Artificial intelligence applied to fetal MRI: A scoping review of current research

Abstract

Artificial intelligence (AI) is defined as the development of computer systems to perform tasks normally requiring human intelligence. A subset of AI, known as machine learning (ML), takes this further by drawing inferences from patterns in data to ‘learn’ and ‘adapt’ without explicit instructions meaning that computer systems can ‘evolve’ and hopefully improve without necessarily requiring external human influences. The potential for this novel technology has resulted in great interest from the medical community regarding how it can be applied in healthcare. Within radiology, the focus has mostly been for applications in oncological imaging, although new roles in other subspecialty fields are slowly emerging. In this scoping review we performed a literature search of the current state-of-the-art and emerging trends for the use of artificial intelligence as applied to fetal magnetic resonance imaging (MRI). Our search yielded several publications covering AI tools for anatomical organ segmentation, improved imaging sequences and aiding in diagnostic applications such as automated biometric fetal measurements and the detection of congenital and acquired abnormalities. We highlight our own perceived gaps in this literature and suggest future avenues for further research. It is our hope that the information presented highlights the varied ways and potential that novel digital technology could make an impact to future clinical practice with regards to fetal MRI.

A Theoretical Exploration of Artificial Intelligence’s Impact on Feto-Maternal Health from Conception to Delivery

“…Meshaka et al in his scoping review identified the capacity of AI in fetal Magnetic Resonance Imaging specifically for spotting congenital and acquired anomalies using algorithms like U-net, CASE-Net, V-net, and SVRnet among others. 71 Together, these studies underscore the capability of AI-enhanced tools to improve the identification of fetal structural abnormalities, exhibiting promising outcomes in accuracy and performance.…”

What is the future of artificial intelligence in obstetrics? A qualitative study among healthcare professionals

“…In that light, it is interesting to follow developments around DL-based systems in fetal MRI and fetal ultrasound imaging. As these technologies focus more on post processing of data (eg, organ segmentation, data denoising) rather than diagnosis,10 these applications could be viewed differently by healthcare professionals with regard to trust. But for high stake scenarios in obstetrics, where professionals need to be convinced of the action to take, based on the output of the AI model, interpretability might be crucial 34…”

“…Various journals have reported on the use of AI in pregnancy-related clinical decision-making. These range from estimating the chance of fetal distress during labour,7 electrohysterography to predict preterm labour,8 to AI-based fetal MRI scans 9 10. In addition, broader oriented research has been conducted on identifying factors within the healthcare domain that play a role in real-world AI adoption 11–16.…”

Machine learning and disease prediction in obstetrics

“…In intrapartum management, studies lacked external validation or quality assessment ( Tan et al, 2021 ; Ghi et al, 2022 ; Tsur et al, 2020 ; Venkatesh et al, 2020 ; Chill et al, 2021 ) but are a first step in developing clinical decision assist tools to improve safety standards. Developing multicentric databases with public availability and having multi-disciplinary and international collaborations will therefore accelerate research and improve the diversity of datasets to better represent minority groups ( Meshaka et al, 2022 , Malani et al, 2023 ).…”