1
|
Chongsuwat T, Wang C, Sohn Y, Klump K. Digital cervicography for cervical cancer screening in low-resource settings: A scoping review. Gynecol Oncol Rep 2023; 45:101130. [PMID: 36683777 PMCID: PMC9845952 DOI: 10.1016/j.gore.2022.101130] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/20/2022] [Revised: 12/20/2022] [Accepted: 12/23/2022] [Indexed: 01/05/2023] Open
Abstract
Introduction Digital cervicography (DC) is a method of capturing images for analysis during visual inspection with acetic acid (VIA) for cervical cancer screening. Cervical cancer is the 3rd leading cause of female cancer in the world with approximately 90 % of deaths due to cervical cancer occurring in low and middle income countries (LMICs). The need for cost-effective and sustainable methods for screening is vital in these settings. This scoping review systematically synthesizes published data illustrating the use of DC in screening programs. We aim to understand how digital cervicography is used, implemented, and impacted on programs. Methods Search of eight online databases identified 53 studies published between 1993 and 2021. Inclusion of articles were English language, cervical cancer screening program located in an LMIC, and DC as an intervention. Results All studies were cross-sectional studies (n = 53), with variation in terminology, uses, and device methods. Devices were grouped as either smartphones (n = 14), commercially available digital cameras (n = 17), or other (EVA®, n = 4; Cerviscope, n = 12; custom device, n = 4; or not specified, n = 2). Nineteen studies found acceptability and feasibility for DC in their screening programs. Various programs using DC found benefits such as task sharing, healthcare worker training, patient education and using images for review from a remote specialist or mentor. Conclusion The use of DC in LMICs is beneficial for support of healthcare workers, enhances quality improvement and demonstrates overall acceptability in screening programs. Advancing technologies for human papillomavirus (HPV) testing and cytology are common methods for cervical cancer screening, although are limited in LMICs. This scoping review demonstrates the different methods, uses, and benefit of digital cervicography in cervical cancer screening programs.
Collapse
Affiliation(s)
- Tana Chongsuwat
- University of Wisconsin School of Medicine and Public Health, 1100 Delaplaine Ct, Madison, WI 53715, United States,Corresponding author at: 1100 Delaplaine Ct, Madison, WI 53715, United States.
| | - Connor Wang
- University of Wisconsin School of Medicine and Public Health, 1100 Delaplaine Ct, Madison, WI 53715, United States
| | - Younji Sohn
- University of Oklahoma College of Medicine, 900 NE 10th St, Oklahoma City, OK 73104, United States
| | - Kathryn Klump
- University of Oklahoma College of Medicine, 900 NE 10th St, Oklahoma City, OK 73104, United States
| |
Collapse
|
2
|
Perkins R, Jeronimo J, Hammer A, Novetsky A, Guido R, Del Pino M, Louwers J, Marcus J, Resende C, Smith K, Egemen D, Befano B, Smith D, Antani S, de Sanjose S, Schiffman M. Comparison of accuracy and reproducibility of colposcopic impression based on a single image versus a two-minute time series of colposcopic images. Gynecol Oncol 2022; 167:89-95. [PMID: 36008184 DOI: 10.1016/j.ygyno.2022.08.001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/14/2022] [Revised: 08/01/2022] [Accepted: 08/02/2022] [Indexed: 11/26/2022]
Abstract
OBJECTIVE Colposcopy is an important part of cervical screening/management programs. Colposcopic appearance is often classified, for teaching and telemedicine, based on static images that do not reveal the dynamics of acetowhitening. We compared the accuracy and reproducibility of colposcopic impression based on a single image at one minute after application of acetic acid versus a time-series of 17 sequential images over two minutes. METHODS Approximately 5000 colposcopic examinations conducted with the DYSIS colposcopic system were divided into 10 random sets, each assigned to a separate expert colposcopist. Colposcopists first classified single two-dimensional images at one minute and then a time-series of 17 sequential images as 'normal,' 'indeterminate,' 'high grade,' or 'cancer'. Ratings were compared to histologic diagnoses. Additionally, 5 colposcopists reviewed a subset of 200 single images and 200 time series to estimate intra- and inter-rater reliability. RESULTS Of 4640 patients with adequate images, only 24.4% were correctly categorized by single image visual assessment (11% of 64 cancers; 31% of 605 CIN3; 22.4% of 558 CIN2; 23.9% of 3412 < CIN2). Individual colposcopist accuracy was low; Youden indices (sensitivity plus specificity minus one) ranged from 0.07 to 0.24. Use of the time-series increased the proportion of images classified as normal, regardless of histology. Intra-rater reliability was substantial (weighted kappa = 0.64); inter-rater reliability was fair ( weighted kappa = 0.26). CONCLUSION Substantial variation exists in visual assessment of colposcopic images, even when a 17-image time series showing the two-minute process of acetowhitening is presented. We are currently evaluating whether deep-learning image evaluation can assist classification.
Collapse
Affiliation(s)
- Rebecca Perkins
- Boston University School of Medicine/Boston Medical Center, Boston, MA, USA.
| | | | - Anne Hammer
- Department of Obstetrics and Gynecology, Gødstrup Hospital, NIDO - centre for research and education, Herning, Denmark; Department of Clinical Medicine, Aarhus University, Aarhus, Denmark
| | - Akiva Novetsky
- Westchester Medical Center/New York Medical College, Valhalla, NY, USA
| | - Richard Guido
- University of Pittsburgh, Magee-Womens Hospital, Pittsburgh, PA, USA
| | - Marta Del Pino
- Clínic Institute of Gynecology, Obstetrics, and Neonatology (ICGON), Hospital Clínic Barcelona, Spain; Institut d'Investigacions Biomèdiques August Pi i Sunyer (IDIBAPS), Spain; Barcelona University, Medicine Faculty, Barcelona, Spain
| | - Jaqueline Louwers
- Diakonessenhuis, department of Obstetrics and Gynecology, Utrecht, the Netherlands
| | - Jenna Marcus
- Feinberg School of Medicine at Northwestern University, Chicago, IL, USA
| | | | - Katie Smith
- University of Oklahoma Health Sciences Center, Oklahoma City, OK, USA
| | | | - Brian Befano
- Information Management Services Inc, 3901 Calverton Blvd Suite 200, Calverton, MD, USA
| | - Debi Smith
- National Cancer Institute, Bethesda, MD, USA
| | - Sameer Antani
- National Library of Medicine, National Institutes of Health, Bethesda, MD, USA
| | - Silvia de Sanjose
- National Cancer Institute, Bethesda, MD, USA; ISGlobal, Barcelona, Spain
| | | |
Collapse
|
3
|
Takahashi T, Matsuoka H, Sakurai R, Akatsuka J, Kobayashi Y, Nakamura M, Iwata T, Banno K, Matsuzaki M, Takayama J, Aoki D, Yamamoto Y, Tamiya G. Development of a prognostic prediction support system for cervical intraepithelial neoplasia using artificial intelligence-based diagnosis. J Gynecol Oncol 2022; 33:e57. [PMID: 35712970 PMCID: PMC9428307 DOI: 10.3802/jgo.2022.33.e57] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/18/2022] [Revised: 04/07/2022] [Accepted: 04/29/2022] [Indexed: 11/30/2022] Open
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. High-grade lesion occupancy in the uterovaginal area was significantly correlated with CIN2 patients’ prognosis. The number of high-grade lesions in 12 segments detected by an artificial intelligence (AI)-based system was comparable to that detected by senior colposcopists. The overall correct response rate of the AI algorithm for detecting high-grade lesions was 89.7%.
Collapse
Affiliation(s)
- Takayuki Takahashi
- Statistical Genetics Team, RIKEN Center for Advanced Intelligence Project, Tokyo, Japan
- Department of Obstetrics and Gynecology, Keio University School of Medicine, Tokyo, Japan
| | - Hikaru Matsuoka
- Statistical Genetics Team, RIKEN Center for Advanced Intelligence Project, Tokyo, Japan
| | - Rieko Sakurai
- Statistical Genetics Team, RIKEN Center for Advanced Intelligence Project, Tokyo, Japan
| | - Jun Akatsuka
- Pathology Informatics Team, RIKEN Center for Advanced Intelligence Project, Tokyo, Japan
- Department of Urology, Nippon Medical School Hospital, Tokyo, Japan
| | - Yusuke Kobayashi
- Department of Obstetrics and Gynecology, Keio University School of Medicine, Tokyo, Japan
| | - Masaru Nakamura
- Department of Obstetrics and Gynecology, Keio University School of Medicine, Tokyo, Japan
| | - Takashi Iwata
- Department of Obstetrics and Gynecology, Keio University School of Medicine, Tokyo, Japan
| | - Kouji Banno
- Department of Obstetrics and Gynecology, Keio University School of Medicine, Tokyo, Japan
| | - Motomichi Matsuzaki
- Statistical Genetics Team, RIKEN Center for Advanced Intelligence Project, Tokyo, Japan
| | - Jun Takayama
- Statistical Genetics Team, RIKEN Center for Advanced Intelligence Project, Tokyo, Japan
- Tohoku University Graduate School of Medicine, Miyagi, Japan
| | - Daisuke Aoki
- Department of Obstetrics and Gynecology, Keio University School of Medicine, Tokyo, Japan
| | - Yoichiro Yamamoto
- Pathology Informatics Team, RIKEN Center for Advanced Intelligence Project, Tokyo, Japan
| | - Gen Tamiya
- Statistical Genetics Team, RIKEN Center for Advanced Intelligence Project, Tokyo, Japan
- Tohoku University Graduate School of Medicine, Miyagi, Japan
| |
Collapse
|