d3pm · Sonio: Deep-Learning for Detection and Diagnostic of Prenatal Malformations

1 child out of 33 is born with a congenital malformation in developed countries, leading to mortality & disability which impact the children, the families & healthcare system. Fetal ultrasound is the standard non invasive examination to screen for malformations, but 50% of malformations are not detected at routine exams as fetal ultrasound is very complex, time-consuming & highly operator-dependent. One needs to acquire the right images, interpret them & combine them with blood or/and genetic tests to get the right diagnosis. We created Sonio, an AI one-stop modular software platform to guide OBGYNS & sonographers during fetal ultrasound. The core is the Clinical Brain, a unique mix between fetal medicine & AI, aware of 1.6k anomalies & 450 syndromes. It can prioritize anomalies to identify the most probable diagnoses based on medical history & observed phenotype. With EIC support, we will fully build image recognition & genomics into our platform to revolutionize prenatal diagnosis.