AI-assisted VIA Screening of Cervical Cancer
This project aims to research and develop AI-assisted VIA screening using mobile-captured photos to build a more consistent and accurate smartphone-based cervical cancer screening tool that can be used by nurses and community health workers as an assistive tool.
- Cervical cancer is the fourth-most common cancer among women globally that leads to 90% deaths LMICs.
- Can be easily cured if diagnosed at an early stage and treated properly but Nepal lacks the accessibility in early-stage screenings.
- VIA (Visual Inspection Using Acetic Acid), is a simpler, inexpensive & accessible test that can be adapted suitably for low-resource settings
- But VIA is subjective, that is dependent on human expertise which is often unavailable in low-resource settings such as primary and community health care settings.
- To research and develop AI-assisted VIA screening using mobile captured photos.
- To build more consistent and accurate smartphone based cervical cancer screening tool that can be used by nurses and community health workers.
- Initial stage of data collection – capturing multiple images over the span of one minute and ongoing validation studies.
- Three different health camps have been set up to follow the data collection protocol 57 patients from these camps have been a part of the validation study VIA test conducted on 758 patients so far.
- (Target: 1500 patients).
- To reduce the limitations, we plan to establish an open-source database portal for other people to contribute as well and make the screening as applicable and accurate as possible with the help of the AI- model
Further aim to design a mobile application that can be used for testing in hospitals and low-resource settings.
Dr. Bishesh Khanal, NAAMII
Dr. Archana Shrestha, IISH
Kanchan Poudel, Research Assistant
Korea International Cooperation Agency (KOICA)
- Institute for Implementation Science & Health (IISH)
- Budhanilakantha Municipality