Multicontrast Pocket Colposcopy Cervical Cancer Diagnostic Algorithm for Referral Populations
Authors:
Open Access
- 1 January 2022
- journal article
- research article
- Published by American Association for the Advancement of Science (AAAS) in BME Frontiers
- Vol. 2022
Abstract
Objective and Impact Statement . We use deep learning models to classify cervix images—collected with a low-cost, portable Pocket colposcope—with biopsy-confirmed high-grade precancer and cancer. We boost classification performance on a screened-positive population by using a class-balanced loss and incorporating green-light colposcopy image pairs, which come at no additional cost to the provider. Introduction . Because the majority of the 300,000 annual deaths due to cervical cancer occur in countries with low- or middle-Human Development Indices, an automated classification algorithm could overcome limitations caused by the low prevalence of trained professionals and diagnostic variability in provider visual interpretations. Methods . Our dataset consists of cervical images ( n = 1,760 ) from 880 patient visits. After optimizing the network architecture and incorporating a weighted loss function, we explore two methods of incorporating green light image pairs into the network to boost the classification performance and sensitivity of our model on a test set. Results . We achieve an area under the receiver-operator characteristic curve, sensitivity, and specificity of 0.87, 75%, and 88%, respectively. The addition of the class-balanced loss and green light cervical contrast to a Resnet-18 backbone results in a 2.5 times improvement in sensitivity. Conclusion . Our methodology, which has already been tested on a prescreened population, can boost classification performance and, in the future, be coupled with Pap smear or HPV triaging, thereby broadening access to early detection of precursor lesions before they advance to cancer.Keywords
Funding Information
- NGA
- Simons Foundation, USA
- ONR
- National Science Foundation
This publication has 34 references indexed in Scilit:
- Secondary Prevention of Cervical Cancer: ASCO Resource-Stratified Clinical Practice GuidelineJournal of Global Oncology, 2017
- Multi-feature based benchmark for cervical dysplasia classification evaluationPattern Recognition, 2017
- Deep Residual Learning for Image Recognition2016
- Rethinking the Inception Architecture for Computer Vision2016
- Accuracy of visual inspection with acetic acid and with Lugol's iodine for cervical cancer screening: Meta‐analysisJournal of Obstetrics and Gynaecology Research, 2015
- A review of life expectancy and infant mortality estimations for Australian Aboriginal peopleBMC Public Health, 2014
- HPV DNAtesting improvesCIN2+ risk stratification and detection ofCIN2+ in delayed triage ofASCUSandLSIL. A population‐based follow‐up study fromWesternNorwayCancer Medicine, 2013
- Cervical Cancer Screening and Prevention in Low-resource SettingsClinical Obstetrics and Gynecology, 2013
- Determinants of VIA (Visual Inspection of the Cervix After Acetic Acid Application) Positivity in Cervical Cancer Screening of Women in a Peri-Urban Area in Andhra Pradesh, IndiaCancer Epidemiology, Biomarkers & Prevention, 2010
- HPV Screening for Cervical Cancer in Rural IndiaNew England Journal of Medicine, 2009