165 newborns die every day of Bacterial Meningitis (BM), an aggressive infection that leaves severe sequelae among 30% of survivors. Rapid detection, particularly in this age group, is difficult due to the little specificity and overlap of its symptoms with those of more common and less severe diseases. Current strategy to improve prognosis is the prompt antibiotic treatment after an early diagnosis by means of a lumbar puncture (LP), invasive and potentially harmful procedure. However, about 95% of the 8.000 LPs performed in young infants with fever of unknown source and suspected for BM result negative, raising Spanish hospital costs in 25M€. In resource-constrained countries lacking of laboratory facilities to analyse the sample, LPs are under-performed in spite of the high incidence of the infection in this context and raising neonatal mortality up to 50%.
In such scenario our objective is, first, to develop a technology providing a non-invasive measurement of the leucocyte concentration in the cerebrospinal fluid (CSF) of newborn suspected for BM. A high leucocyte concentration raises the BM suspicion and confirms the need of antibiotic treatment. The measurement will be done through the young infant fontanel by means of a prototype based on high frequency (20-25MHz) ultrasound. Ultrasound images obtained are processed to estimate cell concentration based on different quantitative approaches: Among them IA algorithms are explored as an alternative for such task.