AI-Powered System Combines MRI and Ultrasound Technology for Fast, Non-Invasive Endometriosis Diagnosis

Endometriosis, a painful condition in which sensitive tissue grows beyond the uterus, affects millions of women worldwide. The diagnosis of endometriosis often faces delays, with an average waiting period of 7-12 years for most women. The current diagnostic approach involves performing keyhole (laparoscopic) surgery to visually inspect endometrial deposits in the abdomen, subsequently confirmed through microscopic analysis. However, surgery presents challenges, accessibility issues, and often incurs delays. The prolonged diagnostic process of endometriosis can contribute to anxiety, depression, and fatigue, and necessitate consultations with numerous healthcare professionals.

Now, a new study using machine learning to automatically digitally combine the diagnostic capabilities of pelvic scans and magnetic resonance imaging (MRI) for identifying endometriosis lesions seeks to shorten the diagnostic journey as well as reduce reliance on surgery. The new artificial intelligence (AI) system with technology developed by the University of Adelaide (Adelaide, Australia) in partnership with researchers from the University of Surrey (Guildford, UK) could improve the quality of life of millions suffering from endometriosis. The IMAGENDO system developed by the researchers leverages AI to analyze data from ultrasound and MRI scans, significantly shortening the time required for endometriosis diagnosis.

Image: The IMAGENDO study aims to reducing the diagnostic delay of endometriosis through imaging (Photo courtesy of University of Adelaide)

“While the legitimate concerns about the use of AI have dominated the headlines, here is an example of how this technology can improve the lives of millions of people who suffer from endometriosis and severe pelvic pain,” said Professor Gustavo Carneiro, Professor of AI and Machine Learning at the University of Surrey and one of the Chief Investigators of IMAGENDO. “IMAGENDO is introducing innovative AI capabilities to provide fast, non-invasive endometriosis diagnosis by combining MRI and ultrasound technology.”

Related Links:
University of Adelaide
University of Surrey