Main findings
We developed an AI model to detect 12 types of CNS malformations in
fetal ultrasound images by training on 37450 images from 15264 fetuses
and testing on 812 images from 449 fetuses, our AI system achieves
performance on par with expert doctors demonstrating an artificial
intelligence capable of detecting congenital malformations with a level
of competence comparable experience doctors. Furthermore, with AI system
assistance, the performance of all the groups doctors get improved,
especially for the trainee doctors.