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

Endometriosis is a common disorder that has many characteristics, including the pouch of Douglas (POD) obliteration, which can be diagnosed using transvaginal ultrasound (TVUS) and magnetic resonance imaging (MRI). TVUS and MRI are complementary, non-invasive endometriosis diagnosis imaging techniques, but patients are usually not scanned using both modalities. Furthermore, it is generally more challenging to detect POD obliteration from MRI than TVUS. To mitigate this imbalance, this research aimed to create a knowledge distillation training algorithm to improve the POD obliteration detection from MRI, by leveraging the detection results from unpaired TVUS data. A machine learning model was pretrained using 8,984 unlabelled MRIs of the female pelvis. The algorithm was then fine tuned with 89 labelled MRI, performed specifically for investigation of endometriosis. Following this, 749 unpaired labelled TVUS videos demonstrating the uterine ‘sliding sing’ were introduced, to distil the knowledge from the teacher TVUS POD obliteration detector to train the student MRI model. The inclusion of the unpaired TVUS videos increased detection of POD obliteration from MRI with our machine learning model. This multimodal analysis method improved the Area Under the Curve (AUC) from 65.0% to 90.6%. Pretraining using digital data from different imaging modalities can improve the diagnosis of POD obliteration. By using a multimodal approach to creating machine learning models, diagnostic accuracy of POD obliteration was able to be improved by utilising unpaired eTVUS videos to pretrain MRI models.