Using AI to Diagnose Birth Defects in Fetal Ultrasound Images
In a new proof-of-concept study led by Dr. Mark Walker of the University of Ottawa’s Faculty of Medicine, researchers are at the forefront of using a unique deep learning model based on artificial intelligence as an assistive tool for fast and accurate reading of ultrasound images.
The goal of the team’s study was to demonstrate the potential of a deep learning architecture to support the early and reliable identification of cystic hygroma from first trimester ultrasounds. Cystic hygroma is an embryonic condition that causes abnormal development of the lymphatic vascular system. It is a rare and life-threatening condition that causes swelling of fluid around the head and neck.
The birth defect can usually be easily diagnosed before birth during an ultrasound appointment, but Dr. Walker – co-founder of the OMNI (Obstetrics, Maternal and Newborn Investigations) research group at The Ottawa Hospital – and his research group wanted to test how well, AI-based pattern recognition could do the trick.
“What we have demonstrated is that in the field of ultrasound, we are able to use the same image classification and identification tools with high sensitivity and specificity,” says Dr. Walker , who thinks their approach could be applied to other commonly identified fetal anomalies. by ultrasound.
Source of the story:
Material provided by University of Ottawa. Note: Content may be edited for style and length.