China
Africa
Explore chapters and articles related to this topic
Artificial intelligence as a feminist bioethics issue
Published in Wendy A. Rogers, Jackie Leach Scully, Stacy M. Carter, Vikki A. Entwistle, Catherine Mills, The Routledge Handbook of Feminist Bioethics, 2022
AI applications are also being developed to advance care for cervical cancer, which is the second most common type of cancer in women aged 15 to 44 years worldwide (ICO/IARC 2014). In particular, less-resourced countries are burdened with 80% of cervical cancer incidence and 90% of cervical cancer mortality respectively (Hu et al. 2019). Pap smears, human papillomavirus (HPV) tests and colposcopy are common screening and diagnostic tools in high-income countries, but they require expensive specialized equipment, laboratories and qualified personnel. Emerging AI technologies for cervical cancer detection include cervicography algorithms to classify cervical dysplasia and automated visual evaluation algorithms that can analyze digital images to identify precancerous cells (Xu et al. 2017; Hu et al. 2019). There is great hope that these methods can provide more affordable tools for low-resource regions that may lack qualified specialists (Xu et al. 2017). Other commercial products in development for cervical care include “smart” tampon platforms that aim at identifying early biomarkers for endometriosis and cervical cancer by analyzing women’s menstrual blood (“Nextgen Jane,” 2020).
Gynaecology
Published in Andrew Stevens, James Raftery, Gynaecology Health Care Needs Assessment, 2018
There is currently no routine clinical role for cervicography in either primary cervical screening or in the further assessment of patients with abnormal cytology. Although there may be a role for cervicography in the surveillance of patients with mild dyskaryosis or borderline changes to reduce the frequency of referral for formal colposcopy this requires further evaluation.28,236
Searching for an ideal cervical cancer screening model to reduce false-negative errors in a country with high prevalence of cervical cancer
Published in Journal of Obstetrics and Gynaecology, 2020
Taejong Song, Seok Ju Seong, Seon-Kyung Lee, Byoung-Ryun Kim, Woong Ju, Ki Hyung Kim, Kyehyun Nam, Jae Chul Sim, Tae Jin Kim
Cervicography is a diagnostic medical procedure in which a non-colposcopist takes pictures of the cervix and submits them to a colposcopist for interpretation (Nam et al. 2016). In this study, the cervix was visualised using a self-retaining speculum, and a specifically TeleCervico camera (Dr.Cervicam; NTL Medical Institute, Yongin, Korea) was used to take two photographs (cervigrams). The first image was obtained 30 s after 5% acetic acid was applied to the cervix after removing mucus or discharge. A second acetic acid application to the cervix was performed, and another image was taken after 15 s after the second application. The images were transmitted to a server via the internet for immediate evaluation. Each cervicogram was interpreted by expert colposcopists, all of whom were professors at hospitals associated with medical colleges in Korea and had considerable experience in colposcopy. The positive cut-off for cervicography was positive 0 or worse.
Advances in technologies for cervical cancer detection in low-resource settings
Published in Expert Review of Molecular Diagnostics, 2019
Kathryn A. Kundrod, Chelsey A. Smith, Brady Hunt, Richard A. Schwarz, Kathleen Schmeler, Rebecca Richards-Kortum
Placing lower-cost technology into the hands of practitioners is a step forward in terms of accessibility, but confidence in the technology and removing subjectivity to reduce inter-user variability is important for proper uptake and consistent performance. Improved algorithms for real-time image classification can bolster confidence in diagnostic decision-making. One approach to improve image classification algorithms is through the use of machine learning (ML) or artificial intelligence (AI). AI has been evaluated with cervicography, a procedure in which an image of the cervix is taken with a fixed-focus camera during screening. In a study including 9,406 women, real-time interpretation of cervigrams without decision support yielded an area under the curve (AUC) of 0.69; after the fact, when AI-enabled image classification was developed, the reported AUC was 0.91, illustrating the potential for AI-enabled decision support [32]. Similarly, cervigrams obtained using VILI and the POCkeT Colposcope were trained using a support vector machine (SVM) classifier, and the resulting algorithm produced a sensitivity of 89.2%, a specificity of 66.7%, and an AUC of 0.84. Decision support on a procedure as variable as VILI would be helpful in improving reproducibility and diagnostic performance [139].