Artificial intelligence in imaging in the first trimester of pregnancy: a systematic review.

ultrasonography in the first trimester of pregnancy offers an early screening tool to identify high risk pregnancies. Artificial intelligence (AI) algorithms have the potential to improve the accuracy of diagnosis and assist the clinician in early risk stratification. to conduct a systematic review of the use of AI in ultrasonography in the first trimester of pregnancy. We conducted a systematic literature review by searching in computerised databases Pubmed, Embase and Google Scholar from inception to January 2024. Full text peer reviewed journal publications written in English on the evaluation of AI in first trimester pregnancy imaging were included. Review papers, conference abstracts, posters, animal studies, non-English and non-peer-reviewed articles were excluded. Risk of bias was assessed by using PROBAST. Of the 1595 non-duplicated records screened, 27 studies were included. Twelve studies focussed on segmentation, eight on plane detection, six on image classification and one on both segmentation and classification. Five studies included fetuses with a gestational age of less than ten weeks. The size of the datasets was relatively small, as sixteen studies included less than 1000 cases. The models were evaluated by different metrics. Duration to run the algorithm was reported in twelve publications and ranged between less than one second and fourteen minutes. Only one study was externally validated. Even though the included algorithms reported a good performance in a research setting on testing datasets, further research and collaboration between AI experts and clinicians is needed before implementation in clinical practice.

Informations de copyright

The Author(s). Published by S. Karger AG, Basel.