Literature DB >> 33349257

Development and validation of an artificial intelligence system for grading colposcopic impressions and guiding biopsies.

Peng Xue1,2, Chao Tang3, Qing Li4, Yuexiang Li5, Yu Shen6, Yuqian Zhao7, Jiawei Chen5, Jianrong Wu8, Longyu Li9, Wei Wang10, Yucong Li11, Xiaoli Cui12, Shaokai Zhang13, Wenhua Zhang2, Xun Zhang14, Kai Ma5, Yefeng Zheng5, Tianyi Qian8, Man Tat Alexander Ng8, Zhihua Liu15, Youlin Qiao1,2, Yu Jiang16, Fanghui Zhao17.   

Abstract

BACKGROUND: Colposcopy diagnosis and directed biopsy are the key components in cervical cancer screening programs. However, their performance is limited by the requirement for experienced colposcopists. This study aimed to develop and validate a Colposcopic Artificial Intelligence Auxiliary Diagnostic System (CAIADS) for grading colposcopic impressions and guiding biopsies.
METHODS: Anonymized digital records of 19,435 patients were obtained from six hospitals across China. These records included colposcopic images, clinical information, and pathological results (gold standard). The data were randomly assigned (7:1:2) to a training and a tuning set for developing CAIADS and to a validation set for evaluating performance.
RESULTS: The agreement between CAIADS-graded colposcopic impressions and pathology findings was higher than that of colposcopies interpreted by colposcopists (82.2% versus 65.9%, kappa 0.750 versus 0.516, p < 0.001). For detecting pathological high-grade squamous intraepithelial lesion or worse (HSIL+), CAIADS showed higher sensitivity than the use of colposcopies interpreted by colposcopists at either biopsy threshold (low-grade or worse 90.5%, 95% CI 88.9-91.4% versus 83.5%, 81.5-85.3%; high-grade or worse 71.9%, 69.5-74.2% versus 60.4%, 57.9-62.9%; all p < 0.001), whereas the specificities were similar (low-grade or worse 51.8%, 49.8-53.8% versus 52.0%, 50.0-54.1%; high-grade or worse 93.9%, 92.9-94.9% versus 94.9%, 93.9-95.7%; all p > 0.05). The CAIADS also demonstrated a superior ability in predicting biopsy sites, with a median mean-intersection-over-union (mIoU) of 0.758.
CONCLUSIONS: The CAIADS has potential in assisting beginners and for improving the diagnostic quality of colposcopy and biopsy in the detection of cervical precancer/cancer.

Entities:  

Keywords:  Artificial intelligence; Cervical cancer prevention; Colposcopy diagnosis and biopsy; Global elimination of cervical cancer

Year:  2020        PMID: 33349257     DOI: 10.1186/s12916-020-01860-y

Source DB:  PubMed          Journal:  BMC Med        ISSN: 1741-7015            Impact factor:   8.775


  1 in total

1.  Application of deep learning to the classification of uterine cervical squamous epithelial lesion from colposcopy images combined with HPV types.

Authors:  Yasunari Miyagi; Kazuhiro Takehara; Yoko Nagayasu; Takahito Miyake
Journal:  Oncol Lett       Date:  2019-12-12       Impact factor: 2.967

  1 in total
  18 in total

1.  Development and validation of a predictive model for endocervical curettage in patients referred for colposcopy: A multicenter retrospective diagnostic study in China.

Authors:  Peng Xue; Bingrui Wei; Samuel Seery; Qing Li; Zichen Ye; Yu Jiang; Youlin Qiao
Journal:  Chin J Cancer Res       Date:  2022-08-30       Impact factor: 4.026

Review 2.  Circulating biomarkers in the diagnosis and management of hepatocellular carcinoma.

Authors:  Philip Johnson; Qing Zhou; Doan Y Dao; Y M Dennis Lo
Journal:  Nat Rev Gastroenterol Hepatol       Date:  2022-06-08       Impact factor: 73.082

3.  Simplified Convolutional Neural Network Application for Cervix Type Classification via Colposcopic Images.

Authors:  Vitalii Pavlov; Stanislav Fyodorov; Sergey Zavjalov; Tatiana Pervunina; Igor Govorov; Eduard Komlichenko; Viktor Deynega; Veronika Artemenko
Journal:  Bioengineering (Basel)       Date:  2022-05-30

4.  Assessment of the Effects of Active Immunisation against Respiratory Syncytial Virus (RSV) using Decision-Analytic Models: A Systematic Review with a Focus on Vaccination Strategies, Modelling Methods and Input Data.

Authors:  Marina Treskova; Francisco Pozo-Martin; Stefan Scholz; Viktoria Schönfeld; Ole Wichmann; Thomas Harder
Journal:  Pharmacoeconomics       Date:  2021-01-19       Impact factor: 4.981

5.  Assessing colposcopic accuracy for high-grade squamous intraepithelial lesion detection: a retrospective, cohort study.

Authors:  Anying Bai; Jiaxu Wang; Qing Li; Samuel Seery; Peng Xue; Yu Jiang
Journal:  BMC Womens Health       Date:  2022-01-11       Impact factor: 2.809

6.  The Performance of Artificial Intelligence in Cervical Colposcopy: A Retrospective Data Analysis.

Authors:  Yuqian Zhao; Yucong Li; Lu Xing; Haike Lei; Duke Chen; Chao Tang; Xiaosheng Li
Journal:  J Oncol       Date:  2022-01-05       Impact factor: 4.375

7.  Artificial Intelligence-Aid Colonoscopy Vs. Conventional Colonoscopy for Polyp and Adenoma Detection: A Systematic Review of 7 Discordant Meta-Analyses.

Authors:  Hui Pan; Mingyan Cai; Qi Liao; Yong Jiang; Yige Liu; Xiaolong Zhuang; Ying Yu
Journal:  Front Med (Lausanne)       Date:  2022-01-13

8.  Deep learning in image-based breast and cervical cancer detection: a systematic review and meta-analysis.

Authors:  Peng Xue; Jiaxu Wang; Dongxu Qin; Huijiao Yan; Yimin Qu; Samuel Seery; Yu Jiang; Youlin Qiao
Journal:  NPJ Digit Med       Date:  2022-02-15

9.  Cohort Profile: Chinese Cervical Cancer Clinical Study.

Authors:  Xi-Ru Zhang; Zhi-Qiang Li; Li-Xin Sun; Ping Liu; Zhi-Hao Li; Peng-Fei Li; Hong-Wei Zhao; Bi-Liang Chen; Mei Ji; Li Wang; Shan Kang; Jing-He Lang; Chen Mao; Chun-Lin Chen
Journal:  Front Oncol       Date:  2021-06-18       Impact factor: 6.244

10.  The Application of Artificial Intelligence-Assisted Colposcopy in a Tertiary Care Hospital within a Cervical Pathology Diagnostic Unit.

Authors:  Aleksandra Zimmer-Stelmach; Jan Zak; Agata Pawlosek; Anna Rosner-Tenerowicz; Joanna Budny-Winska; Michal Pomorski; Tomasz Fuchs; Mariusz Zimmer
Journal:  Diagnostics (Basel)       Date:  2022-01-04
View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.