Diagnosis Of Cervical Precancerous Lesions Research Articles

Application of Three-dimensional Coding Network in Screening and Diagnosis of Cervical Precancerous Lesions

Globally, the incidence of cervical cancer ranks fourth among female malignant tumors, seriously threatening the physical and mental health of women. Early detection and early treatment can greatly reduce the mortality of cervical cancer "cytology /HPV test, colposcopy and cervical biopsy" is the main method for clinical diagnosis of cervical cancer. The progress of medical technology has significantly improved the early diagnosis of cervical cancer, but due to various factors, there are still many cases of missed diagnosis and misdiagnosis. In recent years, artificial intelligence has developed rapidly in the medical field, and has also shown good applicability in the screening and diagnosis of cervical cancer. In this paper, we design an mcs-SEM structure that contains both channels and space compression excitation modules, which can retain comprehensive spatial information at a low computational cost. Then, the structure is embedded in a three-dimensional coding network to realize the combination of two-dimensional convolutional neural network and three-dimensional spatial information, so as to predict the DVH in the complex distribution scenario of multi-endangered organs with higher accuracy.

Оптико-электронная технология: достаточная альтернатива или необходимая помощь в скрининге рака шейки матки?

Aim. To review the advantages and disadvantages of using an optoelectronic cervical screening method to detect cervical intraepithelial neoplasia and cervical cancer. Key points. At the present stage, the use of optical-electronic scanning is extremely important for the best diagnosis of cervical precancerous lesions. It can help to reduce the incidence of cervical cancer and will benefit the health of women. Conclusion. The optoelectronic technology provides sensitivity comparable to that of liquid cytologic examination of cervical micro specimens and can be used both as a primary screening method and for selection of HPV-positive patients for further diagnostic and therapeutic measures. Keywords: cervical cancer, human papillomavirus, cervical intraepithelial neoplasia, optoelectronic screening method.

Microendoscopy in vivo for the pathological diagnosis of cervical precancerous lesions and early cervical cancer

BackgroundCervical cancer is an important public health problem. Conventional colposcopy is inefficient in the diagnosis of cervical lesions and massive biopsies result in trauma. There is an urgent need for a new clinical strategy to triage women with abnormal cervical screening results immediately and effectively. In this study, the high-resolution microendoscopy combined with methylene blue cell staining technology was used to perform real-time in vivo imaging of the cervix for the first time.MethodsA total of 41 patients were enrolled in the study. All patients underwent routine colposcopy and cervical biopsy, and high-resolution images of methylene blue-stained cervical lesions were obtained in vivo using microendoscopy. The cell morphological features of benign and neoplastic cervical lesions stained with methylene blue under microendoscopy were analyzed and summarized. The microendoscopy and histopathology findings of the high-grade squamous intraepithelial lesion (HSIL) and more severe lesions were compared.ResultsThe overall consistency of microendoscopy diagnosis with pathological diagnosis was 95.12% (39/41). Diagnostic cell morphological features of cervicitis, low-grade squamous intraepithelial lesion (LSIL), HSIL, adenocarcinoma in situ, and invasive cancer were clearly demonstrated in methylene blue stained microendoscopic images. In HSIL and more severe lesions, microendoscopic methylene blue cell staining technology can show the microscopic diagnostic features consistent with histopathology.ConclusionsThis study was an initial exercise in the application of the microendoscopy imaging system combined with methylene blue cell staining technology to cervical precancerous lesions and cervical cancer screening. The results provided the basis for a novel clinical strategy for triage of women with abnormal cervical screening results using in vivo non-invasive optical diagnosis technology.

Accuracy of visual inspection methods for the diagnosis of cervical precancerous lesions

Objective: To access the accuracy of visual inspection methods for diagnosing cervical dysplasia. Methods: This cross-sectional study was carried out between 1st December 2016 and 30th April 2017. All cases positive to Visual Inspections with Acetic acid (VIA) or with Lugol’s Iodine (VILI) as well as cases of macroscopic abnormal cervices, irrespective of the results of visual inspection, had a colposcopy-directed biopsy. Results: A total of 109 women out of 1127 screened for cervical dysplasia had both visual inspection and biopsy done. The Sensitivity, Specificity, Positive predictive and Negative predictive values were 44.6%, 52.2%, 75% and 22.6% for VIA and 90.5%, 13.0%, 77.0% and 30% for VILI respectively. Conclusion: In our setting, the sensitivity of VILI in diagnosing cervical dysplasia is higher than that of VIA. Therefore, to reduce the rate of undiagnosed cervical dysplasia that might evolve to cancer, VILI should always be used in combination with VIA.

Construction of a diagnostic classifier for cervical intraepithelial neoplasia and cervical cancer based on XGBoost feature selection and random forest model.

The pathological phenotype of early-stage cervical cancer (CC) is similar to that of cervical intraepithelial neoplasia (CIN), which provides a challenge for the diagnosis of cervical precancerous lesions. Meanwhile, the existing diagnostic methods have certain subjectivity and limitations, resulting in the possibility of misdiagnosis or missed diagnosis. Hence, some methods are needed to assist diagnosis of CC and CIN. Based on the data of CIN and CC in gene expression omnibus (GEO) dataset, the eXtreme Gradient Boosting (XGBoost) algorithm was used to screen the feature genes between CIN and CC for constructing the classifier. Incremental feature selection (IFS) curve was also used for screening. The classifier was validated for reliability using principal component analysis (PCA) dimensionality reduction analysis and heat map analysis of gene expression. Then, differentially expressed genes of CIN and CC were intersected with the classifier genes. Genes in the intersection were used as seeds for protein-protein interaction network construction and restart random walk analysis. And the genes with the top 50 affinity coefficients were selected for gene ontology (GO) and kyoto encyclopedia of genes and genome (KEGG) enrichment analyses to observe the biological functions with differences between CIN and CC. The peripheral blood genes of CIN and CC were analyzed, and seven genes were screened. Using this gene for classifier construction, IFS curve screening revealed that the three-feature gene classifier constructed according to the random forest model had the best effect. The results of PCA dimensionality reduction analysis and gene expression heat map analysis showed that the three-gene classifier could effectively distinguish CIN from CC. A three-gene diagnostic classifier can effectively distinguish CIN patients from CC patients and provide a reference for the clinical diagnosis of early CC.

Cervical lesion image enhancement based on conditional entropy generative adversarial network framework.

Early screening and diagnosis of cervical precancerous lesions are very important to prevent cervical cancer. High-quality colposcopy images will help doctors make faster and more accurate diagnoses. To tackle the problem of low image quality caused by complex interference during colposcopy operation, this paper proposed a conditional entropy generative adversarial networks framework for image enhancement. A decomposition network based on Retinex theory is constructed to obtain the reflection images of the low-quality images, then the conditional generative adversarial network is used as the enhancement network. The low-quality images and the decomposed reflection images are both input the enhancement network for training, and the conditional entropy distance is used as a part of the loss of the conditional generative adversarial network to alleviate the over-fitting problem during the training process. The test results show that compared with published methods, the proposed method of this paper can significantly improve the image quality, and can enhance the colposcopy image while retaining image details.

Accuracy of Visual Inspection Methods for the Diagnosis of Cervical Precancerous Lesions

Accuracy of Visual Inspection Methods for the Diagnosis of Cervical Precancerous Lesions

A Polarization-Imaging-Based Machine Learning Framework for Quantitative Pathological Diagnosis of Cervical Precancerous Lesions.

Polarization images encode high resolution microstructural information even at low resolution. We propose a framework combining polarization imaging and traditional microscopy imaging, constructing a dual-modality machine learning framework that is not only accurate but also generalizable and interpretable. We demonstrate the viability of our proposed framework using the cervical intraepithelial neoplasia grading task, providing a polarimetry feature parameter to quantitatively characterize microstructural variations with lesion progression in hematoxylin-eosin-stained pathological sections of cervical precancerous tissues. By taking advantages of polarization imaging techniques and machine learning methods, the model enables interpretable and quantitative diagnosis of cervical precancerous lesion cases with improved sensitivity and accuracy in a low-resolution and wide-field system. The proposed framework applies routine image-analysis technology to identify the macro-structure and segment the target region in H&E-stained pathological images, and then employs emerging polarization method to extract the micro-structure information of the target region, which intends to expand the boundary of the current image-heavy digital pathology, bringing new possibilities for quantitative medical diagnosis.

Preliminary Study on the Expression of Testin, p16 and Ki-67 in the Cervical Intraepithelial Neoplasia.

Cervical cancer is one of the most common malignant cancers in women worldwide. The 5-year survival rate is 65%; nevertheless, it depends on race, age, and clinical stage. In the oncogenesis of cervical cancer, persistent HPV infection plays a pivotal role. It disrupts the expression of key proteins as Ki-67, p16, involved in regulating the cell cycle. This study aimed to identify the potential role of testin in the diagnosis of cervical precancerous lesions (CIN). The study was performed on selected archival paraffin-embedded specimens of CIN1 (31), CIN2 (75), and CIN3 (123). Moderate positive correlation was observed between testin and Ki-67 as well as testin and p16 expression in all dysplastic lesions (r = 0.4209, r = 0.5681; p < 0.0001 for both). Statistical analysis showed stronger expression of the testin in dysplastic lesions vs. control group (p < 0.0001); moreover, expression was significantly higher in HSIL than LSIL group (p < 0.0024). In addition, a significantly stronger expression of testin was observed in CIN3 vs. CIN1 and CIN3 vs. CIN2. In our study, expression of Ki-67, p16, and testin increased gradually as the lesion progressed from LSIL to HSIL. The three markers complemented each other effectively, which may improve test sensitivity and specificity when used jointly.

Multi-state colposcopy image fusion for cervical precancerous lesion diagnosis using BF-CNN

Colposcopy is one of the most commonly used procedures to screen for cervical lesions in early precancerous stages, allowing effective preventive treatments for cervical cancer. Deep learning based algorithms have been proven promising for analyzing colposcopy images (i.e., cervicograms) to identify cervical precancerous lesions. However, most existing methods only use the single-state images applied with acetic acid solution (i.e., acetic acid cervicograms) as their input data, while missing the additional information provided by colposcopy images applied with Lugol's iodine solution (i.e., Lugol's iodine cervicograms). Since both acetic acid and Lugol's iodine cervicograms are available in clinic, health providers would select suspected lesion regions for further biopsy by visually inspecting both types of cervicograms. Therefore, it is essential to take these two-state images as inputs to extract features because these two types of cervicograms provide complementary information. In this work, we propose a bilinear fuse convolutional neural network (BF-CNN) that implements a feature selection module based on attention mechanisms and utilizes the factorized bilinear pooling technique to effectively fuse two-state image features for automatic diagnosis of cervical precancerous lesions. We applied BF-CNN and alternative algorithms to the real clinic cervicogram dataset consisted of 1400 patients, where both types of cervicograms were available per patient. As a result, BF-CNN obtained similar sensitivity 74.6% as well as the highest accuracy 85.5%, specificity 95.7%, and AUC 0.909, compared with known multi-modal algorithms and our improved algorithm only using one type of cervicograms. BF-CNN is expected to provide a useful tool to help physician make more precise clinic diagnosis.

Raman spectroscopic study of cervical precancerous lesions and cervical cancer

Early detection of cervical lesions, accurate diagnosis of cervical lesions, and timely and effective therapy can effectively avoid the occurrence of cervical cancer or improve the survival rate of patients. In this paper, the spectra of tissue sections of cervical inflammation (n = 60), CIN (cervical intraepithelial neoplasia) I (n = 30), CIN II (n = 30), CIN III (n = 30), cervical squamous cell carcinoma (n = 30), and cervical adenocarcinoma (n = 30) were collected by a confocal Raman micro-spectrometer (LabRAM HR Evolution, Horiba France SAS, Villeneuve d’Ascq, France). The Raman spectra of six kinds of cervical tissues were analyzed, the dominant Raman peaks of different kinds of tissues were summarized, and the differences in chemical composition between the six tissue samples were compared. An independent sample t test (p ≤ 0.05) was used to analyze the difference of average relative intensity of Raman spectra of six types of cervical tissues. The difference of relative intensity of Raman spectra of six kinds of tissues can reflect the difference of biochemical components in six kinds of tissues and the characteristic of biochemical components in different kinds of tissues. The classification models of cervical inflammation, CIN I, CIN II, CIN III, cervical squamous cell carcinoma, and cervical adenocarcinoma were established by using a support vector machine (SVM) algorithm. Six types of cervical tissues were classified and identified with an overall diagnostic accuracy of 85.7%. This study laid a foundation for the application of Raman spectroscopy in the clinical diagnosis of cervical precancerous lesions and cervical cancer.

Diagnosis of cervical precancerous lesions based on multimodal feature changes

To realize the automatic diagnosis of cervical intraepithelial neoplasia (CIN) cases by preacetic acid test and postacetic acid test colposcopy images, this paper proposes a method of cervical precancerous lesion diagnosis based on multimodal feature changes. First, the preacetic acid test and postacetic acid test colposcopy images were registered based on cross-correlation and projection transformation, and then the cervical region was extracted by the k-means clustering algorithm. Finally, a deep learning network was used to extract features and classify the preacetic acid test and postacetic acid test cervical images after registration. Finally, the proposed method achieves a classification accuracy of 86.3%, a sensitivity of 84.1%, and a specificity of 89.8% in 60 test cases. Experimental results show that this method can make better use of the multimodal features of colposcopy images and has lower requirements for medical staff in the process of data acquisition. It has certain clinical significance in cervical cancer precancerous lesion screening systems.

Triple Up-Sampling Segmentation Network With Distribution Consistency Loss for Pathological Diagnosis of Cervical Precancerous Lesions.

Cervical cancer, as one of the most frequently diagnosed cancers in women, is curable when detected early. However, automated algorithms for cervical pathology precancerous diagnosis are limited. In this paper, instead of popular patch-wise classification, an end-to-end patch-wise segmentation algorithm is proposed to focus on the spatial structure changes of pathological tissues. Specifically, a triple up-sampling segmentation network (TriUpSegNet) is constructed to aggregate spatial information. Second, a distribution consistency loss (DC-loss) is designed to constrain the model to fit the inter-class relationship of the cervix. Third, the Gauss-like weighted post-processing is employed to reduce patch stitching deviation and noise. The algorithm is evaluated on three challenging and public datasets: 1) MTCHI for cervical precancerous diagnosis, 2) DigestPath for colon cancer, and 3) PAIP for liver cancer. The Dice coefficient is 0.7413 on the MTCHI dataset, which is significantly higher than the published state-of-the-art results. Experiments on the public dataset MTCHI indicate the superiority of the proposed algorithm on cervical pathology precancerous diagnosis. In addition, the experiments on two other pathological datasets, i.e., DigestPath and PAIP, demonstrate the effectiveness and generalization ability of the TriUpSegNet and weighted post-processing on colon and liver cancers. The end-to-end TriUpSegNet with DC-loss and weighted post-processing leads to improved segmentation in pathology of various cancers.

Bioinformatics Analysis of Key Genes and Pathways of Cervical Cancer.

Background and ObjectiveGlobally, cervical cancer (CC) is the fourth most common cancer affecting women. Although effective screening reduces its incidence, it remains one of the most serious cancers threatening the health of women. Therefore, the purpose of this study is to find new genes that can be used as potential biomarkers for the prognosis of CC.Methods and ResultsAfter downloading three datasets such as GSE6791, GSE63678, and GSE63514 from the Gene Expression Omnibus (GEO), we combined the expression matrixes and analyzed them to obtain the differential expressed genes (DEGs). Next, using the STRING website, we performed the protein interaction network analysis. Subsequently, hub genes were screened using the R and Cytoscape software. Then, the expression difference and survival analyses of the hub genes were confirmed using GIPIA. Here, we established that the KNTC1 gene was correlated to the overall survival prognosis of CC. Besides, the expression of the KNTC1 gene in the GSE63514 dataset was significantly different from that of the normal cervix, cervical pre-cancerous lesions, and CC. Consequently, immunohistochemistry analysis showed that the results have a definite diagnostic value.ConclusionThe KNTC1 gene could be linked with the pathophysiology of CC and maybe one of the early diagnostic markers for the diagnosis of cervical pre-cancerous lesions.

Letter to the editor: the value of microendoscopy in the diagnosis of cervical precancerous lesions and cervical microinvasive carcinoma

Letter to the editor: the value of microendoscopy in the diagnosis of cervical precancerous lesions and cervical microinvasive carcinoma

The value of microendoscopy in the diagnosis of cervical precancerous lesions and cervical microinvasive carcinoma

Cervical cancer is still one of the main causes of death in females. Conventional diagnostic tools such as colposcopy are still unsatisfactory, so accurate diagnostic tools for cervical diseases are needed. Therefore, the purpose of this study was to perform a clinical study to evaluate the value of microendoscopic imaging systems in the diagnosis of cervical precancerous lesions and cervical microinvasive carcinoma (MIC). Totally 106 patients ranging in age from 23 to 67years were recruited. All patients had abnormal thin-layer cytology (TCT) results (≥ low-grade squamous intraepithelial lesions) and high-risk human papillomavirus (HPV) positivity. Each patient was first subjected to ordinary colposcopy, followed by microendoscopy and biopsy. All results of the colposcopy and microendoscopy images were compared to the histopathological diagnosis. Characteristics of pathological blood vessels were easily distinguished by microendoscopy compared with ordinary colposcopy. The diagnostic agreement rate of microendoscopy with the pathological diagnosis was higher (95.3%) than that of ordinary colposcopy (37.7%) (weighted kappa = 0.863, P < .01). When diagnosing HSIL and more advanced disease, the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy of the microendoscopic diagnosis were significantly higher than those of ordinary colposcopy (97.6 and 38.1%), (95.5 and 63.6%), (98.8 and 80.0%), (91.3 and 21.2%) and (97.7 and 43.4%), respectively. This study shows that microendoscopy has important value in the diagnosis of cervical lesions which can provide real-time diagnosis in vivo without staining, particularly for lesions that are not sensitive to acetic acid staining.

MDFI: Multi-CNN Decision Feature Integration for Diagnosis of Cervical Precancerous Lesions

Colposcopy is an essential medical examination that mainly through visual inspection for cervical epithelial tissue to preventing cervical cancer. However, screening by artificial vision has the problems of missed diagnosis, low efficiency, and diversity. This paper proposes a deep learning-based method using multi-CNN decision feature integration for classification and diagnosis of cervical lesions. The proposed method first uses the k-means algorithm to aggregate training data into specific classes in data preprocessing and then trained in cross-validation to improve the generalization ability of the model. Subsequently, two kinds of CNN are separately fine-tuned based on the transfer learning, and then XGBoost algorithm is used to integrate the different CNN decision results for optimizing the final prediction. Two integration ways for decision features (named inner-model integration and outer-model integration) are proposed to embody multi-feature integration from the data level and the model structural level. Simultaneously, two specific integration strategies (inner-to-outer and outer-to-inner) are designed for as the final output based on the combination of the two ways. Experimental results show that the K-means data preprocessing method can improve the training of neural networks, and the proposed multi-decision feature fusion strategy can better obtain the results of computer-aided diagnosis that meet the needs of clinical diagnosis.

The role of p16 / Ki-67 dual staining in HPV positive and negative women in the early diagnosis of cervical precancerous lesions: Cytology, colposcopy and conization protocol

The role of p16 / Ki-67 dual staining in HPV positive and negative women in the early diagnosis of cervical precancerous lesions: Cytology, colposcopy and conization protocol

Accurate segmentation of overlapping cells in cervical cytology with deep convolutional neural networks

Accurate cell segmentation is essential for computer-aided diagnosis of cervical precancerous lesions in cytology images. Automated segmentation poses a great challenge due to the presence of fuzzy and overlapping cells, noisy background, and poor cytoplasmic contrast. Deep learning diagnosis technology has showed its advantages in segmenting complex medical images. We present a new framework based on deep convolutional neural networks (DCNNs) to automatically segment overlapping cells in digital cytology. A double-window based cellular detection method is derived to correctly localize individual cells, in which TernausNet is adopted to classify the image pixels into nucleus, cytoplasm, or background. A modified DeepLab V2 model is applied to perform cytoplasm segmentation. To provide more training samples, a synthesis method is utilized to generate cell masses containing touching or overlapping cells. The presented method was tested on three independent data cohorts, including two public datasets. We achieved improved performance in terms of dice coefficient (DSC), false negative and false positive rates, with up to 15% improvement in DSC, compared with the state-of-the-art approaches. The results indicated that the DCNN based segmentation method could be useful in an image-based computerized analysis system for early detection of cervical cancer.

Pap smear accuracy for the diagnosis of cervical precancerous lesions.

This cross-sectional descriptive study, aimed at accessing the accuracy of Pap smear in diagnosing cervical precancerous lesions, was carried out between 3 January and 30 April 2017. All women screened for cervical dysplasia by means of Pap smear with biopsy done for confirmation were subsequently recruited. Data were analysed using SPSS 20.0. A total of 231 women were screened for cervical dysplasia using Pap smear with 75 biopsies performed. Cervical dysplasia was noticed in 54 cases. The sensitivity, specificity, positive predictive and negative predictive values of Pap smear were 55.5%, 75%, 88.2% and 33.3%, respectively. The sensitivity of Pap smear remains low. Therefore, biopsy should be done in cases of macroscopic cervical architectural changes irrespective of the result of the Pap smear. Moreover, to reduce the number of women with cervical precancerous lesions, the government should make available financial resources to set up HPV vaccination programmes rather than screening programmes.