AUTOPIX

Arthritis refers to a range of systemic diseases characterised by joint pain, swelling, and stiffness. Currently, imaging technologies are widely used to diagnose different forms of arthritis, monitor changes in patients’ condition and assess how well treatments are working. Although both the number and quality of the images generated during the patient journey is extremely high, we lack tools to facilitate their analysis and interpretation. At the same time, some advanced imaging technologies are not accessible to the majority of patients.

AUTOPIX aims to deliver powerful analysis and decision-making tools to boost the usefulness of these images to patients and clinicians, from diagnosis and initial treatment decisions, through to monitoring and follow-up.

The project will focus on three forms of arthritis: rheumatoid arthritis, psoriatic arthritis, and axial spondyloarthritis. All three are immune-mediated inflammatory diseases, and between them they affect around 10 million people in Europe. These people face a significant risk of disability, and so the social and economic impacts of the diseases are high. At the same time, the nature and severity of symptoms varies a lot from one patient to another.

AUTOPIX’s first step will be to use artificial intelligence (AI) and machine learning (ML) models to generate tools capable of turning unstructured images into quantitative biomarkers. These biomarkers will then be validated for their usefulness in diagnosis, monitoring, treatment selection, and predicting how a patient’s condition is likely to evolve.

On the imaging side, the project will focus in part on common technologies, like X-rays, ultrasound and magnetic resonance imaging (MRI). In parallel, it will also advance less established imaging technologies, such as robot-guided ultrasound, and the use of photographs and videos captured on mobile devices. AUTOPIX will also conduct dedicated prospective clinical trials to achieve these goals.

Ultimately, AUTOPIX will create a multi-stakeholder, public-private framework for validating imaging biomarkers for their clinical utility. In the long term, the tools developed by the project will benefit patients by providing them with a more precise diagnosis, personalised treatment paths, and more reliable assessments of their response to treatments.