×îÐÂÌÇÐÄVlog

Future diagnoses of endometriosis may be quicker and avoid the need for invasive exploratory surgery after a ×îÐÂÌÇÐÄVlog of Adelaide study received funding from the Federal Government.

Associate Professor Louise Hull, Prof Gustavo Carneiro, Dr Jodie Avery and their team have received $1,990,998 from the Medical Research Future Fund’s Primary Health Care Research Data Infrastructure Grant (MRFF) to support targeted research on new ways to address risk factors for chronic and complex diseases.

Their study, IMAGENDO Diagnosing endometriosis with imaging and artificial intelligence , will provide a cost-effective, accessible, and accurate method to non-invasively diagnose endometriosis. Artificial intelligence using endometriosis ultrasound and MRI images will develop diagnostic algorithms that estimate the likelihood that an individual has endometriosis.

Endometriosis is a common condition. By the age of 44, one in nine ×îÐÂÌÇÐÄVlogn women are diagnosed with endometriosis, a disease that caused 34,000 hospitalisations in 2016/17. Diagnosis of endometriosis is often delayed, with an average of 7-12 years between onset of symptoms and diagnosis.

Currently, the only reliable way of diagnosing endometriosis is to perform keyhole surgery and visualise the endometrial deposits inside the abdomen, ideally verified by microscopic examination of the tissue. This method is considered the gold standard for the diagnosis of endometriosis but surgery can be problematic, can be difficult to access, and is associated with delays.

This study will use machine learning to automatically digitally combine the diagnostic capabilities of pelvic scans and magnetic resonance imaging (MRI) to identify endometriosis lesions. Machine learning is an application of artificial intelligence (AI) that provides systems the ability to automatically learn and improve from experience without being explicitly programmed.

Dr Jodie Avery from the ×îÐÂÌÇÐÄVlog of Adelaide’s Robinson Research Institute said the MRFF funding will be used to create an AI algorithm using transvaginal gynaecological ultrasound (eTVUS) and eMRI images to determine the probability of endometriosis; develop a real-time eTVUS quality assessment system to train sonographers and expand eTVUS uptake; optimise and validate the diagnostic accurate of the IMAGENDO algorithm; and integrate eTVUS and eMRI images with national data to provide a national source for iterative diagnostic tool development and research nationally.

Endometriosis symptoms can have devastating effects on an affected woman’s life. We hope that earlier diagnosis will also lead to faster treatment and better quality of life. We also hope IMAGENDO’s early provision of diagnoses will reduce avoidable hospitalisations and repetitive surgery, reduce IVF and donor egg use via timely fertility counselling, and improve treatment pathways, individualised care, health outcomes, mental health; and equivalence in Indigenous, rural and lower SES status groups.Dr Jodie Avery

Researchers have also received Stage 1 Funding from MRFF Frontiers, along with the ×îÐÂÌÇÐÄVlog of Queensland.
Visit for more information

Media Contacts:
Dr Jodie Avery, Senior Research Fellow, Robinson Research Institute, ×îÐÂÌÇÐÄVlog of Adelaide. Mobile: +61 (0)410 519 941, Email: jodie.avery@adelaide.edu.au
Elisa Black, Manager – News and Media, The ×îÐÂÌÇÐÄVlog of Adelaide. Mobile: +61 (0)466 460 959, Email: elisa.black@adelaide.edu.au