions identified 79 miRNAs showing significant difference in expression values compared to normal cervical epithelium. Ten selected miRNAs were subsequently measured in an independent group of samples to validate them as promising biomarkers of cervical carcinogenesis. MicroRNAs miR-10b-5p, miR-34c-5p, miR-409-3p and miR-411-5p were confirmed as downregulated, while miR-10a-5p, miR-132-3p, miR-141-5p were significantly upregulated in dysplastic cervical tissues. Further investigation revealed an inverse correlation of miR-409-3p with E6 mRNA levels in precancerous cervical lesions. Subsequent in vitro analyses showed a direct involvement of this miRNA in the regulation of E6 oncogene levels, thus confirming a potential tumor suppressor function of miR-409-3p in cervical malignancies. Hence, miR-409-3p may represent a useful early marker and a potential therapeutic target for cervical cancer.