OP07.05: Artificial intelligence to detect pouch of Douglas obliteration from magnetic resonance imaging by combining unpaired transvaginal ultrasound videos.

This article discusses the use of artificial intelligence (AI) to detect pouch of Douglas (POD) obliteration, a characteristic of endometriosis, from magnetic resonance imaging (MRI) by combining unpaired transvaginal ultrasound (TVUS) videos. The researchers developed a machine learning model that was pretrained using unlabelled MRIs and then fine-tuned with labelled MRIs and unpaired labelled TVUS videos. The inclusion of the TVUS videos improved the detection of POD obliteration from MRI, increasing the diagnostic accuracy. This multimodal approach shows promise in improving the diagnosis of POD obliteration in endometriosis. [Extracted from the article]