Development of a prognostic prediction support system for cervical intraepithelial neoplasia using artificial intelligence-based diagnosis

다국어 초록 (Multilingual Abstract)

Objective: Human papillomavirus subtypes are predictive indicators of cervical intraepithelial neoplasia (CIN) progression. While colposcopy is also an essential part of cervical cancer prevention, its accuracy and reproducibility are limited because of subjective evaluation. This study aimed to develop an artificial intelligence (AI) algorithm that can accurately detect the optimal lesion associated with prognosis using colposcopic images of CIN2 patients by utilizing objective AI diagnosis.
Methods: We identified colposcopic findings associated with the prognosis of patients with CIN2. We developed a convolutional neural network that can automatically detect the rate of high-grade lesions in the uterovaginal area in 12 segments. We finally evaluated the detection accuracy of our AI algorithm compared with the scores by multiple gynecologic oncologists. Results: High-grade lesion occupancy in the uterovaginal area detected by senior colposcopists was significantly correlated with the prognosis of patients with CIN2. The detection rate for high-grade lesions in 12 segments of the uterovaginal area by the AI system was 62.1% for recall, and the overall correct response rate was 89.7%. Moreover, the percentage of high-grade lesions detected by the AI system was significantly correlated with the rate detected by multiple gynecologic senior oncologists (r=0.61).
Conclusion: Our novel AI algorithm can accurately determine high-grade lesions associated with prognosis on colposcopic images, and these results provide an insight into the additional utility of colposcopy for the management of patients with CIN2.

참고문헌 (Reference)

1 World Health Organization, "WHO guidelines for screening and treatment of precancerous lesions for cervical cancer prevention" World Health Organization

2 Carcangiu M, "WHO classification of tumours of female reproductive organs"

3 Ronneberger O, "U-net: convolutional networks for biomedical image segmentation" Springer 234-241, 2015

4 Kyrgiou M, "The up-to-date evidence on colposcopy practice and treatment of cervical intraepithelial neoplasia : the Cochrane colposcopy & cervical cytopathology collaborative group(C5 group)approach" 32 : 516-523, 2006

5 Loopik DL, "The risk of cervical cancer after cervical intraepithelial neoplasia grade 3 : a population-based cohort study with 80, 442 women" 157 : 195-201, 2020

6 Castle PE, "The relationship of community biopsy-diagnosed cervical intraepithelial neoplasia grade 2 to the quality control pathology-reviewed diagnoses : an ALTS report" 127 : 805-815, 2007

7 Darragh TM, "The lower anogenital squamous terminology standardization project for HPV-associated lesions : background and consensus recommendations from the College of American Pathologists and the American Society for Colposcopy and Cervical Pathology" 16 : 205-242, 2012

8 Darragh TM, "The lower anogenital squamous terminology standardization project for HPV-associated lesions : background and consensus recommendations from the College of American Pathologists and the American Society for Colposcopy and Cervical Pathology" 136 : 1266-1297, 2012

9 Yuan C, "The application of deep learning based diagnostic system to cervical squamous intraepithelial lesions recognition in colposcopy images" 10 : 11639-, 2020

10 Massad LS, "The accuracy of colposcopic grading for detection of high-grade cervical intraepithelial neoplasia" 13 : 137-144, 2009

11 Waxman AG, "Revised terminology for cervical histopathology and its implications for management of high-grade squamous intraepithelial lesions of the cervix" 120 : 1465-1471, 2012

12 Aydın S, "Reliability and diagnostic performance of smartphone colposcopy" 155 : 404-410, 2021

13 Cox DR, "Regression models and life-tables" 34 : 187-202, 1972

14 Holowaty P, "Natural history of dysplasia of the uterine cervix" 91 : 252-258, 1999

15 Castellsagué X, "Natural history and epidemiology of HPV infection and cervical cancer" 110 : S4-S7, 2008

16 Song D, "Multimodal entity coreference for cervical dysplasia diagnosis" 34 : 229-245, 2015

17 Berthelot D, "MixMatch: a holistic approach to semi-supervised learning" Neural Information Processing Systems Foundation 5049-5059, 2019

18 Nishio H, "Liquid-based cytology versus conventional cytology for detection of uterine cervical lesions : a prospective observational study" 48 : 522-528, 2018

19 남수정 ; 정요셉 ; 정찬권 ; 곽태영 ; 이지열 ; 박지환 ; 노미정 ; 고현정, "Introduction to digital pathology and computer-aided pathology" 대한병리학회 54 (54): 125-134, 2020

20 Yang B, "False negative colposcopy is associated with thinner cervical intraepithelial neoplasia 2 and 3" 110 : 32-36, 2008

21 Quaas J, "Explanation and use of the Rio 2011 colposcopy nomenclature of the IFCPC(International Federation for Cervical Pathology and Colposcopy) : comments on the general colposcopic assessment of the uterine cervix : adequate/inadequate; squamocolumnar junction; transformation zone" 74 : 1090-1092, 2014

22 Ardila D, "End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography" 25 : 954-961, 2019

23 Bekkers RL, "Does experience in colposcopy improve identification of high grade abnormalities?" 141 : 75-78, 2008

24 Asiedu MN, "Development of algorithms for automated detection of cervical pre-cancers with a low-cost, point-of-care, pocket colposcope" 66 : 2306-2318, 2019

25 Nayar R, "Definitions, criteria, and explanatory notes" Springer 2015

26 Manopunya M, "Colposcopy audit for improving quality of service in areas with a high incidence of cervical cancer" 108 : 4-6, 2010

27 Schiffman M, "Clinical practice. Cervical-cancer screening with human papillomavirus and cytologic cotesting" 369 : 2324-2331, 2013

28 Tainio K, "Clinical course of untreated cervical intraepithelial neoplasia grade 2 under active surveillance : systematic review and meta-analysis" 360 : k499-, 2018

29 Simões PW, "Classification of images acquired with colposcopy using artificial neural networks" 13 : 119-124, 2014

30 Richart RM, "Cervical intraepithelial neoplasia" 8 : 301-328, 1973

31 O’Neill E, "Baseline colposcopic findings in women entering studies on female vaginal products" 78 : 162-166, 2008

32 Tan X, "Automatic model for cervical cancer screening based on convolutional neural network : a retrospective, multicohort, multicenter study" 21 : 35-, 2021

33 Yamamoto Y, "Automated acquisition of explainable knowledge from unannotated histopathology images" 10 : 5642-, 2019

34 Wang CW, "Artificial intelligence-assisted fast screening cervical high grade squamous intraepithelial lesion and squamous cell carcinoma diagnosis and treatment planning" 11 : 16244-, 2021

35 Bao H, "Artificial intelligence-assisted cytology for detection of cervical intraepithelial neoplasia or invasive cancer : a multicenter, clinical-based, observational study" 159 : 171-178, 2020

36 Miyagi Y, "Application of deep learning to the classification of uterine cervical squamous epithelial lesion from colposcopy images combined with HPV types" 19 : 1602-1610, 2020

37 Hu L, "An observational study of deep learning and automated evaluation of cervical images for cancer screening" 111 : 923-932, 2019

38 Ito Y, "An artificial intelligence-assisted diagnostic system improves the accuracy of image diagnosis of uterine cervical lesions" 16 : 27-, 2022

39 Khan MJ, "ASCCP colposcopy standards : role of colposcopy, benefits, potential harms, and terminology for colposcopic practice" 21 : 223-229, 2017

40 Bifulco G, "A prospective randomized study on limits of colposcopy and histology : the skill of colposcopist and colposcopy-guided biopsy in diagnosis of cervical intraepithelial lesions" 10 : 47-, 2015