Current guidelines for cervical cancer screening

A two-stream decision fusion network for cervical pap-smear image classification tasks

Deep learning, especially Convolution Neural Networks (CNNs), has demonstrated superior performance in image recognition and classification tasks. They make complex pattern recognition possible by extracting image features through layers of abstraction. However, despite the excellent performance of deep learning in general image classification, its limitations are becoming apparent in specific domains such as cervical cell medical image classification. This is because although the morphology of cervical cells varies between normal, diseased and cancerous, these differences are sometimes very small and difficult to capture. To solve this problem, we propose a two-stream feature fusion model comprising a manual feature branch, a deep feature branch, and a decision fusion module. Specifically, We process cervical cells through a modified DarkNet backbone network to extract deep features. In order to enhance the learning of deep features, we have devised scale convolution blocks to substitute the original convolution, termed Basic convolution blocks. The manual feature branch comprises a range of traditional features and is linked to a multilayer perceptron. Additionally, we design three decision feature channels trained from both manual and deep features to enhance the model performance in cervical cell classification. Our proposed model demonstrates superior performance when compared to state-of-the-art cervical cell classification models. We establish a 15-category 148762 cervical cytopathology image dataset (CCID). In addition, we additionally conducted experiments on the SIPaKMeD dataset. Numerous experiments show that our proposed model performs excellently compared to state-of-the-art classification models. The outcomes illustrate that our approach can significantly aid pathologists in accurately evaluating cervical smears.

Diagnosis of Cervical Cancer based on Ensemble Deep Learning Network using Colposcopy Images

Traditional screening of cervical cancer type classification majorly depends on the pathologist's experience, which also has less accuracy. Colposcopy is a critical component of cervical cancer prevention. In conjunction with precancer screening and treatment, colposcopy has played an essential role in lowering the incidence and mortality from cervical cancer over the last 50 years. However, due to the increase in workload, vision screening causes misdiagnosis and low diagnostic efficiency. Medical image processing using the convolutional neural network (CNN) model shows its superiority for the classification of cervical cancer type in the field of deep learning. This paper proposes two deep learning CNN architectures to detect cervical cancer using the colposcopy images; one is the VGG19 (TL) model, and the other is CYENET. In the CNN architecture, VGG19 is adopted as a transfer learning for the studies. A new model is developed and termed as the Colposcopy Ensemble Network (CYENET) to classify cervical cancers from colposcopy images automatically. The accuracy, specificity, and sensitivity are estimated for the developed model. The classification accuracy for VGG19 was 73.3%. Relatively satisfied results are obtained for VGG19 (TL). From the kappa score of the VGG19 model, we can interpret that it comes under the category of moderate classification. The experimental results show that the proposed CYENET exhibited high sensitivity, specificity, and kappa scores of 92.4%, 96.2%, and 88%, respectively. The classification accuracy of the CYENET model is improved as 92.3%, which is 19% higher than the VGG19 (TL) model.

A review of image analysis and machine learning techniques for automated cervical cancer screening from pap-smear images

BACKGROUND AND OBJECTIVE

Early diagnosis and classification of a cancer type can help facilitate the subsequent clinical management of the patient. Cervical cancer ranks as the fourth most prevalent cancer affecting women worldwide and its early detection provides the opportunity to help save life. To that end, automated diagnosis and classification of cervical cancer from pap-smear images has become a necessity as it enables accurate, reliable and timely analysis of the condition's progress. This paper presents an overview of the state of the art as articulated in prominent recent publications focusing on automated detection of cervical cancer from pap-smear images.

METHODS

The survey reviews publications on applications of image analysis and machine learning in automated diagnosis and classification of cervical cancer from pap-smear images spanning 15 years. The survey reviews 30 journal papers obtained electronically through four scientific databases (Google Scholar, Scopus, IEEE and Science Direct) searched using three sets of keywords: (1) segmentation, classification, cervical cancer; (2) medical imaging, machine learning, pap-smear; (3) automated system, classification, pap-smear.

RESULTS

Most of the existing algorithms facilitate an accuracy of nearly 93.78% on an open pap-smear data set, segmented using CHAMP digital image software. K-nearest-neighbors and support vector machines algorithms have been reported to be excellent classifiers for cervical images with accuracies of over 99.27% and 98.5% respectively when applied to a 2-class classification problem (normal or abnormal).

CONCLUSION

The reviewed papers indicate that there are still weaknesses in the available techniques that result in low accuracy of classification in some classes of cells. Moreover, most of the existing algorithms work either on single or on multiple cervical smear images. This accuracy can be increased by varying various parameters such as the features to be extracted, improvement in noise removal, using hybrid segmentation and classification techniques such of multi-level classifiers. Combining K-nearest-neighbors algorithm with other algorithm(s) such as support vector machines, pixel level classifications and including statistical shape models can also improve performance. Further, most of the developed classifiers are tested on accurately segmented images using commercially available software such as CHAMP software. There is thus a deficit of evidence that these algorithms will work in clinical settings found in developing countries (where 85% of cervical cancer incidences occur) that lack sufficient trained cytologists and the funds to buy the commercial segmentation software.

Application of the Carolina Framework for Cervical Cancer Prevention

OBJECTIVE

The Carolina Framework for Cervical Cancer Prevention describes 4 main causes of cervical cancer incidence: human papillomavirus (HPV) infection, lack of screening, screening errors, and not receiving follow-up care. We present 2 applications of the Carolina Framework in which we identify high-need counties in North Carolina and generate recommendations for improving prevention efforts.

METHODS

We created a cervical cancer prevention need index (CCPNI) that ranked counties on cervical cancer mortality, HPV vaccine initiation and completion, Pap smear screening, and provision of Pap tests to rarely- or never-screened women. In addition, we conducted in-depth interviews with 19 key informants from programs and agencies involved in cervical cancer prevention in North Carolina.

RESULTS

North Carolina's 100 counties varied widely on individual CCPNI components, including annual cervical cancer mortality (median 2.7/100,000 women; range 0.0-8.0), adolescent girls' HPV vaccine initiation (median 42%; range 15%-62%), and Pap testing in the previous 3 years among Medicaid-insured adult women (median 59%; range 40%-83%). Counties with the greatest prevention needs formed 2 distinct clusters in the northeast and south-central regions of the state. Interviews generated 9 recommendations to improve cervical cancer prevention in North Carolina, identifying applications to specific programs and policies in the state.

CONCLUSIONS

This study found striking geographic disparities in cervical cancer prevention need in North Carolina. Future prevention efforts in the state should prioritize high-need regions as well as recommended strategies and applications in existing programs. Other states can use the Carolina Framework to increase the impact of their cervical cancer prevention efforts.

Compliance with cervical cancer screening and human papillomavirus testing guidelines among insured young women

OBJECTIVE

In December 2009, the American Congress of Obstetricians and Gynecologists (ACOG) recommended that women under 21 years old should not receive cervical cancer screening (Papanicolaou tests) or human papillomavirus (HPV) tests. This study examined whether clinicians stopped administering Papanicolaou and HPV tests among women younger than 21 years of age after new ACOG guidelines were issued.

STUDY DESIGN

This study was a retrospective secondary data analysis of administrative claims data that included insurance enrollees from across the United States that examined the frequency of Papanicolaou tests and HPV tests among 178,898 nonimmunocompromised females 12-20 years old who had a paid claim for a well-woman visit in 2008, 2009, or 2010. Young women with well-woman examinations in each observed year were examined longitudinally to determine whether past diagnoses of cervical cell abnormalities accounted for Papanicolaou testing in 2010.

RESULTS

The proportion of women younger than 21 years old that received a Papanicolaou test as part of her well-woman exam dropped from 77% in 2008 and 2009 to 57% by December of 2010, whereas HPV testing remained stable across time. A diagnosis of cervical cell abnormalities in 2009 was associated with Papanicolaou testing in 2010. However, a previous Papanicolaou test was more strongly associated with a Papanicolaou test in 2010.

CONCLUSION

These data show that some physicians are adjusting their practices among young women according to ACOG guidelines, but Papanicolaou and HPV testing among insured women younger than 21 years of age still remains unnecessarily high.