An Observational Study of Deep Learning and Automated Evaluation of Cervical Images for Cancer Screening

Liming Hu, David Bell, Sameer Antani, Zhiyun Xue, Kai Yu, Matthew P. Horning, Noni Gachuhi, Benjamin Wilson, Mayoore S. Jaiswal, Brian Befano, L. Rodney Long, Rolando Herrero, Mark H. Einstein, Robert D. Burk, Maria Demarco, Julia C. Gage, Ana Cecilia Rodriguez, Nicolas Wentzensen, Mark Schiffman

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

BACKGROUND: Human papillomavirus vaccination and cervical screening are lacking in most lower resource settings, where approximately 80% of more than 500 000 cancer cases occur annually. Visual inspection of the cervix following acetic acid application is practical but not reproducible or accurate. The objective of this study was to develop a "deep learning"-based visual evaluation algorithm that automatically recognizes cervical precancer/cancer. METHODS: A population-based longitudinal cohort of 9406 women ages 18-94 years in Guanacaste, Costa Rica was followed for 7 years (1993-2000), incorporating multiple cervical screening methods and histopathologic confirmation of precancers. Tumor registry linkage identified cancers up to 18 years. Archived, digitized cervical images from screening, taken with a fixed-focus camera ("cervicography"), were used for training/validation of the deep learning-based algorithm. The resultant image prediction score (0-1) could be categorized to balance sensitivity and specificity for detection of precancer/cancer. All statistical tests were two-sided. RESULTS: Automated visual evaluation of enrollment cervigrams identified cumulative precancer/cancer cases with greater accuracy (area under the curve [AUC] = 0.91, 95% confidence interval [CI] = 0.89 to 0.93) than original cervigram interpretation (AUC = 0.69, 95% CI = 0.63 to 0.74; P < .001) or conventional cytology (AUC = 0.71, 95% CI = 0.65 to 0.77; P < .001). A single visual screening round restricted to women at the prime screening ages of 25-49 years could identify 127 (55.7%) of 228 precancers (cervical intraepithelial neoplasia 2/cervical intraepithelial neoplasia 3/adenocarcinoma in situ [AIS]) diagnosed cumulatively in the entire adult population (ages 18-94 years) while referring 11.0% for management. CONCLUSIONS: The results support consideration of automated visual evaluation of cervical images from contemporary digital cameras. If achieved, this might permit dissemination of effective point-of-care cervical screening.

Original languageEnglish (US)
Pages (from-to)923-932
Number of pages10
JournalJournal of the National Cancer Institute
Volume111
Issue number9
DOIs
StatePublished - Sep 1 2019

Fingerprint

Early Detection of Cancer
Uterine Cervical Neoplasms
Observational Studies
Learning
Area Under Curve
Cervical Intraepithelial Neoplasia
Confidence Intervals
Neoplasms
Point-of-Care Systems
Costa Rica
Cervix Uteri
Acetic Acid
Population
Cell Biology
Registries
Vaccination
Sensitivity and Specificity

ASJC Scopus subject areas

  • Oncology
  • Cancer Research

Cite this

An Observational Study of Deep Learning and Automated Evaluation of Cervical Images for Cancer Screening. / Hu, Liming; Bell, David; Antani, Sameer; Xue, Zhiyun; Yu, Kai; Horning, Matthew P.; Gachuhi, Noni; Wilson, Benjamin; Jaiswal, Mayoore S.; Befano, Brian; Long, L. Rodney; Herrero, Rolando; Einstein, Mark H.; Burk, Robert D.; Demarco, Maria; Gage, Julia C.; Rodriguez, Ana Cecilia; Wentzensen, Nicolas; Schiffman, Mark.

In: Journal of the National Cancer Institute, Vol. 111, No. 9, 01.09.2019, p. 923-932.

Research output: Contribution to journalArticle

Hu, L, Bell, D, Antani, S, Xue, Z, Yu, K, Horning, MP, Gachuhi, N, Wilson, B, Jaiswal, MS, Befano, B, Long, LR, Herrero, R, Einstein, MH, Burk, RD, Demarco, M, Gage, JC, Rodriguez, AC, Wentzensen, N & Schiffman, M 2019, 'An Observational Study of Deep Learning and Automated Evaluation of Cervical Images for Cancer Screening', Journal of the National Cancer Institute, vol. 111, no. 9, pp. 923-932. https://doi.org/10.1093/jnci/djy225
Hu, Liming ; Bell, David ; Antani, Sameer ; Xue, Zhiyun ; Yu, Kai ; Horning, Matthew P. ; Gachuhi, Noni ; Wilson, Benjamin ; Jaiswal, Mayoore S. ; Befano, Brian ; Long, L. Rodney ; Herrero, Rolando ; Einstein, Mark H. ; Burk, Robert D. ; Demarco, Maria ; Gage, Julia C. ; Rodriguez, Ana Cecilia ; Wentzensen, Nicolas ; Schiffman, Mark. / An Observational Study of Deep Learning and Automated Evaluation of Cervical Images for Cancer Screening. In: Journal of the National Cancer Institute. 2019 ; Vol. 111, No. 9. pp. 923-932.
@article{c7e73e101850412f9b7a72b8f5a7a98f,
title = "An Observational Study of Deep Learning and Automated Evaluation of Cervical Images for Cancer Screening",
abstract = "BACKGROUND: Human papillomavirus vaccination and cervical screening are lacking in most lower resource settings, where approximately 80{\%} of more than 500 000 cancer cases occur annually. Visual inspection of the cervix following acetic acid application is practical but not reproducible or accurate. The objective of this study was to develop a {"}deep learning{"}-based visual evaluation algorithm that automatically recognizes cervical precancer/cancer. METHODS: A population-based longitudinal cohort of 9406 women ages 18-94 years in Guanacaste, Costa Rica was followed for 7 years (1993-2000), incorporating multiple cervical screening methods and histopathologic confirmation of precancers. Tumor registry linkage identified cancers up to 18 years. Archived, digitized cervical images from screening, taken with a fixed-focus camera ({"}cervicography{"}), were used for training/validation of the deep learning-based algorithm. The resultant image prediction score (0-1) could be categorized to balance sensitivity and specificity for detection of precancer/cancer. All statistical tests were two-sided. RESULTS: Automated visual evaluation of enrollment cervigrams identified cumulative precancer/cancer cases with greater accuracy (area under the curve [AUC] = 0.91, 95{\%} confidence interval [CI] = 0.89 to 0.93) than original cervigram interpretation (AUC = 0.69, 95{\%} CI = 0.63 to 0.74; P < .001) or conventional cytology (AUC = 0.71, 95{\%} CI = 0.65 to 0.77; P < .001). A single visual screening round restricted to women at the prime screening ages of 25-49 years could identify 127 (55.7{\%}) of 228 precancers (cervical intraepithelial neoplasia 2/cervical intraepithelial neoplasia 3/adenocarcinoma in situ [AIS]) diagnosed cumulatively in the entire adult population (ages 18-94 years) while referring 11.0{\%} for management. CONCLUSIONS: The results support consideration of automated visual evaluation of cervical images from contemporary digital cameras. If achieved, this might permit dissemination of effective point-of-care cervical screening.",
author = "Liming Hu and David Bell and Sameer Antani and Zhiyun Xue and Kai Yu and Horning, {Matthew P.} and Noni Gachuhi and Benjamin Wilson and Jaiswal, {Mayoore S.} and Brian Befano and Long, {L. Rodney} and Rolando Herrero and Einstein, {Mark H.} and Burk, {Robert D.} and Maria Demarco and Gage, {Julia C.} and Rodriguez, {Ana Cecilia} and Nicolas Wentzensen and Mark Schiffman",
year = "2019",
month = "9",
day = "1",
doi = "10.1093/jnci/djy225",
language = "English (US)",
volume = "111",
pages = "923--932",
journal = "Journal of the National Cancer Institute",
issn = "0027-8874",
publisher = "Oxford University Press",
number = "9",

}

TY - JOUR

T1 - An Observational Study of Deep Learning and Automated Evaluation of Cervical Images for Cancer Screening

AU - Hu, Liming

AU - Bell, David

AU - Antani, Sameer

AU - Xue, Zhiyun

AU - Yu, Kai

AU - Horning, Matthew P.

AU - Gachuhi, Noni

AU - Wilson, Benjamin

AU - Jaiswal, Mayoore S.

AU - Befano, Brian

AU - Long, L. Rodney

AU - Herrero, Rolando

AU - Einstein, Mark H.

AU - Burk, Robert D.

AU - Demarco, Maria

AU - Gage, Julia C.

AU - Rodriguez, Ana Cecilia

AU - Wentzensen, Nicolas

AU - Schiffman, Mark

PY - 2019/9/1

Y1 - 2019/9/1

N2 - BACKGROUND: Human papillomavirus vaccination and cervical screening are lacking in most lower resource settings, where approximately 80% of more than 500 000 cancer cases occur annually. Visual inspection of the cervix following acetic acid application is practical but not reproducible or accurate. The objective of this study was to develop a "deep learning"-based visual evaluation algorithm that automatically recognizes cervical precancer/cancer. METHODS: A population-based longitudinal cohort of 9406 women ages 18-94 years in Guanacaste, Costa Rica was followed for 7 years (1993-2000), incorporating multiple cervical screening methods and histopathologic confirmation of precancers. Tumor registry linkage identified cancers up to 18 years. Archived, digitized cervical images from screening, taken with a fixed-focus camera ("cervicography"), were used for training/validation of the deep learning-based algorithm. The resultant image prediction score (0-1) could be categorized to balance sensitivity and specificity for detection of precancer/cancer. All statistical tests were two-sided. RESULTS: Automated visual evaluation of enrollment cervigrams identified cumulative precancer/cancer cases with greater accuracy (area under the curve [AUC] = 0.91, 95% confidence interval [CI] = 0.89 to 0.93) than original cervigram interpretation (AUC = 0.69, 95% CI = 0.63 to 0.74; P < .001) or conventional cytology (AUC = 0.71, 95% CI = 0.65 to 0.77; P < .001). A single visual screening round restricted to women at the prime screening ages of 25-49 years could identify 127 (55.7%) of 228 precancers (cervical intraepithelial neoplasia 2/cervical intraepithelial neoplasia 3/adenocarcinoma in situ [AIS]) diagnosed cumulatively in the entire adult population (ages 18-94 years) while referring 11.0% for management. CONCLUSIONS: The results support consideration of automated visual evaluation of cervical images from contemporary digital cameras. If achieved, this might permit dissemination of effective point-of-care cervical screening.

AB - BACKGROUND: Human papillomavirus vaccination and cervical screening are lacking in most lower resource settings, where approximately 80% of more than 500 000 cancer cases occur annually. Visual inspection of the cervix following acetic acid application is practical but not reproducible or accurate. The objective of this study was to develop a "deep learning"-based visual evaluation algorithm that automatically recognizes cervical precancer/cancer. METHODS: A population-based longitudinal cohort of 9406 women ages 18-94 years in Guanacaste, Costa Rica was followed for 7 years (1993-2000), incorporating multiple cervical screening methods and histopathologic confirmation of precancers. Tumor registry linkage identified cancers up to 18 years. Archived, digitized cervical images from screening, taken with a fixed-focus camera ("cervicography"), were used for training/validation of the deep learning-based algorithm. The resultant image prediction score (0-1) could be categorized to balance sensitivity and specificity for detection of precancer/cancer. All statistical tests were two-sided. RESULTS: Automated visual evaluation of enrollment cervigrams identified cumulative precancer/cancer cases with greater accuracy (area under the curve [AUC] = 0.91, 95% confidence interval [CI] = 0.89 to 0.93) than original cervigram interpretation (AUC = 0.69, 95% CI = 0.63 to 0.74; P < .001) or conventional cytology (AUC = 0.71, 95% CI = 0.65 to 0.77; P < .001). A single visual screening round restricted to women at the prime screening ages of 25-49 years could identify 127 (55.7%) of 228 precancers (cervical intraepithelial neoplasia 2/cervical intraepithelial neoplasia 3/adenocarcinoma in situ [AIS]) diagnosed cumulatively in the entire adult population (ages 18-94 years) while referring 11.0% for management. CONCLUSIONS: The results support consideration of automated visual evaluation of cervical images from contemporary digital cameras. If achieved, this might permit dissemination of effective point-of-care cervical screening.

UR - http://www.scopus.com/inward/record.url?scp=85063356201&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063356201&partnerID=8YFLogxK

U2 - 10.1093/jnci/djy225

DO - 10.1093/jnci/djy225

M3 - Article

C2 - 30629194

AN - SCOPUS:85063356201

VL - 111

SP - 923

EP - 932

JO - Journal of the National Cancer Institute

JF - Journal of the National Cancer Institute

SN - 0027-8874

IS - 9

ER -