Search

Postcoital bleeding is a worrying, for both women and health care provider. This study aimed to evaluate the prevalence of abnormal cervical cytology among patient with PCB in the private outpatient care setting, and to identify risk-factors for cervical pathology among these patients. A cross sectional study of 90 patients presented to the privet clinic, during the period 1st feb-1st Des. 2019. Inclusion criteria include married women presented with post coital bleeding, non-pregnant, all patients undergo Pap Smear Cytology. The commonest age presented with PCB was 40-44 years old 22(24.4%), followed by (45-49) years and (25-29) years 18(20%). Those aged ≥40 years 44(48.9%), and those aged ≤34 34(37.8%). The mean parity was 4.7±2.8, hormonal contraception was commonly used by those with PCB followed by intra uterine contraceptive device (IUCD), 30(33.3%), 18(20) respectively. Most of the patient were House wives 78(86.7%), The physical examination show that most patient had cervical erosion 68(75.5%), followed by healthy cervix in 12(13.3%), while suspicious features was found among 6(6.7%), Moderate and sever dysplasia was found more among those aged ≥40 years 10(22.7%), while it was 4(8.7%) among those aged < 40 years. there is higher prevalence of High-grade squamous intraepithelial lesions among females with PCB, and non- significant difference among those aged less or more than 40 years. Therefore it’s important to examine any patient complaining of PCB with PAP smear cytology and colposcopy examination.

Objectives: In the cervical smear screening test as a sample collection method for liquid-based thin layer cytology, classically the collecting device is placed into a liquid fixative solution and vigorously swirled or rotated ten times in the solution and the collection device is removed from the solution. In this study, a plastic smear brush was used as the collection device. After the cervical cell sample was obtained, the smear brush was detached from the stick and left in the solution and given to the laboratory. Our aim in the study is to examine whether smear inadequacy rates have decreased with the method used in the study compared to the classical method. Material and methods: While the classical technique which the collecting device is placed into a solution and mixed and removed from the solution is defined as Method 1. The technique used in the study was defined as Method 2. The cervical smear screening test results obtained by two different methods in two consecutive time periods were analyzed. The two methods were compared using chi-square test in terms of smear inadequacy. Results: A total of 2129 test results, including 1129 smears in Method 1 and 1000 smears in Method 2 were examined. The mean ages of the patients tested in both methods were similar (36 ± 6.1 and 37 ± 6.7). Abnormal test result rate was similar for Method 1 and Method 2 (5.8% vs 4.9%, respectively). The inadequate sample rate was higher in Method 1 than Method 2 (8.3% vs 2.1%, respectively). Conclusions: The study showed that leaving the smear brush in the solution is a better way to reduce the inadequacy sample rates. This result may guide clinicians about smear techniques.

Cervical cancer has influenced life of women worldwide as the fourth most severe cancer. Early screening, detection and treatment of cervical cancer notably increase the life quality and reduce the death rate of patients. Therefore, automatic diagnosis of cervical cancer could bridge the gap between testing needs and capabilities. Cervical cell detection plays an important role in cancer screening, the intent of this study is to classify the cervical cells through deep learning models, which helps to monitor the patients’ health. SSD (Single Shot MultiBox Detector) network is integrated with the positive and negative features to address the shortcomings of insufficient sensitivity to small objects. Besides, center loss function is added to better address situations that intra-class differences are greater than inter-class differences. A dataset containing 1462 benchmarked cervical cells was utilized. 80% (1167) are used for training and the remaining 20% (295) are allocated for testing. Proposed optimized SSD network achieved the accuracy of 90.8% and mAP (mean Average Precision) of 81.53%, which is 7.54% and 4.92% higher than YOLO (You Only Look Once) and classical SSD, respectively. The addition of complementary features improves the network sensitivity and the overall accuracy. It is also concluded that the proposed SSD network could be applied in cell classification for the early automatic detection of cervical cancer.

Background: Early detection of cervical cancer may give life to women all over the world. Pap-smear test and Human papillomavirus test are techniques used for the detection and prevention of cervical cancer. Objective: In this paper, pap-smear images are analysed and cells are classified using stacked autoencoder based deep neural network. Pap-smear cells are classified into 2 classes and 4 classes. Twoclass classification includes classification of cells in normal and abnormal cells while four-class classification includes classification of cells in normal cells , mild dysplastic cells, moderate dysplastic cells and severe dysplastic cells. Methods: The features are extracted by deep neural networks based on their architecture. Proposed deep neural networks consist of three stacked auto encoders with hidden sizes 512, 256 and 128, respectively. Softmax used as the outer layer for the classification of pap smear cells. Results: Average accuracy achieved for 2-class classification among normal and abnormal cells is 98.2 % while for 4-class classification among normal, mild, moderate and severe dysplastic cells is 93.8 % respectively. Conclusion: The proposed approach avoids image segmentation and feature extraction applied by previous works. This study highlights deep learning as an important tool for cells classification of pap-smear images. The accuracy of the proposed method may vary with the different combination of hidden size and number of autoencoders.

BACKGROUND: Bhutan implemented a national program for human papillomavirus (HPV) vaccination in 2010 involving girls aged 12 to 18 years and achieving nearly 90% coverage.OBJECTIVE: To estimate HPV vaccine effectiveness in a city in Bhutan.DESIGN: 2 cross-sectional surveys, 2011-2012 and 2018.SETTING: 2 hospitals in Thimphu, capital of Bhutan.PARTICIPANTS: Sexually active women aged 17 to 29 years: 1445 participants from the baseline survey and 1595 from the repeated survey.INTERVENTION: National HPV vaccination program.MEASUREMENTS: HPV was assessed in cervical cell samples by using general primer GP5+/GP6+-mediated polymerase chain reaction. Human papillomavirus types were stratified as vaccine types (HPV6/11/16/18) and nonvaccine types. Age- and sexual behavior-adjusted overall, total, and indirect (herd immunity) vaccine effectiveness (VE) was computed as (1 - HPV prevalence ratio) for HPV among all women and among unvaccinated women.RESULTS: Between the 2 surveys, the prevalence of HPV vaccine types decreased from 8.3% to 1.4%, whereas the prevalence of nonvaccine types increased from 25.8% to 31.4%. The overall and indirect adjusted VE against vaccine-targeted HPV types was 88% (95% CI, 80% to 92%) and 78% (CI, 61% to 88%), respectively. Among women younger than 27 years, who were targeted by the vaccination program, the overall and indirect adjusted VE was 93% (CI, 87% to 97%) and 88% (CI, 69% to 95%), respectively. No impact on nonvaccine HPV types was detectable.LIMITATION: Hospital-based recruitment; self-reported vaccination status.CONCLUSION: In Bhutan, the prevalence of vaccine-targeted HPV types has decreased sharply, providing the first evidence of the effectiveness of a high-coverage national HPV vaccination program in a lower-middle-income country.PRIMARY FUNDING SOURCE: Bill & Melinda Gates Foundation.

Cervical cancer if detected early has an upward of 89% survival rate. The leading tool in identifying cervical cancer in its infancy is the Papanicolaou (Pap smear) test, which since its introduction dropped cervical cancer related deaths by 60%. The Pap smear test or Liquid-based Cytology (LBC) is a time-consuming procedure that requires a pathologist to manually identify cervical cells that may be in the middle of the processes that indicate cervical cancer. Unfortunately, due to the expenses related to conducting the Pap smear test many women are blocked from access to it and this leads to over 4000 women dying annually from cervical cancer in the United States alone. The aim of this research is to automate the methods used by pathologists in conducting the Pap smear or LBC. We show that using machine vision, ensemble learning and deep learning methods a significant portion of the Pap smear can be done automated. We set out to extract cells and cell clusters and classify those samples based on the Bethesda System for reporting cervical cytology. Achieving an accuracy of 90.4% and 91.6% for the ensemble learning and deep learning methods respectively when evaluated with a five-fold cross-validation demonstrates promise in the creation of an automated Pap smear screening test.

In cervical cancer screening, accurate segmentation of cervical nucleus is a key part in the early diagnosis of cervical cancer. However, the cervical nucleus segmentation faces many great challenges owing to the overlapping cervical cells, uneven staining and poor contrast of cervical cytology smear images. In this paper, a tree domain structure and screening algorithm based on depth-first searching strategy are proposed to obtain candidate nucleus regions according to the annular clustering characteristics of nucleus depth information in cervical cytology images. Then, the candidate nucleus regions are finely segmented with an iterative level set algorithm based on adaptive radius morphological dilation. Experimental results are evaluated on the ISBI2015 public dataset. The performance of the proposed nucleus segmentation algorithm is higher than that of the state-of-the-art methods in terms of positive predictive value, negative predictive value, precision, recall of the cervical nucleus segmentation.

Analysis of pap smear images under a microscope by experts is a laborious and time consuming task. Computer-assisted diagnostic (CAD) systems can simplify this tedious process and allow experts to focus on more critical cases. Effective screening and early diagnosis can help to detect precancerous cells and allow early treatment. In this study, we have used a deep learning approach for classification of cervical cell images which obtained from pap smear slides. The proposed method automatically classifies cervical cell images into five categories without using any pre-processing on raw input images. We have obtained the promising results as compared to the previous studies in the literature. The proposed model can give a second opinion to clinicians in their daily routines and help them to focus on more complex cases.

Cervical cancer is regarded as one of the most common type of cancer suffered by women in the world. However, it can be treated if being detected early. The main method of diagnosing this type of cancer is through Papanicolaou test, in which cervical cells are collected and examined under a microscope. The process of examining the cervical cells is often done manually and is labourious. Several methods have been proposed to automate this process using machine learning. This study explores three Convolutional Neural Network models (i.e., AlexNet, Inception-V3 and ResNet50-V2) in classifying cervical cells. Transfer learning was implemented with different sets of varying number of images. Herlev dataset was used in this study. In the Herlev dataset, images were classified into seven classes (i.e. four abnormal and three normal). The classification done was based on seven-class classification. Performance of each model was measured based on accuracy, precision and recall. Based on the result obtained, ResNet50-V2 performed the best with the accuracy, precision and recall compared to the other two models.

Pap smear is a microscopic screening process of cervical smear used to detect pre-cancerous and cancerous cells in the cervix region. Cell nuclei segmentation is one of the most significant task in cervical cell image analysis which aids in identifyi

Objective: To estimate the prevalence and to determine factor associated with abnormal cervical cell among the Hmong and Mien hill tribe women. Methods: A cross-sectional study aimed to estimate the prevalence and to determine the factors associated with abnormal cervical cell among the Hmong and Mien hill tribe women living in Pha Yao province, Thailand was conducted. The data from validated questionnaires and Papanicolaou (Pap) smear test results were collected. Logistic regression was used to detect the associations between variables and abnormal cervical cell at the significant level of alpha = 0.05. Results: Totally, 450 Hmong and Mien women were recruited into the analysis. The overall prevalence of abnormal cervical cell was 2.2%; 1.2% were atypical squamous cells of undetermined significance (ASC-US), 0.4% were atypical squamous cells-cannot exclude HSIL (ASC-H), 0.4% were cervical intraepithelium neoplasia-I (CIN-I) and 0.2% were cervical intraepithelium neoplasia-II (CIN-II). Two variables, the number of their sexual partners and the number of husbands’ sexual partners, were significantly associated with abnormal cervical cell. The women who had ≥ 4 sexual partners had a 7.09 times (95%CI=1.85-27.17) more likely to have abnormal cervical cell than those who had < 4 sexual partners. The women whose husbands had ≥ 4 partners had a 5.63 times (95%CI=1.51-20.90) more likely to have abnormal cervical cell than those whose husbands had < 4 sexual partners. Conclusion: The number of sexual partners is significantly associated with abnormal cervical cell among the Hmong and Mien hill tribe women. Health interventions regarding safe sex should be promoted in the hill tribe people.

Cervical cancer, one of the most common fatal cancers among women, can be prevented by regular screening to detect any precancerous lesions at early stages and treat them. Pap smear test is a widely performed screening technique for early detection of cervical cancer, whereas this manual screening method suffers from high false-positive results because of human errors. To improve the manual screening practice, machine learning (ML) and deep learning (DL) based computer-aided diagnostic (CAD) systems have been investigated widely to classify cervical pap cells. Most of the existing researches require pre-segmented images to obtain good classification results, whereas accurate cervical cell segmentation is challenging because of cell clustering. Some studies rely on handcrafted features, which cannot guarantee the classification stage's optimality. Moreover, DL provides poor performance for a multiclass classification task when there is an uneven distribution of data, which is prevalent in the cervical cell dataset. This investigation has addressed those limitations by proposing DeepCervix, a hybrid deep feature fusion (HDFF) technique based on DL to classify the cervical cells accurately. Our proposed method uses various DL models to capture more potential information to enhance classification performance. Our proposed HDFF method is tested on the publicly available SIPAKMED dataset and compared the performance with base DL models and the LF method. For the SIPAKMED dataset, we have obtained the state-of-the-art classification accuracy of 99.85%, 99.38%, and 99.14% for 2-class, 3-class, and 5-class classification. Moreover, our method is tested on the Herlev dataset and achieves an accuracy of 98.32% for binary class and 90.32% for 7-class classification., 12 pages, 8 figures, Published in Computers in Biology and Medicine

To apply topological information to solve a cervical histopathology image clustering (CHIC) problem, a graph based unsupervised learning (GBUL) approach is proposed in this paper. First, the GBUL method applies color features and k-means clustering to carry out a first-stage “coarse” clustering. Then, a skeletonization based node generation (SBNG) approach is introduced to approximate the distribution of cervical cell nuclei. Thirdly, based on the SBNG nodes, multiple graphs are constructed. Next, graph features are extracted based on the constructed graphs. Finally, k-means clustering is used again for the second-stage clustering. In the experiment, a practical Hematoxylin–eosin staining cervical histopathology image dataset with 40 whole-slide imaging images is tested, obtaining a promising CHIC result and showing a huge potential in the cancer risk prediction field.

Cervical cancer is one of the primary factors that endanger women’s health, and Thinprep cytologic test (TCT) is the common testing tool for the early diagnosis of cervical cancer. However, it is tedious and time-consuming for pathologists to assess and find abnormal cells in many TCT samples. Thus, automatic detection of abnormal cervical cells is highly demanded. Nevertheless, false positive cells are inevitable after automatic detection. It is still a burden for the pathologist if the false positive rate is high. To this end, here we propose a semi-supervised cervical cell diagnosis method that can significantly reduce the false positive rate. First, we incorporate a detection network to localize the suspicious abnormal cervical cells. Then, we design a semi-supervised classification network to identify whether the cervical cells are truly abnormal or not. To boost the performance of the semi-supervised classification network, and make full use of the localizing information derived from the detection network, we use the predicted bounding boxes of the detection network as an additional constraint for the attention masks from the classification network. Besides, we also develop a novel consistency constraint between the teacher and student models to guarantee the robustness of the network. Our experimental results show that our network can achieve satisfactory classification accuracy using only a limited number of labeled cells, and also greatly reduce the false positive rate in cervical cell detection.

OBJECTIVE This study aims to discover the most prevalent high-risk (hr) HPV genotypes in the regions of Loreto and La Libertad, Peru. METHODS In 2015, cervical cell samples were collected during pelvic examinations from women in the geographically distinct regions of Loreto and La Libertad, Peru. In 2017, additional samples were collected in La Libertad. A total of 429 women between the ages of 18 and 65 years living in these regions were enrolled in the study. All samples were analyzed by polymerase chain reaction for the hrHPV genotypes 16, 18, and 35. RESULTS Sample collection from 126 women in 2015 in Loreto revealed an hrHPV incidence of 15.9% (20 of 126), with 60% (12 of 126) of HPV infections due to hrHPV 16. Samples from La Libertad revealed an hrHPV incidence of 14.5% incidence (44 of 303) (among 303 women). Of these infections, 38% (17) were attributable to hrHPV type 35 and 20% (9) were due to hrHPV type 16. CONCLUSION The prevalence of hrHPV genotypes in Peru may differ from those observed in North America and Europe. Loreto appears to follow the prevalence trend observed in North America, with hrHPV type 16 accounting for the majority of cases. However, hrHPV type 35 may account for a greater contribution to the cervical cancer burden in La Libertad. Further research, specifically on cervical tumor specimens, is needed.

Introduction: Alternative methods of dry storage and transportation may be a viable alternative to the use of liquid storage medium for cervical samples, especially for screening programs in places with few resources. Objective: The objective of this study is to verify the viability and efficacy of human papillomavirus DNA (HPV-DNA) detection in cervical cell samples collected and stored on a Flinders Technology Associates (FTA) card (Whatman Indicating FTA® Elute Micro Card) and subsequently recovered in ethanol-based liquid medium and to compare the results to those obtained using samples stored directly in ethanol-based liquid medium. Study Design: Thirty-four women submitted to ETZ (excision of the transformation zone of the cervix) were included in this study. Before ETZ, 2 samples of exfoliated cervical cells were collected from each woman by a doctor and stored in ethanol-based liquid medium and on an FTA card. DNA recovery from FTA samples was performed using ethanol-based liquid medium. Detection of HPV-DNA in the samples was performed using the Cobas® 4800 HPV Test Platform. Results and Conclusions: The HPV-DNA detection positivity rates were 70.6% for the samples collected directly in liquid medium and 64.7% for the samples stored on the FTA card, with high detection accuracy in the DNA samples recovered from the FTA card (area under the curve = 0.958; 95% confidence interval = 0.890–1.000). The concordance between the results obtained using the 2 storage media was 94.1% (Kappa = 0.866). These preliminary results suggest that collection of cervical material on an FTA card may be an alternative to storage in liquid medium since the liquid medium has some limitations. In addition, DNA recovery from the card using ethanol-based liquid medium streamlines the workflow in the laboratory and reduces the cost associated with reagents, thereby facilitating access to the HPV test in places with few resources and potentially improving cervical cancer screening.

Background and objective Cervical cell classification has important clinical significance in cervical cancer screening at early stages. In contrast with the conventional classification methods which depend on hand-crafted or engineered features, Convolutional Neural Network (CNN) generally classifies cervical cells via learned deep features. However, the latent correlations of images may be ignored during CNN feature learning and thus influence the representation ability of CNN features. Methods We propose a novel cervical cell classification method based on Graph Convolutional Network (GCN). It aims to explore the potential relationship of cervical cell images for improving the classification performance. The CNN features of all the cervical cell images are firstly clustered and the intrinsic relationships of images can be preliminarily revealed through the clustering. To further capture the underlying correlations existed among clusters, a graph structure is constructed. GCN is then applied to propagate the node dependencies and thus yield the relation-aware feature representation. The GCN features are finally incorporated to enhance the discriminative ability of CNN features. Results Experiments on the public cervical cell image dataset SIPaKMeD from International Conference on Image Processing in 2018 demonstrate the feasibility and effectiveness of the proposed method. In addition, we introduce a large-scale Motic liquid-based cytology image dataset which provides the large amount of data, some novel cell types with important clinical significance and staining difference and thus presents a great challenge for cervical cell classification. We evaluate the proposed method under two conditions of the consistent staining and different staining. Experimental results show our method outperforms the existing state-of-arts methods according to the quantitative metrics (i.e. accuracy, sensitivity, specificity, F-measure and confusion matrices). Conclusions The intrinsic relationship exploration of cervical cells contributes significant improvements to the cervical cell classification. The relation-aware features generated by GCN effectively strengthens the representational power of CNN features. The proposed method can achieve the better classification performance and also can be potentially used in automatic screening system of cervical cytology.

Every two minutes one woman dies of cervical cancer globally, due to lack of sufficient screening. Given a whole slide image (WSI) obtained by scanning a microscope glass slide for a Liquid Based Cytology (LBC) based Pap test, our goal is to assist the pathologist to determine presence of precancerous or cancerous cervical anomalies. Inter-annotator variation, large image sizes, data imbalance, stain variations, and lack of good annotation tools make this problem challenging. Existing related work has focused on sub-problems like cell segmentation and cervical cell classification but does not provide a practically feasible holistic solution. We propose a practical system architecture which is based on displaying regions of interest on WSIs containing potential anomaly for review by pathologists to increase productivity. We build multiple deep learning classifiers as part of the proposed architecture. Our experiments with a dataset of ~19000 regions of interest provides an accuracy of ~89% for a balanced dataset both for binary as well as 6-class classification settings. Our deployed system provides a top-5 accuracy of ~94%.

Deep learning methods show promising results for overlapping cervical cell instance segmentation. However, in order to train a model with good generalization ability, voluminous pixel-level annotations are demanded which is quite expensive and time-consuming for acquisition. In this paper, we propose to leverage both labeled and unlabeled data for instance segmentation with improved accuracy by knowledge distillation. We propose a novel Mask-guided Mean Teacher framework with Perturbation-sensitive Sample Mining (MMT-PSM), which consists of a teacher and a student network during training. Two networks are encouraged to be consistent both in feature and semantic level under small perturbations. The teacher’s self-ensemble predictions from K-time augmented samples are used to construct the reliable pseudo-labels for optimizing the student. We design a novel strategy to estimate the sensitivity to perturbations for each proposal and select informative samples from massive cases to facilitate fast and effective semantic distillation. In addition, to eliminate the unavoidable noise from the background region, we propose to use the predicted segmentation mask as guidance to enforce the feature distillation in the foreground region. Experiments show that the proposed method improves the performance significantly compared with the supervised method learned from labeled data only, and outperforms state-of-the-art semi-supervised methods. Code: https://github.com/SIAAAAAA/MMT-PSM.

The aim of this work is to propose an ensemble of descriptors for Cervical Cell Classification. The system proposed here achieves strong discriminative power that generalizes well thanks to the combination of multiple descriptors based on different approaches, both learned and handcrafted. For each descriptor, a separate classifier is trained, then the set of classifiers is combined by sum rule. The system we propose here also presents a simple and effective method for boosting the performance of trained CNNs by combining the scores (using sum rule) of multiple CNNs into an ensemble. Different types of ensembles and different CNN topologies with different learning parameter sets are evaluated. Moreover, features extracted from tuned CNNs are used for training a set of Support Vector Machines (SVM). First, we validate our method on two cervical cell-related datasets; then, for more in-depth validation, we test the same system on other bioimage classification problems. Results show that the proposed system obtains state-of-the-art performance in all datasets, despite not being tuned on a specific dataset, i.e. the same descriptors with the same parameters are used in all the datasets. The MATLAB code of the descriptors will be available at https://github.com/LorisNanni.

It is necessary to realize the automatic detection of cervical cells in Pap Smears. We present an automatic cervical cell detection approach based on the so-called Dense-Cascade R-CNN (Dense-Cascade Region-based Convolutional Neural Networks). The approach consists of three modules: data augmentation, training set balancing (TSB), and the Dense-Cascade R-CNN. The data augmentation module carries out operations such as rotation, scale, flip, etc. on input images to increase the samples. The TSB module is used to balance the number of cervical cell samples of various classes in the training set after data augmentation. As for the Dense-Cascade R-CNN module, the residual neural network (ResNet) with 101 layers in a Cascade R-CNN is replaced by a dense connected convolution neural network (DenseNet) with 121 layers so as to improve the detection performance of cervical cells. We evaluated the proposed method on the Herlev dataset. The results show that our approach can improve both mean average precision (mAP) and mean average recall (mAR) for Cascade R-CNN. Our cervical cell automatic detection approach can be used as an auxiliary diagnostic tool for cervical cancer screening.

Background: Cervical cancer is one of the most common cancers in women worldwide with 122,844 women are diagnosed every year in India. 67,477 die from the disease. High-quality screening with cytology (Pap smear) has markedly reduced mortality from squamous cell cervical cancer. Objective: Efficacy of Kasīsādi Kṣāra Karma followed by Dārvyādi Yonivarti (Vaginal suppository) in cervical cell pathology was evaluated. Materials and Methods: Total 44 patients with cervical erosion diagnosed by Pap smear test were selected from the outpatient department of Prasutitantra and Streeroga, out of which three patients discontinued. The treatment protocol comprised of Kṣāra Karma by Kasīsādi Kṣāra in one sitting followed by Dārvyādi Yoni Varti of 3 gm once at bed time from next day for 21 days. The assessment was done with subjective criteria and Pap-smear after 45 days. Results: The results were observed to be highly significant in clinical features of disease such as yonitaḥ -srāva (77.67%), yoni-kaṇḍu (84.09%), yoni-dāha (87.5%), kaṭi -śūla (73.41%), udara -śūla ( 79.48%), mūtra- dāha (84%), daurbalya ( 72.34%) and area of erosion (85.96%), appearance of erosion (69.32%). Conclusion:Kasīsādi Kṣāra followed by Dārvyādi Yoni Varti was effective in the management of primitive cervical cell pathology.

Objective To assess the concordance of high-risk HPV (HR-HPV) testing with the Alinity assay on cervical samples collected with diverse collection/storage protocols (ThinPrep, SurePath, Cervicollect) and to assess inter-assay concordance of HR-HPV testing of cervical cell specimens with Alinity m HR HPV assay (Alinity) vs cobas® 4800 HPV assay (cobas). Methods Specimens were obtained from 560 women attending a Women's Health clinic. Two specimens were obtained from each woman with combinations of two of the three collection devices and aliquots were tested by the two assays. Results Alinity showed an agreement of 93.9%, Kappa = 0.89 (263/280) between ThinPrep and SurePath specimens; 97.5%, Kappa = 0.95 (347/356) and 92.9%, Kappa = 0.85 (104/112) between ThinPrep and SurePath aliquots taken before or after cytology processing, respectively. Cervi-Collect specimens showed an agreement of 94.6%, Kappa = 0.89 (265/280) with ThinPrep specimens. Compared to cobas, Alinity showed agreements of 94.3%, Kappa = 0.88 (395/419) and 91.8%, Kappa = 0.82 (257/280) between ThinPrep and SurePath specimens, respectively. Alinity and cobas detected genotypes 16/18 and other high-risk HPV types at similar rates and showed similar correlations with cytology grades. Conclusions Compared to cobas, Alinity performed equally well for detecting HPV in cervical specimens obtained with ThinPrep and SurePath. The Cervi-Collect device compared well to the other collection methods. Alinity is a reliable assay for simultaneous detection of HPV-16/18 and other high-risk genotypes in cervical specimens., Highlights • Alinity m HR HPV assay demonstrated very good agreement with ThinPrep and SurePath pre- and post-cytology cervical specimens. • Alinity m HR HPV had very good agreement with ThinPrep and Cervi-Collect specimens. • Alinity m HR HPV and cobas 4800 HPV had very good agreement and identified HPV-16/18 and other HR types.

Automation-assisted cervical screening via Pap smear or liquid-based cytology (LBC) is a highly effective cell imaging based cancer detection tool, where cells are partitioned into "abnormal" and "normal" categories. However, the success of most traditional classification methods relies on the presence of accurate cell segmentations. Despite sixty years of research in this field, accurate segmentation remains a challenge in the presence of cell clusters and pathologies. Moreover, previous classification methods are only built upon the extraction of hand-crafted features, such as morphology and texture. This paper addresses these limitations by proposing a method to directly classify cervical cells - without prior segmentation - based on deep features, using convolutional neural networks (ConvNets). First, the ConvNet is pre-trained on a natural image dataset. It is subsequently fine-tuned on a cervical cell dataset consisting of adaptively re-sampled image patches coarsely centered on the nuclei. In the testing phase, aggregation is used to average the prediction scores of a similar set of image patches. The proposed method is evaluated on both Pap smear and LBC datasets. Results show that our method outperforms previous algorithms in classification accuracy (98.3%), area under the curve (AUC) (0.99) values, and especially specificity (98.3%), when applied to the Herlev benchmark Pap smear dataset and evaluated using five-fold cross-validation. Similar superior performances are also achieved on the HEMLBC (H&E stained manual LBC) dataset. Our method is promising for the development of automation-assisted reading systems in primary cervical screening.

Multi-spectral imaging technique plays an important role in real-world applications such as medicine and medical detections. This paper proposes a cervical cancer cell screening method to simultaneously adopt TBS classification and DNA quantitative analysis for a single cell smear. Through using compound staining on a smear, the cytoplasm is stained by Papanicolauo and the nucleus is stained by Feulgen. The main evaluation parameter is the DNA content of the nucleus, not the subjective description of cell morphology, which is more objective than the TBS classification method and reduces the chances of missing a diagnosis due to subjective factors. Each nucleus has its own DI value and color image of the whole cell, which is convenient for doctors as it allows them to review and confirm the morphology of cells with a nucleus DI of over 2.5. Mouse liver smears and cervical cases are utilized as the measuring specimens to evaluate the performance of the microscope multi-spectral imaging system, illustrative results demonstrate that the proposed system qualifies, with high accuracy and reliability, and further presents wide application prospects in the early diagnosis of cervical cancer.

This paper presents a novel hierarchical nuclei segmentation algorithm for isolated and overlapping cervical cells based on a narrow band level set implementation. Our method applies a new multiscale analysis algorithm to estimate the number of clusters in each image region containing cells, which turns into the input to a narrow band level set algorithm. We assess the nuclei segmentation results on three public cervical cell image databases. Overall, our segmentation method outperformed six state-of-the-art methods concerning the number of correctly segmented nuclei and the Dice coefficient reached values equal to or higher than 0.90. We also carried out classification experiments using features extracted from our segmentation results and the proposed pipeline achieved the highest average accuracy values equal to 0.89 and 0.77 for two-class and three-class problems, respectively. These results demonstrated the suitability of the proposed segmentation algorithm to integrate decision support systems for cervical cell screening.

Cervical cancer that is a disease, in which malignant (cancer) cells form in the tissues of the cervix, is one of the fourth leading causes of cancer death in female community worldwide. The cervical cancer can be prevented and/or cured if it is diagnosed in the pre-cancerous lesion stage or earlier. A common physical examination technique widely used in the screening is called Papanicolaou test or Pap test which is used to detect the abnormality of the cell. Due to intricacy of the cell nature, automating of this procedure is still a herculean task for the pathologist. This paper addresses solution for the challenges in terms of a simple and novel method to segment and classify the cervical cell automatically. The primary step of this procedure is pre-processing in which de-nosing, de-correlation operation and segregation of colour components are carried out, Then, two new techniques called Morphological and Statistical Edge based segmentation and Morphological and Statistical Region Based segmentation Techniques- put forward in this paper, and that are applied on the each component of image to segment the nuclei from cervical image. Finally, all segmented colour components are combined together to make a final segmentation result. After extracting the nuclei, the morphological features are extracted from the nuclei. The performance of two techniques mentioned above outperformed than standard segmentation techniques. Besides, Morphological and Statistical Edge based segmentation is outperformed than Morphological and Statistical Region based Segmentation. Finally, the nuclei are classified based on the morphological value. The segmentation accuracy is echoed in classification accuracy. The overall segmentation accuracy is 97%.

In this paper, the classication capability of Calinski-Harabasz criterion as an internal cluster validation measure has been evaluated for clustering-based region discrimination on cervical cells. In this approach, subregions in the sample image are initially randomly constructed to be the individuals of the population. At each generation, individuals are evaluated according to their Accordingly a novel genetic structure for meta heuristic area isolation is proposed. Evaluation of proposed combination of genetic algorithm and Calinski-Harabasz measure is achieved by experiments, conducted on real cervical cell samples. We have used two separate cluster validity measures to evaluate the performance of the clustering approach. Jaccard index and F-score are utilized for objective comparison. Results shows that, Calinski-Harabasz criteria may have a better performance with proposed novel genetic structure and presented mechanism may have great potential on discrimination of specic regions.

Accurate segmentation of cervical cells in Pap smear images is an important step in automatic pre-cancer identification in the uterine cervix. One of the major segmentation challenges is overlapping of cytoplasm, which has not been well-addressed in previous studies. To tackle the overlapping issue, this paper proposes a learning-based method with robust shape priors to segment individual cell in Pap smear images to support automatic monitoring of changes in cells, which is a vital prerequisite of early detection of cervical cancer. We define this splitting problem as a discrete labeling task for multiple cells with a suitable cost function. The labeling results are then fed into our dynamic multi-template deformation model for further boundary refinement. Multi-scale deep convolutional networks are adopted to learn the diverse cell appearance features. We also incorporated high-level shape information to guide segmentation where cell boundary might be weak or lost due to cell overlapping. An evaluation carried out using two different datasets demonstrates the superiority of our proposed method over the state-of-the-art methods in terms of segmentation accuracy.

Cell instance segmentation in Pap smear image remains challenging due to the wide existence of occlusion among translucent cytoplasm in cell clumps. Conventional methods heavily rely on accurate nuclei detection results and are easily disturbed by miscellaneous objects. In this paper, we propose a novel Instance Relation Network (IRNet) for robust overlapping cell segmentation by exploring instance relation interaction. Specifically, we propose the Instance Relation Module to construct the cell association matrix for transferring information among individual cell-instance features. With the collaboration of different instances, the augmented features gain benefits from contextual information and improve semantic consistency. Meanwhile, we proposed a sparsity constrained Duplicate Removal Module to eliminate the misalignment between classification and localization accuracy for candidates selection. The largest cervical Pap smear (CPS) dataset with more than 8000 cell annotations in Pap smear image was constructed for comprehensive evaluation. Our method outperforms other methods by a large margin, demonstrating the effectiveness of exploring instance relation.

We evaluate the characteristic of the normal epithelial cervical cell in Pap Smear images, using feature analysis. The evaluation affects the determination of proper pap smear image determination. This study aims to analyze the performance of feature selection on data classification and discovering features which significantly affect the classification of the normal epithelial cervical cell. Feature selection process has been done to 54 features in the nuclei area and the cytoplasm of the cervical epithelial cell, using Feature Subset Selection. Furthermore, we compare the performance of two classification methods: K-Nearest Neighbors (KNN) and Backpropagation. Both methods resulting in the same 12 features to differentiate between normal cervical cells. The classification accuracies for both methods are 92.29% for KNN and 91.51% for Backpropagation.

Development of an accurate and automated algorithm to completely segment cervical cells in Pap images is still one of the most challenging tasks. The main reasons are the presence of overlapping cells and the lack of guiding mechanism for the convergence of ill-defined contours to the actual cytoplasm boundaries. In this paper, we propose a novel method to address these problems based on level set method (LSM). Firstly, we proposed a morphological scaling-based topology filter (MSTF) and derived a new mathematical toolbox about vector calculus for evolution of level set function (LSF). Secondly, we combine MSTF and the mathematical toolbox into a multifunctional filtering algorithm 2D codimension two-object level set method (DCTLSM) to split touching cells. The DCTLSM can morphologically scale up and down the contour while keeping part of the contour points fixed. Thirdly, we design a contour scanning strategy as the evolution method of LSF to segment overlapping cells. In this strategy, a cutting line can be detected by morphologically scaling the union LSF of the pairs of cells. Then, we used this cutting line to construct a velocity field with an effective guiding mechanism for attracting and repelling LSF. The performance of the proposed algorithm was evaluated quantitatively and qualitatively on the ISBI-2014 dataset. The experimental results demonstrated that the proposed method is capable of fully segmenting cervical cells with superior segmentation accuracy compared with recent peer works.

The nuclei and cytoplasm segmentation of cervical cells is a well studied problem. However, the current segmentation algorithms are not robust to clinical practice due to the high computational cost or because they cannot accurately segment cells with high overlapping. In this paper, we propose a method that is capable of segmenting both cytoplasm and nucleus of each individual cell in a clump of overlapping cells. The proposed method consists of three steps: 1) cellular mass segmentation; 2) nucleus segmentation; 3) cytoplasm identification based on an active contour method. We carried out experiments on both synthetic and real cell images. The performance evaluation of the proposed method showed that it was less sensitive to the increase in the number of cells per image and the overlapping ratio against two other existing algorithms. It has also achieved a promising low processing time and, hence, it has the potential to support expert systems for cervical cell recognition.

This study was conducted to 1206 women who had cervical cancer screening at Chonburi Cancer Hospital. The spilt-sample study aimed to compare the efficacy of abnormal cervical cells detection between liquid-based cytology (LBC) and conventional cytology (CC). The collection of cervical cells was performed by broom and directly smeared on a glass slide for CC then the rest of specimen was prepared for LBC. All slides were evaluated and classified by The Bethesda System. The results of the two cytological tests were compared to the gold standard. The LBC smear significantly decreased inflammatory cell and thick smear on slides. These two techniques were not difference in detection rate of abnormal cytology and had high cytological diagnostic agreement of 95.7%. The histologic diagnosis of cervical tissue was used as the gold standard in 103 cases. Sensitivity, specificity, positive predictive value, negative predictive value, false positive, false negative and accuracy of LBC at ASC-US cut off were 81.4, 75.0, 70.0, 84.9, 25.0, 18.6 and 77.7%, respectively. CC had higher false positive and false negative than LBC. LBC had shown higher sensitivity, specificity, PPV, NPV and accuracy than CC but no statistical significance. In conclusion, LBC method can improve specimen quality, more sensitive, specific and accurate at ASC-US cut off and as effective as CC in detecting cervical epithelial cell abnormalities.

The identification of normal and abnormal cells is considered as one of the most challenging task for computer assisted Pap smear analysis system especially when abnormal cells are hidden behind overlapped cells. The complexity of the problem depends on whether only cytoplasm of two cells are overlapped, or only nuclei are overlapped with disjoint cytoplasm, and in some case both cytoplasm and nuclei are overlapped. Sometimes, Pap smear sample contains mixture of cells with disjoint/overlapped cytoplasm and nuclei. Hence, there is need for algorithm which segments cells from the cluster of overlapped cells. In case of overlapped nuclei, identifying the point of overlapping accurately is one of the significant steps in segmenting overlapped cells. This paper discusses image processing-based method which segment disjoint nuclei and identifies the point of intersection called as concavity point in the cluster of cells where only nuclei are overlapped.

The accurate nuclei segmentation of cervical cell images is a very vital step in automated cervical diseases diagnosis. However, segmentation challenges exist because of problems such as nuclei embedment into cytoplasm folding or overlapping areas, impurity interference, low contrast and nuclei variation in shape and size. These problems can cause the nuclei segmentation results not so ideal. This paper presents an automated method for cells nuclei detection in cervical cell images. We propose an intermediate segment qualifier to categorize the nuclei segmentation results after the nuclei segmentation based on the integration of convolutional neural network and simple linear iterative clustering superpixel method. Then we apply a gradient vector flow snake model for further refinement. We evaluate the proposed method using the ISBI 2014 challenge dataset. In the experiments, we demonstrate that our method performs well and is preferable to the state-of-the-art approaches.

Background A pilot screening campaign in Rwanda, based on careHPV-testing followed by visual inspection with acetic acid triage (careHPV+VIA triage), was evaluated against other WHO-recommended screening options, namely HPV screen-and-treat and VIA screen-and-treat. Methods 764 women aged 30-69 underwent at visit 1: i) VIA, and cervical cell collection for ii) careHPV in Rwanda, and iii) liquid-based cytology and GP5+/6+ HR-HPV PCR in The Netherlands. All 177 women positive by VIA, careHPV and/or PCR were recalled, of whom 84% attended. At visit 2, VIA was again used to triage screen-positive women for treatment and to obtain biopsies from all women either from visible lesions or at 12 o’clock of the squamocolumnar junction. Cross-sectional screening indices were estimated primarily against histological high-grade squamous intraepithelial lesions or worse (hHSIL+), after imputation of missing histology data, based on 1-visit or 2-visit approaches. Results In a 1-visit screen-and-treat approach, VIA had sensitivity and specificity of 41% and 96%, respectively, versus 71% and 88% for careHPV, and 88% and 86% for PCR. In a 2-visit approach (in which hHSIL+ imputed among women without visit 2 were considered untreated) careHPV sensitivity dropped to 59% due to loss of 13% of hHSIL+. For careHPV+VIA triage, sensitivity dropped further to 35%, as another 24% of hHSIL+ were triaged to no treatment. Conclusions CareHPV was not as sensitive as gold-standard PCR, but detected considerably more hHSIL+ than VIA. However, due to careHPV-positive hHSIL+ women being lost to follow-up and/or triaged to no treatment, 2-visit careHPV+VIA triage did not perform better than VIA screen-and-treat. Electronic supplementary material The online version of this article (10.1186/s12905-018-0549-5) contains supplementary material, which is available to authorized users.

Objectives We analyzed the chromosomal-arm-level copy number alterations (CNAs) in the cervical exfoliative cell and tissue samples by using the low-coverage whole genomic sequencing technique. Methods In this study, we retrospectively collected 55 archived exfoliated cervical cell suspension samples and the corresponding formalin-fixed and paraffin-embedded tissue section samples including 27 invasive cervical cancer and 28 control cases. We also collected 19 samples of the cervical exfoliative cells randomly from women to verify the new algorithm model. We analyzed the CNAs in cervical exfoliated cell and tissue samples by using the low-coverage next generation of sequencing. Results In the model-building study, multiple chromosomal-arm-level CNAs were detected in both cervical exfoliated cell and tissue samples of all cervical cancer cases. By analyzing the consistency of CNAs between exfoliated cells and cervical tissue samples, as well as the heterogeneity in individual patient, we also established a C-score algorithm model according to the chromosomal-arm-level changes of 1q, 2q, 3p, 7q. The C-score model was then validated by the pathological diagnosis of all 74 exfoliated cell samples (including 55 cases in model-building group and 19 cases in verification group). In our result, a cutoff value of C-score >6 showed 100% sensitivity and 100% specificity in the diagnosis of cervical cancer. Conclusion In this study, we found that CNAs of cervical exfoliated cell samples could robustly distinguish invasive cervical cancer from cancer-free tissues. And we have also developed a C-score algorithm model to process the sequencing data in a more standardized and automated way.

Automated classification of cervical cancer cells has the potential to reduce high mortality rates due to cervical cancer in developing countries. However traditional algorithms for the same depend on accurate segmentation of cells, which in itself is an open problem. Often the algorithms are also not evaluated by considering the huge inter-observer variability in ground truth labels. We propose a new deep learning algorithm that does not depend on accurate segmentation by directly classifying image patches with cells. We evaluate the proposed algorithm on the popular Herlev dataset and show that it achieves state of the art accuracy while being extremely fast. The experimental results are also demonstrated using AIndra dataset collected by us, which also captures the inter observer variability.

To investigate the clinical significance of human wings apart-like (hWAPL) genetic polymorphisms in cervical carcinogenesis. hWAPL polymorphisms and human papillomavirus (HPV) types were examined in 175 cervical smears of exfoliated cervical cell samples using a real-time polymerase chain reaction system. A significant difference was detected in the frequency of the CC genotype between the HPV(+) low-grade squamous intraepithelial lesion (LSIL) and high-grade squamous intraepithelial lesion (HSIL) groups [Odds ratio 0.21, 95% confidence interval (CI) 0.0723–0.61; P = 0.0029]. A significant difference was noted in the frequency of the CC genotype between the high-risk HPV-positive LSIL and HSIL groups (odds ratio 0.2955, 95% CI 0.0893–0.9771; P = 0.0414). The CC genotype of hWAPL gene promoter polymorphism may be associated with cervical carcinogenesis.

Information on the prevalence and type distribution of human papillomavirus (HPV) among Malaysian women is currently limited. The present study therefore aimed to provide an updated estimate on the prevalence and type distribution of HPV among Malaysian women with and without cervical cancer. Total DNA was isolated from the cervical cell specimens of 185 histopathologically confirmed cervical cancer patients and 209 cancer-free healthy females who were tested negative in a recent Pap test. Viral-specific DNA was subsequently amplified with biotinylated primers and hybridized to HPV type-specific probes via a proprietary “flow-through hybridization” process for determination of HPV genotype. It was demonstrated that 83.2% of the cervical cancer patients and none (0.0%) of the cancer-free females were positive for HPV infection. Among HPV-positive subjects, 14 different viral genotypes were observed, namely HPV16, 18, 31, 33, 35, 45, 52, 53, 58, 66/68, 73, 81, 82, and 84/26. A total of 91.6% of the HPV-positive subjects had single-type HPV infections and the remaining 8.4% were simultaneously infected by two HPV genotypes. The most common HPV infections found were HPV16 (35.7%), HPV18 (26.0%), HPV58 (9.1%), and HPV33 (7.1%) single-type infections, followed by HPV16 + HPV18 co-infections (5.2%). The study has successfully provided an updated estimate on the prevalence and type distribution of HPV among Malaysian women with and without cervical cancer. These findings could contribute valuable information for appraisal of the impact and cost-effectiveness of prophylactic HPV vaccines in the Malaysian population.

Automatic detection of abnormal cells from cervical smear images is extremely demanded in annual diagnosis of women’s cervical cancer. For this medical cell recognition problem, there are three different feature sections, namely cytology morphology, nuclear chromatin pathology and region intensity. The challenges of this problem come from feature combination s and classification accurately and efficiently. Thus, we propose an efficient abnormal cervical cell detection system based on multi-instance extreme learning machine (MI-ELM) to deal with above two questions in one unified framework. MI-ELM is one of the most promising supervised learning classifiers which can deal with several feature sections and realistic classification problems analytically. Experiment results over Herlev dataset demonstrate that the proposed method outperforms three traditional methods for two-class classification in terms of well accuracy and less time.

Cervical nuclei carry substantial diagnostic information for cervical cancer. Therefore, in automation-assisted reading of cervical cytology, automated and accurate segmentation of nuclei is essential. This paper proposes a novel approach for segmentation of cervical nuclei that combines fully convolutional networks (FCN) and graph-based approach (FCNG). FCN is trained to learn the nucleus high-level features to generate a nucleus label mask and a nucleus probabilistic map. The mask is used to construct a graph by image transforming. The map is formulated into the graph cost function in addition to the properties of the nucleus border and nucleus region. The prior constraints regarding the context of nucleus-cytoplasm position are also utilized to modify the local cost functions. The globally optimal path in the constructed graph is identified by dynamic programming. Validation of our method was performed on cell nuclei from Herlev Pap smear dataset. Our method shows a Zijdenbos similarity index (ZSI) of 0.92 ± 0.09, compared to the best state-of-the-art approach of 0.89 ± 0.15. The nucleus areas measured by our method correlated strongly with the independent standard (r2 = 0.91).