The Artificial Intelligence implementation of Swede Score estimation using mobile colposcopes

Purpose and goal: We aim to develop and validate an automatic image analysis tool that enables more secure and reliable diagnostic in distinguishing lesions that can lead to cervical cancer from benign lesions. Expected results and effects: In this project a software tool will be developed based on state-of-the-art machine learning methods

which will help medical personel analyze images that are taken by the Gynius developed handheld colposcopes named Gynocular. The software will be developed and validated both on data that has been gathered in the field of the cervical cancer screening sessions in developing countries. Approach and implementation:

This project will be carried out with the collaboration of Gynius, Stiftelsen Chalmers Industriteknik and Elekta Foundation. Also, gynecologists will participate as experts in evaluating the developed methods. Gynius has been developing medtech devices for use in the field of cervical cancer for a decade and

will lead the management of the project.