Cervical Intraepithelial Neoplasia Classification Research Articles

Net benefit of diagnostic tests for multistate diseases: an indicator variables approach

ABSTRACT A limitation of the common measures of diagnostic test performance, such as sensitivity and specificity, is that they do not consider the relative importance of false negative and false positive test results, which are likely to have different clinical consequences. Therefore, the use of classification or prediction measures alone to compare diagnostic tests or biomarkers can be inconclusive for clinicians. Comparing tests on net benefit can be more conclusive because clinical consequences of misdiagnoses are considered. The literature suggested evaluating the binary diagnostic tests based on net benefit, but did not consider diagnostic tests that classify more than two disease states, e.g., stroke subtype (large-artery atherosclerosis, cardioembolism, small-vessel occlusion, stroke of other determined etiology, stroke of undetermined etiology), skin lesion subtype, breast cancer subtypes (benign, mass, calcification, architectural distortion, etc.), METAVIR liver fibrosis state (F0- F4), histopathological classification of cervical intraepithelial neoplasia (CIN), prostate Gleason grade, brain injury (intracranial hemorrhage, mass effect, midline shift, cranial fracture) . Other diseases have more than two stages, such as Alzheimer's disease (dementia due to Alzheimer's disease, mild cognitive disability (MCI) due to Alzheimer's disease, and preclinical presymptomatics due to Alzheimer's disease). In diseases with more than two states, the benefits and risks may vary between states. This paper extends the net-benefit approach of evaluating binary diagnostic tests to multi-state clinical conditions to rule-in or rule-out a clinical condition based on adverse consequences of work-up delay (due to false negative test result) and unnecessary workup (due to false positive test result). We demonstrate our approach with numerical examples and real data.

Update in pathological classification of cervical intraepithelial neoplasia and cervical cancer

Update in pathological classification of cervical intraepithelial neoplasia and cervical cancer

Using Natural Language Processing to Improve Discrete Data Capture From Interpretive Cervical Biopsy Diagnoses at a Large Health Care Organization.

The terminology used by pathologists to describe and grade dysplasia and premalignant changes of the cervical epithelium has evolved over time. Unfortunately, coexistence of different classification systems combined with nonstandardized interpretive text has created multiple layers of interpretive ambiguity. To use natural language processing (NLP) to automate and expedite translation of interpretive text to a single most severe, and thus actionable, cervical intraepithelial neoplasia (CIN) diagnosis. We developed and applied NLP algorithms to 35 847 unstructured cervical pathology reports and assessed NLP performance in identifying the most severe diagnosis, compared to expert manual review. NLP performance was determined by calculating precision, recall, and F score. The NLP algorithms yielded a precision of 0.957, a recall of 0.925, and an F score of 0.94. Additionally, we estimated that the time to evaluate each monthly biopsy file was significantly reduced, from 30 hours to 0.5 hours. A set of validated NLP algorithms applied to pathology reports can rapidly and efficiently assign a discrete, actionable diagnosis using CIN classification to assist with clinical management of cervical pathology and disease. Moreover, discrete diagnostic data encoded as CIN terminology can enhance the efficiency of clinical research.

Automated Cervical Digitized Histology Whole-Slide Image Analysis Toolbox

Background: Cervical intraepithelial neoplasia (CIN) is regarded as a potential precancerous state of the uterine cervix. Timely and appropriate early treatment of CIN can help reduce cervical cancer mortality. Accurate estimation of CIN grade correlated with human papillomavirus type, which is the primary cause of the disease, helps determine the patient's risk for developing the disease. Colposcopy is used to select women for biopsy. Expert pathologists examine the biopsied cervical epithelial tissue under a microscope. The examination can take a long time and is prone to error and often results in high inter-and intra-observer variability in outcomes. Methodology: We propose a novel image analysis toolbox that can automate CIN diagnosis using whole slide image (digitized biopsies) of cervical tissue samples. The toolbox is built as a four-step deep learning model that detects the epithelium regions, segments the detected epithelial portions, analyzes local vertical segment regions, and finally classifies each epithelium block with localized attention. We propose an epithelium detection network in this study and make use of our earlier research on epithelium segmentation and CIN classification to complete the design of the end-to-end CIN diagnosis toolbox. Results: The results show that automated epithelium detection and segmentation for CIN classification yields comparable results to manually segmented epithelium CIN classification. Conclusion: This highlights the potential as a tool for automated digitized histology slide image analysis to assist expert pathologists.

Classification of Cervical Intraepithelial Neoplasia (CIN) using fine-tuned Convolutional Neural Networks

Convolutional Neural Network (CNN) is considered one of the most successful deep learning techniques used in classification or diagnosis of medical images. However, CNN requires a high computational resource and time; and a large dataset which most medical images (cervix) do not possess. In order to compensate for these shortcomings, we propose an optimized fine-tuned CNN model to classify cervix images into Cervical Intraepithelial Neoplasia grades (CIN 1,2,3) normal and cancerous cervix images. This classification ensures that patients are diagnosed correctly, and appropriate treatments are administered. Deep learning techniques such as Data Augmentation, 1 cycle policy for optimal learning rates selection, Discriminative Fine-Tuning, Mixed Precision Training were used to optimize the fine-tuned DenseNet CNN model. The model achieved 96.3% accuracy, the specificity of 98.86%, and sensitivity of 94.97% on the datasets.

Cervical Precancerous Lesion Detection Based on Deep Learning of Colposcopy Images

With the rapid development of deep learning, automatic lesion detection is widely used in clinical screening. In this paper, we make use of convolutional neural network (CNN) algorithm to help medical experts detect cervical precancerous lesion during the colposcopic screening, especially in the classification of cervical intraepithelial neoplasia (CIN). Firstly, the original image data is classified into six categories: normal, cervical cancer, mild (CIN1), moderate (CIN2), severe (CIN3) and cervicitis, which are further augmented to solve the problem of few samples of endoscopic images and non-uniformity for each category. Then, a CNN-based model is built and trained for the multi-classification of the six categories, we have added some optimization algorithms to this CNN model to make the training parameters more effective. For the test dataset, the accuracy of the proposed CNN model algorithm is 89.36%, and the area under the receiver operating characteristic (ROC) curve is 0.954. Among them, the accuracy is increased by 18%–32% compared with other traditional learning methods, which is 9%–20% higher than several commonly used deep learning models. At the same number of iterations, the time consumption of proposed algorithm is only one quarter of other deep learning models. Our study has demonstrated that cervical colposcopic image classification based on artificial intelligence has high clinical applicability, and can facilitate the early diagnosis of cervical cancer.

DeepCIN: Attention-Based Cervical histology Image Classification with Sequential Feature Modeling for Pathologist-Level Accuracy

Background: Cervical cancer is one of the deadliest cancers affecting women globally. Cervical intraepithelial neoplasia (CIN) assessment using histopathological examination of cervical biopsy slides is subject to interobserver variability. Automated processing of digitized histopathology slides has the potential for more accurate classification for CIN grades from normal to increasing grades of pre-malignancy: CIN1, CIN2, and CIN3. Methodology: Cervix disease is generally understood to progress from the bottom (basement membrane) to the top of the epithelium. To model this relationship of disease severity to spatial distribution of abnormalities, we propose a network pipeline, DeepCIN, to analyze high-resolution epithelium images (manually extracted from whole-slide images) hierarchically by focusing on localized vertical regions and fusing this local information for determining Normal/CIN classification. The pipeline contains two classifier networks: (1) a cross-sectional, vertical segment-level sequence generator is trained using weak supervision to generate feature sequences from the vertical segments to preserve the bottom-to-top feature relationships in the epithelium image data and (2) an attention-based fusion network image-level classifier predicting the final CIN grade by merging vertical segment sequences. Results: The model produces the CIN classification results and also determines the vertical segment contributions to CIN grade prediction. Conclusion: Experiments show that DeepCIN achieves pathologist-level CIN classification accuracy.

Comparison of Classifier Configurations for the Classification of Cervical Intraepithelial Neoplasia Using Acetic Acid Test Images

Cervical cancer represents a major cause of death for women. Automatic classification of cervical images from acetic acid test could serve as a promising screening tool for cervical cancer. Despite an increasing volume of studies on automatic classification of cervical images, reported methods varied markedly in terms of features and classifiers used, and therefore the performance. The classification performance using different configurations of the classifier has not been well characterized. The objective of this study was to evaluate several frequently used features and classifiers in acetic-acid cervical image based cervical intraepithelial neoplasia classification. Seven typically used color or texture-based features and four frequently used classifiers (Support Vector Machine, Random Forest, Back-Propagation Neural Network and K-Nearest Neighbors) were included in the comparison based on a balanced large sample size including 175 CIN negative and 175 CIN positive patients. The results showed that the Support Vector Machine demonstrated the best classification accuracy when a subset of features was used. The finding of this study may provide useful reference values to the development of an automatic cervical cancer screening tool.

A Hybrid Deep Learning and Handcrafted Feature Approach for Cervical Cancer Digital Histology Image Classification

Cervical cancer is the second most common cancer affecting women worldwide but is curable if diagnosed early. Routinely, expert pathologists visually examine histology slides for assessing cervix tissue abnormalities. A localized, fusion-based, hybrid imaging and deep learning approach is explored to classify squamous epithelium into cervical intraepithelial neoplasia (CIN) grades for a dataset of 83 digitized histology images. Partitioning the epithelium region into 10 vertical segments, 27 handcrafted image features and rectangular patch, sliding window-based convolutional neural network features are computed for each segment. The imaging and deep learning patch features are combined and used as inputs to a secondary classifier for individual segment and whole epithelium classification. The hybrid method achieved a 15.51% and 11.66% improvement over the deep learning and imaging approaches alone, respectively, with a 80.72% whole epithelium CIN classification accuracy, showing the enhanced epithelium CIN classification potential of fusing image and deep learning features.

A Fuzzy Reasoning Model for Cervical Intraepithelial Neoplasia Classification Using Temporal Grayscale Change and Textures of Cervical Images During Acetic Acid Tests

Objective: A novel fuzzy reasoning model using temporal grayscale change and texture information of acetic acid test cervical images was developed to classify the patients at risk for Cervical Intraepithelial Neoplasia (CIN). Methods: Pre- and post-acetic acid test images were obtained from 505 patients (383 CIN negative and 122 CIN positive). An automatic image segmentation algorithm was implemented to extract the acetowhite region, followed by feature extraction of the: 1) temporal grayscale change from pre- to post-images; 2) texture coarseness; and 3) texture complexity of post-test images. The index of CIN was derived based on fuzzy reasoning incorporating expert knowledge. Logistic regression was built with cross validation to compare the classification performance between different combinations of features. Results: The averaged sensitivity was 80.8%, 80.9%, and 82.8% and specificity was 82.0%, 87.4%, and 86.2% for three individual features, respectively. The combination of all three features significantly improved the sensitivity (84.7%) without a significant loss of specificity (86.5%). The fuzzy reasoning model further improved the sensitivity significantly (sensitivity 85.9% and specificity 86.6%). Conclusion: Image texture features outperformed temporal grayscale change in specificity. Combining grayscale- and texture-based features could improve the overall classification performance, creating a synergistic effect. The proposed fuzzy reasoning model could further increase the sensitivity without requiring additional features. Significance: The proposed automatic CIN classification algorithm could provide a useful screening tool in the prevention of cervical cancers.

Diagnostic value of p16/mcm2 dual staining in cervical intraepithelial neoplasia and its association with high-risk HPV infection

Objective: To study the expression of p16/mcm2 immunocytochemical dual staining in cervical lesions and its association with high-risk HPV infection, and discuss its clinical value in cervical cancer screening. Methods: From May to December 2015, a total of 1 127 women receiving cervical cancer screening, high-risk HPV (HR-HPV) test and liquid-based cytology test were included in the study. p16/mcm2 immunocytochemical dual staining was performed on residual cytology specimens and the results were compared with histopathology results. Results: p16/mcm2 had a higher expression risk in HPV16/18 group and other HR-HPV group compared with HPV negative group, with OR of 15.95 (95%CI: 9.59-26.51) and 10.53 (95%CI: 7.41-14.98), respectively. The positive rate of p16/mcm2 increased with cervical intraepithelial neoplasia (CIN) severity, and was higher in both CIN2 group and CIN3 group than in benign lesion group (P<0.05). The overall sensitivity of p16/mcm2 to detect CIN2+and CIN3+lesions were 86.1% and 92.0%, respectively, and the overall specificity were 46.1% and 44.4%, respectively. In group with cytologic diagnoses of atypical squamous cells (ASC) and low-grade squamous intraepithelial lesion (LSIL), the sensitivity to detect CIN2+and CIN3+lesions were 85.7% and 87.5%, respectively, and the specificity were 45.5% and 44.1%, respectively. Conclusions: p16/mcm2 dual staining has higher sensitivity than cytology test and better specificity than HPV test. It can identify high-grade cervical lesions and guide the classification of CIN. p16/mcm2 might be used as an innovative biomarker for cervical cancer screening.

Clinical value of p16/Ki-67 immunocytochemical dual staining in cervical cancer screening

Objective: to investigate the clinical value of p16/Ki-67 immunocytochemical dual staining (abbreviated as p16/Ki-67 dual staining) in cervical intraepithelial neoplasia (CIN) and cervical cancer screening. Methods: From July to November 2015, a total of 980 women attending cervical cancer screening and receiving high-risk human papillomavirus (HR-HPV) test and thinprep cytologic test (TCT) were included in the study. p16/Ki-67 immunocytochemical dual staining was performed on residual cytologic specimens and compared with histopathology results. Results: The expression risks of p16/Ki-67 in HPV16/18 group and another HR-HPV group were higher than HPV negative group, with an odds ratio of 10.64 (95%CI: 5.66~20.02) and 5.40 (95%CI: 3.62~8.04), respectively. The positive rate of p16/Ki-67 increased with the grade of TCT and histologic diagnosis, and was higher in both CIN2 and CIN3 groups than normal group (P<0.05). The sensitivity of p16/Ki-67 to detect CIN2+ and CIN3+ lesions was 89.3% and 94.1%, respectively, and the specificity was 69.3% and 66.8%, respectively. The sensitivity of TCT to detect CIN2+ and CIN3+ lesions was 60.7% and 64.7%, respectively, and the specificity was 49.3% and 49.1%, respectively. Conclusions: Compared with TCT, p16/Ki-67 dual staining has higher sensitivity and specificity. It can identify high-grade cervical lesions and guide the classification of CIN. p16/Ki-67 dual staining in conjunction with HPV test may be considered as an efficient method for cervical cancer screening.

Cervical intraepithelial neoplasia (CIN) in African women living with HIV: role and effect of rigorous histopathological review by a panel of pathologists in the HARP study endpoint determination

AIMSTo analyse the effect of the expert end-point committee (EPC) review on histological endpoint classification of cervical intraepithelial neoplasia (CIN).MethodsA cohort of women living with HIV were recruited in Burkina...

Application value of detection on stathmin, p16 and Ki-67 in the cervical intractable cases

Objective To investigate the clinical application value of stathmin, p16 and Ki-67 in the cervical intractable cases. Methods Immunohistochemical method was used to detect the expressions of stathmin, p16 and Ki-67 in surgical specimens of 288 cervical intractable cases, including 30 cases of cervical benign changes, 70 cases of cervical intraepithelial neoplasia (CIN) Ⅰ, 78 cases of CINⅡ, 85 cases of CIN Ⅲ and 25 cases of squamous cell carcinoma (SCC, as control group). The application value of stathmin, p16 and Ki-67 in the cervical cases were analyzed. Results The positive expression rates of Ki-67 of cervical benign changes and CINⅠwere 20.0 % (6/30) and 54.3 % (38/70) (χ2 = 3.29, P > 0.05). The expression rates of Ki-67 in CINⅡ, CINⅢ and SCC were all 100.0 %, and compared with the cervix benign changes, the differences were statistically significant (χ2= 112, P 0.05), but the expression rates in CINⅢ and SCC were higher than those in cervical benign change, CIN Ⅰand CIN Ⅱ(P < 0.01). The positive expressions of stathmin, p16 and Ki-67 in each group of CIN were positively correlated (r = 0.412, P < 0.05). Conclusions Combined detection of p16 and Ki-67 can assist in the differential diagnosis of cervical intractable cases, and provide objective indicators for the classification and accurate diagnosis of CIN. Combined detection of p16 and stathmin may help to identify high-grade, low-grade CIN and cervix benign changes for the reduction of over-treatment. Key words: Cervical intraepithelial neoplasia; Uterine cervical diseases; Stathmin; p16; Ki-67; Diagnosis

Enhancements in localized classification for uterine cervical cancer digital histology image assessment

Background: In previous research, we introduced an automated, localized, fusion-based approach for classifying uterine cervix squamous epithelium into Normal, CIN1, CIN2, and CIN3 grades of cervical intraepithelial neoplasia (CIN) based on digitized histology image analysis. As part of the CIN assessment process, acellular and atypical cell concentration features were computed from vertical segment partitions of the epithelium region to quantize the relative distribution of nuclei. Methods: Feature data was extracted from 610 individual segments from 61 images for epithelium classification into categories of Normal, CIN1, CIN2, and CIN3. The classification results were compared against CIN labels obtained from two pathologists who visually assessed abnormality in the digitized histology images. In this study, individual vertical segment CIN classification accuracy improvement is reported using the logistic regression classifier for an expanded data set of 118 histology images. Results: We analyzed the effects on classification using the same pathologist labels for training and testing versus using one pathologist labels for training and the other for testing. Based on a leave-one-out approach for classifier training and testing, exact grade CIN accuracies of 81.29% and 88.98% were achieved for individual vertical segment and epithelium whole-image classification, respectively. Conclusions: The Logistic and Random Tree classifiers outperformed the benchmark SVM and LDA classifiers from previous research. The Logistic Regression classifier yielded an improvement of 10.17% in CIN Exact grade classification results based on CIN labels for training-testing for the individual vertical segments and the whole image from the same single expert over the baseline approach using the reduced features. Overall, the CIN classification rates tended to be higher using the training-testing labels for the same expert than for training labels from one expert and testing labels from the other expert. The Exact class fusion- based CIN discrimination results obtained in this study are similar to the Exact class expert agreement rate.

Nuclei-Based Features for Uterine Cervical Cancer Histology Image Analysis With Fusion-Based Classification.

Cervical cancer, which has been affecting women worldwide as the second most common cancer, can be cured if detected early and treated well. Routinely, expert pathologists visually examine histology slides for cervix tissue abnormality assessment. In previous research, we investigated an automated, localized, fusion-based approach for classifying squamous epithelium into Normal, CIN1, CIN2, and CIN3 grades of cervical intraepithelial neoplasia (CIN) based on image analysis of 61 digitized histology images. This paper introduces novel acellular and atypical cell concentration features computed from vertical segment partitions of the epithelium region within digitized histology images to quantize the relative increase in nuclei numbers as the CIN grade increases. Based on the CIN grade assessments from two expert pathologists, image-based epithelium classification is investigated with voting fusion of vertical segments using support vector machine and linear discriminant analysis approaches. Leave-one-out is used for the training and testing for CIN classification, achieving an exact grade labeling accuracy as high as 88.5%.

Diagnostic imaging of cervical intraepithelial neoplasia based on hematoxylin and eosin fluorescence.

BackgroundPathological classification of cervical intraepithelial neoplasia (CIN) is problematic as it relies on subjective criteria. We developed an imaging method that uses spectroscopy to assess the fluorescent intensity of cervical biopsies derived directly from hematoxylin and eosin (H&E) stained tissues.MethodsArchived H&E slides were identified containing normal cervical tissue, CIN I, and CIN III cases, from a Community Hospital and an Academic Medical Center. Cases were obtained by consensus review of at least 2 senior pathologists. Images from H&E slides were captured first with bright field illumination and then with fluorescent illumination. We used a Zeiss Axio Observer Z1 microscope and an AxioVision 4.6.3-AP1 camera at excitation wavelength of 450–490 nm with emission captured at 515–565 nm. The 32-bit grayscale fluorescence images were used for image analysis.ResultsWe reviewed 108 slides: 46 normal, 33 CIN I and 29 CIN III. Fluorescent intensity increased progressively in normal epithelial tissue as cells matured and advanced from the basal to superficial regions of the epithelium. In CIN I cases this change was less prominent as compared to normal. In high grade CIN lesions, there was a slight or no increase in fluorescent intensity. All groups examined were statistically different.ConclusionPresently, there are no markers to help in classification of CIN I-III lesions. Our imaging method may complement standard H&E pathological review and provide objective criteria to support the CIN diagnosis.

Relationship between the virus content of high risk HPV and cervical intraepithelial neoplasia

Objective To study the relationship between the virus content of high risk HPV and cervical intraepithelial neoplasia（CIN）.Methods 450 patients with cervical intraepithelial neoplasia （CIN） were selected as the observation group ,450 healthy women at the same time were the control group ,then the positive rate and content of the control group and observation group with different high risk HPV types were detected and compared ,then the detection results of observation group with different CIN classification were compared too ,and the relationship of the detection indexes between the CIN were analyzed by the Logistic analysis .Results The HPV DNA positive rate of observation group with different high risk types were 9.11%,6.67%,6.67%,6.67%and 6.00%,respectively,and they were all higher than those of control group （χ2 =6.871,6.240,6.240,6.240,5.871,all P〈0.05）,and the positive rate of patients with different CIN classification had obvious differences too ,the virus content and constitution of observation group were respectively （301.35 ±32.67） Copies/mL and 11.56%,10.22%,9.56%,and they were all obviously higher than those of control group （t=6.276,χ2 =7.132,6.915,5.878,all P〈0.05）,and the content of patients with different classification had obvious differences ,all P〈0.05,there were all significant differences ,and the item had close relationship to CIN by the Logistic analysis .Conclusion The high risk HPV virus content of patients with cervical intraepithelial neoplasia shows abnormal state ,and which have close relationship to the disease . Key words: Papillomavirus infections; Cervical intraepithelial neoplasia

Classification of cervical intraepithelial neoplasia based on histopathological image analysis and pattern recognition methods

Classification of cervical intraepithelial neoplasia based on histopathological image analysis and pattern recognition methods

Interobserver Agreement in the Reporting of Cervical Biopsy Specimens Obtained From Women Screened by Visual Inspection With Acetic Acid and Hybrid Capture 2

Visual inspection with acetic acid (VIA) and human papillomavirus detection have sensitivity higher than cytology but lower specificity. The high false-positive rate of either test poses a challenge to the colposcopists who obtain biopsies from the innocuous changes and to the pathologists who have to interpret large numbers of specimens that are either normal or have low-grade abnormalities. Interobserver variation in histopathologic interpretations of cervical punch biopsy specimens is high, specially for the lower-grade abnormalities. Use of the modified Bethesda system to report histology in place of the cervical intraepithelial neoplasia (CIN) system has the potential to reduce such variability as there are fewer categories. The present study aimed to assess the interobserver agreement to interpret cervical punch biopsies when both pathologists followed the modified Bethesda classification system and also when one pathologist followed the modified Bethesda classification system and the other followed the CIN classification system. Colposcopy-directed punch biopsies were obtained from VIA and/or Hybrid Capture 2-positive women. The Institute pathologist interpreted the slides using the CIN system. Blinded review was done by 2 external pathologists who independently interpreted cervical punch biopsies using the Bethesda system. The Institute pathologist's diagnoses based on CIN system were converted post hoc into categories belonging to the Bethesda system for comparison. The overall agreement was poor (κ=0.36). The lowest agreement was observed in the low-grade squamous intraepithelial lesion category (κ=0.23) and the highest in the squamous cell carcinoma category (κ=0.76). The agreement between the reviewers, both of whom used the Bethesda system, was substantial.