Cargando…

Multicontrast Pocket Colposcopy Cervical Cancer Diagnostic Algorithm for Referral Populations

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...

Descripción completa

Detalles Bibliográficos
Autores principales: Skerrett, Erica, Miao, Zichen, Asiedu, Mercy N., Richards, Megan, Crouch, Brian, Sapiro, Guillermo, Qiu, Qiang, Ramanujam, Nirmala
Formato: Online Artículo Texto
Lenguaje:English
Publicado: AAAS 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10521679/
https://www.ncbi.nlm.nih.gov/pubmed/37850189
http://dx.doi.org/10.34133/2022/9823184
_version_ 1785110183361380352
author Skerrett, Erica
Miao, Zichen
Asiedu, Mercy N.
Richards, Megan
Crouch, Brian
Sapiro, Guillermo
Qiu, Qiang
Ramanujam, Nirmala
author_facet Skerrett, Erica
Miao, Zichen
Asiedu, Mercy N.
Richards, Megan
Crouch, Brian
Sapiro, Guillermo
Qiu, Qiang
Ramanujam, Nirmala
author_sort Skerrett, Erica
collection PubMed
description 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 ([Formula: see text]) 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.
format Online
Article
Text
id pubmed-10521679
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher AAAS
record_format MEDLINE/PubMed
spelling pubmed-105216792023-10-17 Multicontrast Pocket Colposcopy Cervical Cancer Diagnostic Algorithm for Referral Populations Skerrett, Erica Miao, Zichen Asiedu, Mercy N. Richards, Megan Crouch, Brian Sapiro, Guillermo Qiu, Qiang Ramanujam, Nirmala BME Front Research Article 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 ([Formula: see text]) 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. AAAS 2022-08-25 /pmc/articles/PMC10521679/ /pubmed/37850189 http://dx.doi.org/10.34133/2022/9823184 Text en Copyright © 2022 Erica Skerrett et al. https://creativecommons.org/licenses/by/4.0/Exclusive Licensee Suzhou Institute of Biomedical Engineering and Technology, CAS. Distributed under a Creative Commons Attribution License (CC BY 4.0). (https://creativecommons.org/licenses/by/4.0/)
spellingShingle Research Article
Skerrett, Erica
Miao, Zichen
Asiedu, Mercy N.
Richards, Megan
Crouch, Brian
Sapiro, Guillermo
Qiu, Qiang
Ramanujam, Nirmala
Multicontrast Pocket Colposcopy Cervical Cancer Diagnostic Algorithm for Referral Populations
title Multicontrast Pocket Colposcopy Cervical Cancer Diagnostic Algorithm for Referral Populations
title_full Multicontrast Pocket Colposcopy Cervical Cancer Diagnostic Algorithm for Referral Populations
title_fullStr Multicontrast Pocket Colposcopy Cervical Cancer Diagnostic Algorithm for Referral Populations
title_full_unstemmed Multicontrast Pocket Colposcopy Cervical Cancer Diagnostic Algorithm for Referral Populations
title_short Multicontrast Pocket Colposcopy Cervical Cancer Diagnostic Algorithm for Referral Populations
title_sort multicontrast pocket colposcopy cervical cancer diagnostic algorithm for referral populations
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10521679/
https://www.ncbi.nlm.nih.gov/pubmed/37850189
http://dx.doi.org/10.34133/2022/9823184
work_keys_str_mv AT skerretterica multicontrastpocketcolposcopycervicalcancerdiagnosticalgorithmforreferralpopulations
AT miaozichen multicontrastpocketcolposcopycervicalcancerdiagnosticalgorithmforreferralpopulations
AT asiedumercyn multicontrastpocketcolposcopycervicalcancerdiagnosticalgorithmforreferralpopulations
AT richardsmegan multicontrastpocketcolposcopycervicalcancerdiagnosticalgorithmforreferralpopulations
AT crouchbrian multicontrastpocketcolposcopycervicalcancerdiagnosticalgorithmforreferralpopulations
AT sapiroguillermo multicontrastpocketcolposcopycervicalcancerdiagnosticalgorithmforreferralpopulations
AT qiuqiang multicontrastpocketcolposcopycervicalcancerdiagnosticalgorithmforreferralpopulations
AT ramanujamnirmala multicontrastpocketcolposcopycervicalcancerdiagnosticalgorithmforreferralpopulations