Developing an US-MRI Biomarker Fusion Model for Endometriosis (DEFEND)

In the United Kingdom (UK), endometriosis is one of the most common gynaecological diseases needing treatment. The prevalence of disease is often underestimated, however it is believed to affect at least 1 in 10 women in the UK. Within the NHS, endometriosis costs the UK economy approximately £8.2 billion a year in treatment, loss of work and healthcare costs.

Currently, the first diagnostic recommendation for endometriosis is and Ultrasound (US) scan or a MRI, followed by a diagnostic surgery called laparoscopy. Accurate diagnoses is usually limited to specialist tertiary centres, therefore a delayed diagnosis is a significant problem for women with endometriosis. Limited experience in the disease area can also lead to misdiagnosis and the latest report from the National Institute of Clinical Excellence (NICE) reports a time delay of around 7.5 years before a confirmed diagnosis of endometriosis. A model that could accurately predict surgical findings of endometriosis would be of significant clinical and economical benefit.

The main aim of this study is to curate a database of patients with varying levels of endometriosis. This database will contain fully anonymised MR and US images alongside clinical data for further use in research. There will be no intervention outside of standard of care. US and clinical data will be collected during routine visits and patients will be offered an additional visit to have a MRI. The ultimate aim is to then use this data to develop a widely available diagnostic tool based on MRI and US imaging modalities using computer modelling. Validating the predictive model with surgical findings will increase confidence and access to advanced imaging for non-experts, allowing clinicians to accurately predict surgical findings as well as reduce time to diagnosis.