AI-Driven Large-scale Screening for Oral and Oropharyngeal Cancer

Purpose and goal:

High mortality in oral cancer is largely due to late diagnosis. Today´s cancer detection methods are expensive and painful. In the project, we have scaled up and improved our AI-methods for early diagnosis based on non-invasive sampling, providing radically reduced costs and at the same time increased accuracy.

As part of introducing our techniques in healthcare, we have started a 5-year longitudinal multicenter study with eight regions in Sweden, an important step towards our long-term goal of implementing cheap and efficient AI-driven screening for oral and oropharyngeal cancer. Expected results and effects:

The project enables reliable detection of patients at risk of developing cancer of the oral cavity and throat through non-invasive brush sampling. Cytological analysis is enhanced by an XAI-based diagnostic support system that reduces the burden of manual analysis and provides fast and reliable diagnosis at low cost. The project results, in the form of an economically efficient and practically simple, yet powerful screening program for early detection of oral and oropharyngeal cancer, will have a strong positive impact on global health, but also on the usefulness of AI in healthcare.

Approach and implementation:

The project, a collaboration between Sweden and India, initially suffered from the pandemic in several ways; travel was limited, the opportunity for sampling was reduced and our international medical expertise was largely occupied with Covid patients. However, travel restrictions encouraged the development of our web-based annotation environment into a platform for efficient communication of collected samples and AI results.

Getting the longitudinal study off the ground was labor intensive. We are asking for powerful efforts to simplify cooperation between Sweden´s regions.