Fetal Assessment Suite (FetAS): a web-based platform for automatic fetal MRI analysis using AI.
Authors
Affiliations (10)
Affiliations (10)
- Department of Electrical, Computer and Biomedical Engineering, Toronto Metropolitan University, Toronto, ON, Canada.
- Institute for Biomedical Engineering, Science and Technology (iBEST), Toronto Metropolitan University and St. Michael's Hospital, Toronto, ON, Canada.
- Division of Neuroradiology, The Hospital for Sick Children, Toronto, ON, Canada.
- Institute of Diagnostic and Interventional Neuroradiology, University Hospital, Augsburg, Germany.
- Department of Diagnostic Imaging, The Hospital for Sick Children, Toronto, ON, Canada.
- Department of Diagnostic and Interventional Radiology, The Hospital for Sick Children, Toronto, ON, Canada.
- Department of Medical Imaging, University of Toronto, Toronto, ON, Canada.
- Department of Electrical, Computer and Biomedical Engineering, Toronto Metropolitan University, Toronto, ON, Canada. [email protected].
- Institute for Biomedical Engineering, Science and Technology (iBEST), Toronto Metropolitan University and St. Michael's Hospital, Toronto, ON, Canada. [email protected].
- Department of Obstetrics and Gynecology, University of Toronto, Toronto, ON, Canada. [email protected].
Abstract
Fetal MRI provides high-resolution, three-dimensional imaging with superior soft tissue contrast, offering critical diagnostic insights that complement ultrasound, particularly in cases of suspected abnormalities. However, its interpretation remains labour-intensive and highly dependent on subspecialized radiological expertise, which limits accessibility and contributes to diagnostic delays. To address these challenges, we present the Fetal Assessment Suite (FetAS), a secure, web-based platform designed to streamline and standardize fetal MRI analysis. FetAS automates key tasks, including artifact detection, motion correction, segmentation of the fetal body, amniotic fluid, and placenta, as well as classification of fetal and placental position and orientation, using AI models developed to reduce reliance on expert radiologists. By consolidating these capabilities into a single, user-friendly interface, FetAS reduces the cognitive and time burden of interpretation, supports timely clinical decision-making, and promotes equitable access to care in regions without local expertise. In addition, FetAS enables research through standardized pipelines, facilitates data sharing, and provides a foundation for future advancements in maternal-fetal imaging. Collectively, these features establish FetAS as both a diagnostic tool and a platform for expanding high-quality prenatal care across diverse healthcare settings.