Prenatal alcohol consumption has a deleterious effect on foetal development, causing a wide range of life-long adverse outcomes for the unborn child. Alcohol’s teratogenic insult targets the developing central nervous system resulting in craniofacial effects, neurocognitive and behavioural deficits, and restricted growth. Foetal Alcohol Spectrum Disorder (FASD) is the umbrella term encompassing the range of outcomes that result from prenatal
alcohol exposure. At the most severe end of this spectrum is Foetal Alcohol Syndrome (FAS), characterised by a reduced head circumference (<10th %tile), cognitive and/or behavioural defects, and a set of identifiable facial characteristics. Currently, no reliable biomarker exists for diagnosis, so the analysis of the facial dysmorphism plays
an important role for identification. However, only a small proportion (10-15%) of the alcohol-exposed population present with the facial criteria required for an FAS diagnosis, meaning affected individuals are often missed, undiagnosed or misdiagnosed. The clinical assessment for FASD related facial dysmorphism remains necessarily subjective. Utilising 3D imaging in combination with machine learning we ultimately aim to provide improved methods for FASD screening.

The main aims of our project are to improve our understanding of FASD related face
and brain dymorphorism, identify the relationships between face-brain and behaviour and subsequently deliver
tools to introduce into the clinical workflow.