-
PloS One 2023Precise segmentation of the nucleus is vital for computer-aided diagnosis (CAD) in cervical cytology. Automated delineation of the cervical nucleus has notorious...
Precise segmentation of the nucleus is vital for computer-aided diagnosis (CAD) in cervical cytology. Automated delineation of the cervical nucleus has notorious challenges due to clumped cells, color variation, noise, and fuzzy boundaries. Due to its standout performance in medical image analysis, deep learning has gained attention from other techniques. We have proposed a deep learning model, namely C-UNet (Cervical-UNet), to segment cervical nuclei from overlapped, fuzzy, and blurred cervical cell smear images. Cross-scale features integration based on a bi-directional feature pyramid network (BiFPN) and wide context unit are used in the encoder of classic UNet architecture to learn spatial and local features. The decoder of the improved network has two inter-connected decoders that mutually optimize and integrate these features to produce segmentation masks. Each component of the proposed C-UNet is extensively evaluated to judge its effectiveness on a complex cervical cell dataset. Different data augmentation techniques were employed to enhance the proposed model's training. Experimental results have shown that the proposed model outperformed extant models, i.e., CGAN (Conditional Generative Adversarial Network), DeepLabv3, Mask-RCNN (Region-Based Convolutional Neural Network), and FCN (Fully Connected Network), on the employed dataset used in this study and ISBI-2014 (International Symposium on Biomedical Imaging 2014), ISBI-2015 datasets. The C-UNet achieved an object-level accuracy of 93%, pixel-level accuracy of 92.56%, object-level recall of 95.32%, pixel-level recall of 92.27%, Dice coefficient of 93.12%, and F1-score of 94.96% on complex cervical images dataset.
Topics: Female; Humans; Image Processing, Computer-Assisted; Neural Networks, Computer; Papanicolaou Test; Vaginal Smears; Diagnosis, Computer-Assisted
PubMed: 37788295
DOI: 10.1371/journal.pone.0283568 -
Viruses May 2024We have been encouraging practicing gynecologists to adopt molecular diagnostics tests, PCR, and cancer biomarkers, as alternatives enabled by these platforms, to...
We have been encouraging practicing gynecologists to adopt molecular diagnostics tests, PCR, and cancer biomarkers, as alternatives enabled by these platforms, to traditional Papanicolaou and colposcopy tests, respectively. An aliquot of liquid-based cytology was used for the molecular test [high-risk HPV types, (HR HPV)], another for the PAP test, and one more for p16/Ki67 dual-stain cytology. A total of 4499 laboratory samples were evaluated, and we found that 25.1% of low-grade samples and 47.9% of high-grade samples after PAP testing had a negative HR HPV-PCR result. In those cases, reported as Pap-negative, 22.1% had a positive HR HPV-PCR result. Dual staining with p16/Ki67 biomarkers in samples was positive for HR HPV, and 31.7% were also positive for these markers. Out of the PCR results that were positive for any of these HR HPV subtypes, n 68.3%, we did not find evidence for the presence of cancerous cells, highlighting the importance of performing dual staining with p16/Ki67 after PCR to avoid unnecessary colposcopies. The encountered challenges are a deep-rooted social reluctance in Mexico to abandon traditional Pap smears and the opinion of many specialists. Therefore, we still believe that colposcopy continues to be a preferred procedure over the dual-staining protocol.
Topics: Humans; Female; Mexico; Uterine Cervical Neoplasms; Papillomavirus Infections; Molecular Diagnostic Techniques; Papanicolaou Test; Biomarkers, Tumor; Papillomaviridae; Cyclin-Dependent Kinase Inhibitor p16; Vaginal Smears; Colposcopy; Gynecology; Adult; Middle Aged; Ki-67 Antigen; Polymerase Chain Reaction; Early Detection of Cancer; Private Practice
PubMed: 38932179
DOI: 10.3390/v16060887 -
Acta Medica Portuguesa Sep 2023Screening is effective in reducing cancer-related morbidity and mortality. The aim of this study was to analyze the level of, and income-related inequalities in,...
INTRODUCTION
Screening is effective in reducing cancer-related morbidity and mortality. The aim of this study was to analyze the level of, and income-related inequalities in, screening attendance, in Portugal for population-based screening programs.
METHODS
Data from the Portuguese Health Interview Survey 2019 was used. Variables included in the analysis were self-reported: mammography, pap smear test, fecal occult blood test. Prevalence and concentration indices were computed at national/regional level. We analyzed: up-to-date screening (within recommended age/interval), under-screening (never or overdue screening), and over-screening (due to frequency higher than recommended or screening outside target group).
RESULTS
Up-to-date screening rates were 81.1%, 72%, and 40%, for breast, cervical and colorectal cancer, respectively. Never-screening was 3.4%, 15.7%, and 39.9%, for breast, cervical, and colorectal cancer, respectively. Over-screening related with frequency was highest for cervical cancer; in breast cancer, over-screening was observed outside recommended age, affecting one third of younger women and one fourth of older women. In these cancers, over-screening was concentrated among women with higher income. Never-screening was concentrated among individuals with lower income for cervical cancer and higher income for colorectal cancer. Beyond the recommended age, 50% of individuals never underwent screening for colorectal cancer and 41% of women never underwent screening for cervical cancer.
CONCLUSION
Overall, screening attendance was high, and inequalities were low in the case of breast cancer screening. The priority for colorectal cancer should be to increase screening attendance.
Topics: Humans; Female; Aged; Uterine Cervical Neoplasms; Vaginal Smears; Portugal; Early Detection of Cancer; Prevalence; Breast Neoplasms; Colorectal Neoplasms; Mass Screening; Socioeconomic Factors
PubMed: 37339163
DOI: 10.20344/amp.19443 -
International Journal of Molecular... Jan 2024It is thought that numerous genotypes of human papillomavirus (HPV) are associated with various atypical cells, such as multinucleated cells, koilocytes, binucleated...
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.
Topics: Female; Humans; Papanicolaou Test; Vaginal Smears; Uterine Cervical Dysplasia; Uterine Cervical Neoplasms; Human Papillomavirus Viruses; Papillomavirus Infections; Papillomaviridae; DNA, Viral
PubMed: 38279211
DOI: 10.3390/ijms25021212 -
Proceedings (Baylor University. Medical... 2024Diagnosing atypical glandular cells (AGC) is a significant challenge in cytomorphology.
BACKGROUND
Diagnosing atypical glandular cells (AGC) is a significant challenge in cytomorphology.
METHODS
A retrospective study was undertaken to assess the prevalence of AGC and the subsequent histological outcomes over 5 years at a single institution.
RESULTS
A total of 159,649 ThinPrep Pap tests, including 395 cases of AGC, were retrieved, of which 330 AGC cases had follow-up histopathology. Among these 330 cases, 43.9% were classified as AGC not otherwise specified, followed by AGC-endocervical cells at 33.3%. The most frequently observed histological findings at follow-up included CIN1 and benign mucosa with reactive changes, followed by high-grade squamous intraepithelial lesion and cervical squamous cell carcinoma. The overall 5-year insignificant AGC rate was 0.12%, and the overall 5-year significant AGC rate was 0.08%. Notably, 36.7% of AGC cases tested positive for high-risk human papillomavirus. Interestingly, the level of experience did not significantly impact the rates for significant or insignificant AGC diagnosis. However, senior cytopathologists had a higher AGC report rate compared to their junior peers.
CONCLUSION
The AGC diagnostic rate at our institution falls within the range given by the College of American Pathologists. A significant number of cases had follow-up histologic results available, and the overall 5-year insignificant AGC rate was 0.12%.
PubMed: 38628324
DOI: 10.1080/08998280.2024.2324656 -
Annals of Medicine and Surgery (2012) May 2024In Palestine, cervical cancer is the third most common gynaecological cancer, exhibiting higher mortality rates compared to regional counterparts. Late-stage diagnosis...
BACKGROUND
In Palestine, cervical cancer is the third most common gynaecological cancer, exhibiting higher mortality rates compared to regional counterparts. Late-stage diagnosis and limited awareness contribute to this disparity. This study aims to assess the awareness of Palestinian medical students regarding cervical cancer prevention.
METHODS
A questionnaire-based survey involving 532 medical students from various Palestinian universities was conducted between October 2023 and December 2023. The survey encompassed closed-ended quantitative and demographic questions distributed through social media.
RESULTS
The study was carried out on a group of 532 medical students (66.3% women and 33.6% men), (average age 21.7 years). Most students (77.7%) knew that the main risk factor for cervical cancer was human papillomavirus (HPV) infection. Participants doing the internship had the greatest knowledge, whereas students from the first year had the poorest knowledge about the main risk factors for cancer of the cervix. Only about half, 50.2% of all students, knew that in Palestine, there is no screening program. 84.4% of students correctly indicated that the cervical cancer screening test is a pap smear test. 41.4% of respondents knew that microscopic evaluation of the exfoliated cells from the vaginal part of the cervix is the screening test for cervical cancer which is used. Only about half of the students (45.1%) knew that there were no specific early symptoms of cervical cancer.
CONCLUSIONS
This study highlights the need for enhanced education, particularly regarding screening program awareness, among Palestinian medical students. Addressing these knowledge gaps is crucial for effective preventive strategies.
PubMed: 38694304
DOI: 10.1097/MS9.0000000000001935 -
Scientific Reports Jul 2023
PubMed: 37407808
DOI: 10.1038/s41598-023-37880-w -
Open Life Sciences 2023Cervical cancer is one of the most dangerous and widespread illnesses afflicting women throughout the globe, particularly in East Africa and South Asia. In...
Cervical cancer is one of the most dangerous and widespread illnesses afflicting women throughout the globe, particularly in East Africa and South Asia. In industrialised nations, the incidence of cervical cancer has consistently decreased over the past few decades. However, in developing countries, the reduction in incidence has been considerably slower, and in some instances, the incidence has increased. Implementing routine screenings for cervical cancer is something that has to be done to protect the health of women. Cervical cancer is famously difficult to diagnose and cure due to the slow rate at which it spreads and develops into more advanced stages of the disease. Screening for cervical cancer using a Pap smear, more often referred to as a Pap test, has the potential to detect the illness in its earlier stages. For the purpose of selecting features for this article, a gray level co-occurrence matrix (GLCM) technique was used. Following this step, classification is performed with methods such as convolutional neural network (CNN), support vector machine, and auto encoder. According to the findings of this experiment, the GLCM-CNN classifier proved to be the one with the highest degree of precision.
PubMed: 38045489
DOI: 10.1515/biol-2022-0770 -
Cervical Cancer Classification From Pap Smear Images Using Deep Convolutional Neural Network Models.Interdisciplinary Sciences,... Mar 2024As one of the most common female cancers, cervical cancer often develops years after a prolonged and reversible pre-cancerous stage. Traditional classification...
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.
Topics: Female; Humans; Papanicolaou Test; Uterine Cervical Neoplasms; Neural Networks, Computer; Algorithms; Image Interpretation, Computer-Assisted
PubMed: 37962777
DOI: 10.1007/s12539-023-00589-5 -
Cureus Jan 2024Planning vaccination and treatment options requires knowledge about the regional incidence of human papillomavirus infection (HPV) and its genotypes. The aim of our...
OBJECTIVE
Planning vaccination and treatment options requires knowledge about the regional incidence of human papillomavirus infection (HPV) and its genotypes. The aim of our study was to determine the regional prevalence of HPV with genotypic subclassification and to evaluate the efficacy of HPV testing in cervical screening. Material and Method: This retrospective cohort study analyzed records of 10,152 women aged 30-65 from the On Dokuz Mayıs University Medical Faculty's Gynecology Clinic, excluding those with a history of cervical disease, hysterectomy, or current pregnancy. Pre- and postmenopausal and total HPV prevalence were calculated. There was a total of 544 patients who underwent a colposcopic biopsy after cervical screening. The research focused on comparing the efficacy of Pap smears, HPV tests, and co-tests in detecting LSIL or more severe conditions, utilizing the BD Viper LT System for HPV screening and liquid-based cytology for smear tests.
RESULTS
The prevalence of HPV in our region was determined to be 10.9%. When considering menopausal status, HPV prevalence was found to be 9.8% in premenopausal individuals and 12.4% in postmenopausal individuals. Evaluation of the pap smear results revealed a sensitivity of 74.8% for premenopausal and 81% for postmenopausal patients, with a specificity of 51% observed in both menopausal categories. In contrast, HPV testing demonstrated a sensitivity of 90.8% in premenopausal and 92.4% in postmenopausal individuals, with a specificity of 58% for both groups. The co-test results indicated an even higher sensitivity, with 97.9% in premenopausal and 100% in postmenopausal individuals, albeit with a reduced specificity of 28% in both cases. When identifying LSIL (low-grade squamous intraepithelial lesions) and more severe conditions, the sensitivity and specificity of the primary HPV test surpassed those of the pap smear. While the primary HPV test's sensitivity is markedly lower compared to the co-test, it boasts a significantly higher specificity.
CONCLUSION
Regional HPV prevalence studies are valuable for the implementation of screening policies. The primary HPV DNA test is a reliable method for detecting preinvasive and invasive lesions in patients over 30 years of age.
PubMed: 38374849
DOI: 10.7759/cureus.52615