Full title: Improved prediction of dysplasia in the cervix with AI.
Start: January 2023
End: December 2024
Denmark has a screening programme for dysplasia in the cervix for all women between the age of 23 and 65. If first screening shows a risk for dysplasia, the woman is referred to colposcopy.
Because colposcopy is subjective and dependant on the experience of the colposcopist, the national Danish guidelines recommend four biopsies. The biopsies are unpleasant and may cause adverse effects.
The purpose of the project is to improve diagnostics of cervical cancer with artificial intelligence. The project will develop, test and implement an AI solution to guide the colposcopist in real time to find the best spots for biopsies. The solution will allow the colposcopist to inspect the cervix with a colposcope as usual, but with an overlay on the video that identifies the areas where cell changes are most likely to be found.
The hope is to be able to reduce the required number of biopsies in order to lessen discomfort for the woman and support the colposcopist, as well as to reduce the amount of biopsies sent to analysis at the Department of Pathology.
The solution is designed so that it changes as little as possible to the existing workflow and at the same time increases the skills of especially the less experienced colposcopists
- The Department of Gynaecology and Obstetrics, Odense University Hospital
- The research group Applied AI & Data Science at the Maersk Mc-Kinney Moller Institute, the University of Southern Denmark
- Cellari ApS
- Centre for Clinical Artificial Intelligence (CAI-X) as project manager.
The project is funded by the Region of Southern Denmark’s Innovation Fund.
Lone Kjeld Petersen, Professor at the Department of Gynaecology and Obstetrics, OUH, was on the cover of the local newspaper Fyens Stiftstidende in January 2023.
Read the article “Kunstig intelligens skal hjælpe OUH med at opdage kræft” (in Danish only, login required).
Lone Kjeld Petersen
Department of Gynaecology and Obstetrics
(+45) 30 57 68 10 firstname.lastname@example.org
Esmaeil S. Nadimi
Head of Technical Research
Centre for Clinical Artificial Intelligence
(+45) 27 78 19 29 email@example.com