scholarly journals Development of algorithms for automated detection of cervical pre-cancers with a low-cost, point-of-care, Pocket colposcope

2018 ◽  
Author(s):  
Mercy Nyamewaa Asiedu ◽  
Anish Simhal ◽  
Usamah Chaudhary ◽  
Jenna L. Mueller ◽  
Christopher T. Lam ◽  
...  
Keyword(s):  
Acetic Acid ◽  
Visual Inspection ◽  
Point Of Care ◽  
Low Cost ◽  
Intraepithelial Neoplasia ◽  
Support Vector ◽  
Machine Model ◽  
Data Set ◽  
Automatic Feature Extraction ◽  
Lugol’S Iodine

AbstractGoalIn this work, we propose methods for (1) automatic feature extraction and classification for acetic acid and Lugol’s iodine cervigrams and (2) methods for combining features/diagnosis of different contrasts in cervigrams for improved performance.MethodsWe developed algorithms to pre-process pathology-labeled cervigrams and to extract simple but powerful color and textural-based features. The features were used to train a support vector machine model to classify cervigrams based on corresponding pathology for visual inspection with acetic acid, visual inspection with Lugol’s iodine, and a combination of the two contrasts.ResultsThe proposed framework achieved a sensitivity, specificity, and accuracy of 81.3%, 78.6%, and 80.0%, respectively when used to distinguish cervical intraepithelial neoplasia (CIN+) relative to normal and benign tissues. This is superior to the average values achieved by three expert physicians on the same data set for discriminating normal/benign cases from CIN+ (77% sensitivity, 51% specificity, 63% accuracy).ConclusionThe results suggest that utilizing simple color- and textural-based features from visual inspection with acetic acid and visual inspection with Lugol’s iodine images may provide unbiased automation of cervigrams.SignificanceThis would enable automated, expert-level diagnosis of cervical pre-cancer at the point-of-care.

scholarly journals Visual Inspection with Acetic Acid (VIA) in cervical cancer screening in low resource settings

2014 ◽  
Vol 13 (4) ◽  
pp. 454-459
Author(s):  
Shaheen Shaheen ◽  
Rajyashri Sharma ◽  
Rashi Rashi
Keyword(s):  
Acetic Acid ◽  
Visual Inspection ◽  
Pap Smear ◽  
Screening Program ◽  
Low Cost ◽  
Medical Science ◽  
High Sensitivity ◽  
Intraepithelial Neoplasia ◽  
Screening Methods ◽  
Cervical Lesions

Objective: To evaluate the feasibility and validity of visual inspection of the cervix with acetic acid (VIA) for screening cervical intraepithelial neoplasia. Materials and Methods: In this study, 942 women recruited from gynecology outpatient clinic, were screened using the Papanicolaou (PAP) smear, and VIA. The sensitivity and specificity of both the screening methods were analyzed. Results: VIA was positive in 29.3%. The sensitivity of VIA (74.16%) was much higher than that of the Pap smear (47.83%). The specificity of VIA (50.00%) was lower than that of the Pap smear (74.16%), resulting in high false-positive rates for VIA. Conclusion: Visual inspection of the cervix with acetic acid is sensitive for ecto-cervical lesions. The advantage of the VIA method lies in its easy technique, low cost and high sensitivity which are important factors for determining the efficacy of any screening program in developing countries. DOI: http://dx.doi.org/10.3329/bjms.v13i4.15019 Bangladesh Journal of Medical Science Vol.13(4) 2014 p.454-459

scholarly journals Test characteristics of visual inspection with 4% acetic acid (VIA) and Lugol's iodine (VILI) in cervical cancer screening in Kerala, India

2003 ◽  
Vol 106 (3) ◽  
pp. 404-408 ◽  
Author(s):  
Rengaswamy Sankaranarayanan ◽  
Ramani Wesley ◽  
Somanathan Thara ◽  
Namrata Dhakad ◽  
Bharathykutty Chandralekha ◽  
...  
Keyword(s):  
Cervical Cancer ◽  
Acetic Acid ◽  
Cancer Screening ◽  
Cervical Cancer Screening ◽  
Visual Inspection ◽  
Lugol’S Iodine ◽  
Test Characteristics

scholarly journals Comparative evaluation of test characteristics of acetic acid, lugol’s iodine and toluidine blue stains in cervical cancer screening

2017 ◽  
Vol 6 (11) ◽  
pp. 4857
Author(s):  
Ankita Kumari ◽  
Neha Singh ◽  
Shaila Mitra ◽  
Reena Srivastav
Keyword(s):  
Cervical Cancer ◽  
Acetic Acid ◽  
Toluidine Blue ◽  
Visual Inspection ◽  
Pap Smear ◽  
Invasive Cervical Cancer ◽  
Signs And Symptoms ◽  
Diagnostic Efficacy ◽  
Cross Sectional ◽  
Lugol’S Iodine

Background: Cervical cancer rank second in female cancer and India alone account for one fourth of the global cervical cancer burden. The study was aimed to evaluate the diagnostic efficacy of acetic acid (3%), lugol’s iodine and toluidine blue (1%) in detection of abnormal cervical lesions.Methods: This cross-sectional study was conducted in the Department of Obstetrics and Gynecology, BRD Medical College, Gorakhpur over a period of one year from July 2016 to June 2017. The study included 200 women in age group 20-60 years with signs and symptoms suspicious of abnormal cervical lesion. The cases were subjected to detailed history, clinical examination, Pap smear, Visual inspection test, colposcopy followed by cervical biopsy.Results: Out of total 200 patients, 114 patients had acetowhite area on VIA (visual inspection with acetic acid) test, 113 were VILI (visual inspection with lugol’s iodine) positive and 107 women stained positive with Toluidine blue but only 88 showed biopsy proven pre-invasive and invasive lesions. So, sensitivity of acetic acid, lugol’s iodine and Toluidine blue was 81.8%, 84.09% and 90.9% respectively. Similarly, the specificity of the three stains were 62.5%, 65.17% and 75.8% respectively.Conclusions: Toluidine blue (1%) has proved to be significantly more sensitive and specific stain as compared to acetic acid (3%) and lugol’s iodine (50% dilution) in diagnosing pre-invasive and invasive cervical cancer. Hence, it may aid as an important tool in screening and treating precancerous and cancerous lesions.

scholarly journals Preliminary verification for application of a support vector machine-based cloud detection method to GOSAT-2 CAI-2

2018 ◽  
Vol 11 (5) ◽  
pp. 2863-2878 ◽  
Author(s):  
Yu Oishi ◽  
Haruma Ishida ◽  
Takashi Y. Nakajima ◽  
Ryosuke Nakamura ◽  
Tsuneo Matsunaga
Keyword(s):  
Support Vector Machine ◽  
Land Cover ◽  
Greenhouse Gases ◽  
Visual Inspection ◽  
Fiscal Year ◽  
Tropical Rainforests ◽  
Support Vector ◽  
Accuracy Evaluation ◽  
Data Set ◽  
Land Cover Types

Abstract. The Greenhouse Gases Observing Satellite (GOSAT) was launched in 2009 to measure global atmospheric CO2 and CH4 concentrations. GOSAT is equipped with two sensors: the Thermal And Near infrared Sensor for carbon Observations (TANSO)-Fourier transform spectrometer (FTS) and TANSO-Cloud and Aerosol Imager (CAI). The presence of clouds in the instantaneous field of view of the FTS leads to incorrect estimates of the concentrations. Thus, the FTS data suspected to have cloud contamination must be identified by a CAI cloud discrimination algorithm and rejected. Conversely, overestimating clouds reduces the amount of FTS data that can be used to estimate greenhouse gas concentrations. This is a serious problem in tropical rainforest regions, such as the Amazon, where the amount of useable FTS data is small because of cloud cover. Preparations are continuing for the launch of the GOSAT-2 in fiscal year 2018. To improve the accuracy of the estimates of greenhouse gases concentrations, we need to refine the existing CAI cloud discrimination algorithm: Cloud and Aerosol Unbiased Decision Intellectual Algorithm (CLAUDIA1). A new cloud discrimination algorithm using a support vector machine (CLAUDIA3) was developed and presented in another paper. Although the use of visual inspection of clouds as a standard for judging is not practical for screening a full satellite data set, it has the advantage of allowing for locally optimized thresholds, while CLAUDIA1 and -3 use common global thresholds. Thus, the accuracy of visual inspection is better than that of these algorithms in most regions, with the exception of snow- and ice-covered surfaces, where there is not enough spectral contrast to identify cloud. In other words, visual inspection results can be used as truth data for accuracy evaluation of CLAUDIA1 and -3. For this reason visual inspection can be used for the truth metric for the cloud discrimination verification exercise. In this study, we compared CLAUDIA1–CAI and CLAUDIA3–CAI for various land cover types, and evaluated the accuracy of CLAUDIA3–CAI by comparing both CLAUDIA1–CAI and CLAUDIA3–CAI with visual inspection (400  ×  400 pixels) of the same CAI images in tropical rainforests. Comparative results between CLAUDIA1–CAI and CLAUDIA3–CAI for various land cover types indicated that CLAUDIA3–CAI had a tendency to identify bright surface and optically thin clouds. However, CLAUDIA3–CAI had a tendency to misjudge the edges of clouds compared with CLAUDIA1–CAI. The accuracy of CLAUDIA3–CAI was approximately 89.5 % in tropical rainforests, which is greater than that of CLAUDIA1–CAI (85.9 %) for the test cases presented here.

scholarly journals Visual inspection of cervix with acetic acid as a feasible screening test for cervical neoplasia among women attending at OPD in Rajshahi Medical College Hospital

KYAMC Journal ◽  
2018 ◽  
Vol 9 (2) ◽  
pp. 56-60
Author(s):  
Nahid Yusuf ◽  
Md Ahmed Ali ◽  
Nazmun Nahar ◽  
Shipra Chaudhury ◽  
Md Zillur Rahman
Keyword(s):  
Acetic Acid ◽  
Predictive Value ◽  
Urban Areas ◽  
Visual Inspection ◽  
Pap Smear ◽  
Low Cost ◽  
Low Grade ◽  
College Hospital ◽  
Health Care Centre ◽  
Simple Method

Background: Visual inspection of cervix after application of 3-5% acetic acid (VIA) is a potential alternative to Pap smear cytology for screening of cervical cancer in resource poor settings.Objectives: This study was to evaluate the performance of visual inspection based screening approach in the detection of precancerous and early cancerous lesions of the cervix.Materials & Methods: VIA was carried out in 540 eligible women attending Gynae OPD. Detection of well-defined, opaque, acetowhite lesion close to squamocolumnar junction or in transitional zone of the cervix constituted positive VIA. All screened women evaluated by colposcopy and biopsy were taken from colposcopically suspected areas. The final diagnosis was based on histology.Results: Out of 540 patients, 328 were VIA negative and 212 were VIA positive. Colposcopy showed normal results in 340 cases, low grade CIN in 138 cases, high grade CIN in 44 cases and cancer in 18 cases. There were biopsy proven chronic cervicitis and metaplastic changes in 423 cases, CIN I in 66 cases, CIN II in 25 cases, CIN III / carcinoma-in-situ in 5 cases. The sensitivity of VIA was 74.36%, specificity 70.45%, positive predictive value 41.04%, & negative predictive value 90.85%.Conclusion: VIA can differentiate a normal cervix from a precancerous cervix with reasonable accuracy. As it is low cost and simple method, it can be set in any hospital or any health care centre of rural or urban areas of poor resource settings.KYAMC Journal Vol. 9, No.-2, July 2018, Page 56-60

Implementation of a community-based cervical cancer screening program using visual inspection with acetic acid and Lugol’s iodine in Kutch District, India.

2012 ◽  
Vol 30 (15_suppl) ◽  
pp. e12009-e12009
Author(s):  
Surbhi Grover ◽  
Melody Ju ◽  
Lilie L. Lin ◽  
Shobha Krishnan
Keyword(s):  
Cervical Cancer ◽  
Acetic Acid ◽  
Cancer Screening ◽  
Cervical Cancer Screening ◽  
Visual Inspection ◽  
Screening Program ◽  
Cancer Center ◽  
Community Based ◽  
Screening Programs ◽  
Lugol’S Iodine

e12009 Background: Visual inspection with acetic acid and Lugol’s iodine (VIA/VILI) is increasingly reframed as a bridge modality through which low resource countries can provide cervical cancer screening while waiting for the more effective HPV DNA tests to become affordable. Often the screening programs are organized by government bodies that lack the trust of the local communities and hence such programs suffer from poor participation. Here we aim to describe a locally-sustained VIA/VILI screening program in rural Kutch district in India directed by Kutch Mahlia Vikas Sangathan (KMVS), a local NGO committed to women empowerment. Methods: All capacity-building measures (funding, training, materials, and healthcare workers) were rooted in the local community. Heath workers were sent to Tata Memorial Cancer Center in Mumbai for training. NGO members held information sessions prior the screening camps educating women about the significance of screening. A three-visit screening model using VIA/VILI was implemented. At first visit, all women were consented and screened. VIA/VILI positive women returned for a second visit for biospy. Biopsy positive women then returned for a third visit to arrange for treatment. All the screening camps were conducted in community buildings such as schools with the collaboration of the village leaders. Results: Screening camps were set up in 17 villages in 2010-2011, screening a total of 832 married women upto the age of 50. There were 0 cervical intraepithelial neoplasia (CIN) positive lesions or invasive cancers found. None of the women were lost to follow-up. Conclusions: It is feasible to develop a community level screening program and to provide cancer prevention needs from within a community. Future directions include further evaluation of downstream protocols after VIA/VILI tests, increasing health worker diagnostic and treatment capacity, and determining positive recruitment factors in women attending screening camps. The KMVS screening program has been well-received and has been approached by several other NGO’s and training centers seeking to build similar community-based cervical cancer screening programs.

scholarly journals Distributed collaborative prediction: Results of the machine learning contest

2017 ◽  
Vol 36 (3) ◽  
pp. 267-269 ◽  
Author(s):  
Matt Hall ◽  
Brendon Hall
Keyword(s):  
Machine Learning ◽  
Leading Edge ◽  
Support Vector ◽  
Small Data ◽  
Machine Model ◽  
Data Set ◽  
Facies Classification ◽  
Machine Learning Model ◽  
Wireline Logs ◽  
Naive Approach

The Geophysical Tutorial in the October issue of The Leading Edge was the first we've done on the topic of machine learning. Brendon Hall's article ( Hall, 2016 ) showed readers how to take a small data set — wireline logs and geologic facies data from nine wells in the Hugoton natural gas and helium field of southwest Kansas ( Dubois et al., 2007 ) — and predict the facies in two wells for which the facies data were not available. The article demonstrated with 25 lines of code how to explore the data set, then create, train and test a machine learning model for facies classification, and finally visualize the results. The workflow took a deliberately naive approach using a support vector machine model. It achieved a sort of baseline accuracy rate — a first-order prediction, if you will — of 0.42. That might sound low, but it's not untypical for a naive approach to this kind of problem. For comparison, random draws from the facies distribution score 0.16, which is therefore the true baseline.

Sign in / Sign up

Export Citation Format

Share Document