Cric searchable image database as a public platform for conventional pap smear cytology data

AbstractAmidst the current health crisis and social distancing, telemedicine has become an important part of mainstream of healthcare, and building and deploying computational tools to support screening more efficiently is an increasing medical priority. The early identification of cervical cancer precursor lesions by Pap smear test can identify candidates for subsequent treatment. However, one of the main challenges is the accuracy of the conventional method, often subject to high rates of false negative. While machine learning has been highlighted to reduce the limitations of the test, the absence of high-quality curated datasets has prevented strategies development to improve cervical cancer screening. The Center for Recognition and Inspection of Cells (CRIC) platform enables the creation of CRIC Cervix collection, currently with 400 images (1,376 × 1,020 pixels) curated from conventional Pap smears, with manual classification of 11,534 cells. This collection has the potential to advance current efforts in training and testing machine learning algorithms for the automation of tasks as part of the cytopathological analysis in the routine work of laboratories.

Download Full-text

Machine Learning Assisted Cervical Cancer Detection

Frontiers in Public Health ◽

10.3389/fpubh.2021.788376 ◽

2021 ◽

Vol 9 ◽

Author(s):

Mavra Mehmood ◽

Muhammad Rizwan ◽

Michal Gregus ml ◽

Sidra Abbas

Keyword(s):

Machine Learning ◽

Cervical Cancer ◽

Mean Squared Error ◽

Medical Center ◽

Pearson Correlation ◽

False Negative ◽

Hybrid Approach ◽

False Negative Rate ◽

Machine Learning Algorithms ◽

Screening Programs

Cervical malignant growth is the fourth most typical reason for disease demise in women around the globe. Cervical cancer growth is related to human papillomavirus (HPV) contamination. Early screening made cervical cancer a preventable disease that results in minimizing the global burden of cervical cancer. In developing countries, women do not approach sufficient screening programs because of the costly procedures to undergo examination regularly, scarce awareness, and lack of access to the medical center. In this manner, the expectation of the individual patient's risk becomes very high. There are many risk factors relevant to malignant cervical formation. This paper proposes an approach named CervDetect that uses machine learning algorithms to evaluate the risk elements of malignant cervical formation. CervDetect uses Pearson correlation between input variables as well as with the output variable to pre-process the data. CervDetect uses the random forest (RF) feature selection technique to select significant features. Finally, CervDetect uses a hybrid approach by combining RF and shallow neural networks to detect Cervical Cancer. Results show that CervDetect accurately predicts cervical cancer, outperforms the state-of-the-art studies, and achieved an accuracy of 93.6%, mean squared error (MSE) error of 0.07111, false-positive rate (FPR) of 6.4%, and false-negative rate (FNR) of 100%.

Download Full-text

Point-of-care digital cytology with artificial intelligence for cervical cancer screening at a peripheral clinic in Kenya

10.1101/2020.08.12.20172346 ◽

2020 ◽

Author(s):

Oscar Holmstrom ◽

Nina Linder ◽

Harrison Kaingu ◽

Ngali Mbuuko ◽

Jumaa Mbete ◽

...

Keyword(s):

Cervical Cancer ◽

Pap Smear ◽

Point Of Care ◽

Screening Method ◽

Machine Learning Algorithms ◽

Learning System ◽

Pap Smears ◽

Low Grade ◽

High Grade ◽

Predictive Values

Cervical cancer is highly preventable but remains a common and deadly cancer in areas without screening programmes. Pap smear analysis is the most commonly used screening method but is labour-intensive, subjective and requires access to medical experts. We developed a diagnostic system in which microscopy samples are digitized at the point-of-care (POC) and analysed by a cloud-based deep-learning system (DLS) and evaluated the system for the detection of cervical cell atypia in Pap smears at a peripheral clinic in Kenya. A total of 740 conventional Pap smears were collected, digitized with a portable slide scanner and uploaded over mobile networks to a cloud server for training and validation of the system. In total, 16,133 manually-annotated image regions where used for training of the DLS. The DLS achieved a high average sensitivity (97.85%; 95% confidence interval (CI) 83.95-99.75%) and area under the curve (AUCs) (0.95) for the detection of cervical-cellular atypia, compared to the pathologist assessment of digital and physical slides. Specificity was higher for high-grade atypia (95.9%; 95% CI 94.9-97.6%) than for low-grade atypia (84.2%; 95% CI 79.9-87.9%). Negative predictive values were high (99.3-100%), and no samples classified as high grade by manual sample analysis had false-negative assessments by the DLS. The study shows that advanced digital microscopy diagnostics supported by machine learning algorithms is implementable in rural, resource-constrained areas, and can achieve a diagnostic accuracy close to the level of highly trained experts.

Download Full-text

Performance Analysis of Machine Learning Algorithms for Cervical Cancer Detection

International Journal of Healthcare Information Systems and Informatics ◽

10.4018/ijhisi.2020040101 ◽

2020 ◽

Vol 15 (2) ◽

pp. 1-21 ◽

Cited By ~ 1

Author(s):

Sanjay Kumar Singh ◽

Anjali Goyal

Keyword(s):

Machine Learning ◽

Cervical Cancer ◽

Pap Smear ◽

Learning Algorithm ◽

Early Stage ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Data Sets ◽

Hybrid Techniques ◽

Cpu Time

Cervical cancer is second most prevailing cancer in women all over the world and the Pap smear is one of the most popular techniques used to diagnosis cervical cancer at an early stage. Developing countries like India has to face the challenges in order to handle more cases day by day. In this article, various online and offline machine learning algorithms has been applied on benchmarked data sets to detect cervical cancer. This article also addresses the problem of segmentation with hybrid techniques and optimizes the number of features using extra tree classifiers. Accuracy, precision score, recall score, and F1 score are increasing in the proportion of data for training and attained up to 100% by some algorithms. Algorithm like logistic regression with L1 regularization has an accuracy of 100%, but it is too much costly in terms of CPU time in comparison to some of the algorithms which obtain 99% accuracy with less CPU time. The key finding in this article is the selection of the best machine learning algorithm with the highest accuracy. Cost effectiveness in terms of CPU time is also analysed.

Download Full-text

A Comparative Study of Different Machine Learning Algorithms for Disease Prediction

International Journal of Advanced Research in Computer Science and Software Engineering ◽

10.23956/ijarcsse/v7i7/0177 ◽

2017 ◽

Vol 7 (7) ◽

pp. 172

Author(s):

Anantvir Singh Romana

Keyword(s):

Machine Learning ◽

Subsequent Treatment ◽

Machine Learning Algorithms ◽

Machine Learning Techniques ◽

Support Vector ◽

Disease Prediction ◽

Classification Problems ◽

Learning Techniques ◽

Neural Network Classifiers ◽

Diagnostic Detection

Accurate diagnostic detection of the disease in a patient is critical and may alter the subsequent treatment and increase the chances of survival rate. Machine learning techniques have been instrumental in disease detection and are currently being used in various classification problems due to their accurate prediction performance. Various techniques may provide different desired accuracies and it is therefore imperative to use the most suitable method which provides the best desired results. This research seeks to provide comparative analysis of Support Vector Machine, Naïve bayes, J48 Decision Tree and neural network classifiers breast cancer and diabetes datsets.

Download Full-text

Comparison of Several Machine Learning Algorithms in the Diagnosis of Cervical Cancer

10.1145/3474198.3478165 ◽

2021 ◽

Author(s):

Canfei Luo ◽

Bingxiang Liu ◽

Jingwen Xia

Keyword(s):

Machine Learning ◽

Cervical Cancer ◽

Learning Algorithms ◽

Machine Learning Algorithms

Download Full-text

An Extensive Review on Machine Learning and Deep Learning Based Cervical Cancer Diagnosis and Classification Models

Journal of Computational and Theoretical Nanoscience ◽

10.1166/jctn.2020.9437 ◽

2020 ◽

Vol 17 (12) ◽

pp. 5438-5446

Author(s):

C. Suguna ◽

S. P. Balamurugan

Keyword(s):

Machine Learning ◽

Cervical Cancer ◽

Deep Learning ◽

Comparative Study ◽

Cancer Diagnosis ◽

Pap Smear ◽

Classification Models ◽

Extensive Review ◽

Diagnosis And Classification ◽

Automated Machine Learning

Cervical cancer is a commonly occurring deadliest disease among women, which needs earlier diagnosis to reduce the prevalence. Pap-smear is considered as a widely employed technique to screen and diagnose cervical cancer. Since classical manual screening techniques are inefficient in the identification of cervical cancer, several research works have been started to develop automated machine learning (ML) and deep learning (DL) tools for cervical cancer diagnosis. This paper surveys the recent works made on cervical cancer diagnosis and classification. The recently presently ML and DL models for cervical cancer diagnosis and classification has been reviewed in detail. Besides, segmentation techniques developed for cervical cancer diagnosis also surveyed. At the end of the survey, a brief comparative study has been carried out to identify the significance of the reviewed methods.

Download Full-text

Machine-Learning-Based External Plagiarism Detecting Methodology From Monolingual Documents

Feature Dimension Reduction for Content-Based Image Identification - Advances in Multimedia and Interactive Technologies ◽

10.4018/978-1-5225-5775-3.ch007 ◽

2018 ◽

pp. 122-139

Author(s):

Saugata Bose ◽

Ritambhra Korpal

Keyword(s):

Machine Learning ◽

Language Processing ◽

Confusion Matrix ◽

False Negative ◽

False Negative Rate ◽

Search Space ◽

Machine Learning Algorithms ◽

C4.5 Decision Tree ◽

N Gram ◽

Four Levels

In this chapter, an initiative is proposed where natural language processing (NLP) techniques and supervised machine learning algorithms have been combined to detect external plagiarism. The major emphasis is on to construct a framework to detect plagiarism from monolingual texts by implementing n-gram frequency comparison approach. The framework is based on 120 characteristics which have been extracted during pre-processing steps using simple NLP approach. Afterward, filter metrics has been applied to select most relevant features and supervised classification learning algorithm has been used later to classify the documents in four levels of plagiarism. Then, confusion matrix was built to estimate the false positives and false negatives. Finally, the authors have shown C4.5 decision tree-based classifier's suitability on calculating accuracy over naive Bayes. The framework achieved 89% accuracy with low false positive and false negative rate and it shows higher precision and recall value comparing to passage similarities method, sentence similarity method, and search space reduction method.

Download Full-text

“A Pap smear saved my life”: Personal experiences of cervical abnormalities shape attitudes to cervical screening renewal

Journal of Medical Screening ◽

10.1177/0969141319889648 ◽

2019 ◽

Vol 27 (4) ◽

pp. 223-226 ◽

Cited By ~ 1

Author(s):

Helena M Obermair ◽

Kirsten J McCaffery ◽

Rachael H Dodd

Keyword(s):

Cervical Cancer ◽

Pap Smear ◽

Screening Program ◽

Cervical Screening ◽

Personal History ◽

Pap Smears ◽

Increased Risk ◽

Women's Lives ◽

History Of ◽

Screening Intervals

Objective In 2017, the Australian National Cervical Screening Program changed from two-yearly Pap smears between ages 18 and 69, to five-yearly human papillomavirus screening between ages 25 and 74 (the “Renewal”). This study investigated attitudes towards the changes, among individuals previously affected by cervical abnormalities/cervical cancer, personally or through a friend/relative. Methods We conducted a thematic analysis of comments expressing personal history or a family/friend history of cervical abnormalities/cervical cancer as a reason for opposing changes to the cervical screening program. The comments were taken from a 20% random sample of 19,633 comments posted on the “Change.org” petition “Stop May 1st Changes to Pap Smears – Save Women's Lives” in February–March 2017. Results There were 831 (20.8%) commenters who reported that they were concerned about a change in screening due to: feelings of increased personal vulnerability to cervical cancer due to their own personal history of cervical abnormalities; comparison of extended screening intervals and later age of first screening to their own experiences; and a perception of increased personal risk due to family history. Conclusion Women previously affected by cervical abnormalities or cervical cancer, personally or through a friend/relative, expressed concern about changes to cervical screening due to perceived increased risk and feeling vulnerable due to personal history.

Download Full-text

Spectrum of cytological patterns in cervical PAP smears in a tertiary care center of Western region of Nepal

Nepal Journal of Medical Sciences ◽

10.3126/njms.v4i1.24118 ◽

2019 ◽

Vol 4 (1) ◽

pp. 2-8

Author(s):

Pragya Gautam Ghimire ◽

Durga BC Rawat ◽

Kavita Sinha ◽

Kamar Jahan ◽

Richa Shrestha

Keyword(s):

Cervical Cancer ◽

Epithelial Cell ◽

Pap Smear ◽

Statistical Significance ◽

Care Center ◽

Tertiary Care ◽

Pap Smears ◽

Low Grade ◽

Squamous Intraepithelial Lesion ◽

Intraepithelial Lesion

Introduction: Cervical cancer is a common health problem in Nepal. There is paucity of data regarding the spectrum of findings in cervical Pap in western Nepal. This study was aimed to study the cytological patterns in cervical Pap smears in patients in a tertiary hospital of Nepal. Methods: This is a prospective, cross sectional, hospital based study. Clinical features of patients who had presented with Pap smear was noted in a structured proforma. Pap smears were studied by a senior pathologist and reported based on revised Bethesda system (2014). Results: Most of the cases belonged to 31-40 years 399 (42.8%). Unsatisfactory/ inadequate sample was present in 133(14.05%) with obscuration due to inflammatory exudate being most common cause. Negative for intraepithelial lesion or malignancy rate was noted in 798 (85.54%) with 477(51.2%) being normal findings. Epithelial cell abnormalities were noted in 116 (14.5 %) smears. Low-grade squamous intraepithelial lesion constituted 321(34.5%), High grade squamous intraepithelial lesion 273(29.3 %) and Atypical squamous cells of undetermined significance 153(16.4%) of epithelial cell abnormalities. Squamous cell carcinoma was present in 9(1%) of all reviewed smears. There was no statistical significance between the age and abnormalities of Pap smear (p=0.9). Conclusions: Pap smear is pivotal in cervical cancer screening in developing countries. It also identifies various inflammatory, infective, benign and malignant pathologies at the earliest thereby decreasing the morbidity and mortality.

Download Full-text

Knowledge, Attitude, Practice and Barriers regarding cervical cancer and its screening using Pap smear, in rural women of Ba, Lautoka and Nadi, Fiji.

Pacific Journal of Reproductive Health ◽

10.18313/pjrh.2015.913 ◽

2015 ◽

Vol 1 (2) ◽

pp. 50 ◽

Cited By ~ 1

Author(s):

Swaran Naidu ◽

Gillian Heller ◽

George Qalomaiwasa ◽

Sheetal Naidu ◽

Rajat Gyaneshwar

Keyword(s):

Risk Factors ◽

Cervical Cancer ◽

Rural Women ◽

Pap Smear ◽

Age Groups ◽

Pap Test ◽

High Rate ◽

Pap Smears ◽

Screening Programs ◽

Lack Of Knowledge

Background: Fiji has a high rate of cervical cancer, which is the second most common cause of cancer deaths in women in the country. Less than 10% of women are screened for cervical cancer in Fiji.In this paper we report the result of a study on Knowledge, Attitude, Practice and Barriers (KAPB) to cervical cancer and its screening with Pap smears, conducted on 1505 rural women in Fiji.Objectives: To assess the knowledge, attitudes, practice and barriers to cervical cancer and it’s screening with Pap smears in rural women of Ba, Lautoka and Nadi, in Fiji.Methods: Structured questionnaires were administered to women presenting to a rural outreach Reproductive Health education and clinics, by trained health educators to ascertain their Knowledge, Attitudes, Practice and Barriers to cervical cancer and its screening with Pap smears.Results: Seventy two percent of rural women had no knowledge of cervical cancer and 80% had no knowledge of the risk factors of cervical cancer. Lack of knowledge was significantly different for age groups (p=0.006), education levels and employment status(p<0.001) and ethnicity (p=0.022). Those groups with lowest knowledge were teenagers (18 to 19 years); those with less education; and iTaukei respondents. Of the respondents who had at least some knowledge of the Pap smear, 75% had had a Pap test. Of those who had no knowledge of the Pap smear, only 45% had had the test (p<0.001). Of those who did not have a Pap smear the commonest barrier was lack of knowledge at 46.3% and fear of procedure was 29.4%.Conclusion: More education is required to acquaint women in rural Fiji about cervical cancer, its associated risk factors as well as the benefits of cervical cancer screening programs and other prevention strategies.

Download Full-text