SBIR Phase I: Quantitative methods for assessment of infants cranial malformations using 2D photos

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase I project includes use of image analysis to provide decision support to parents, clinicians and caregivers in various pediatric health conditions. In a recent survey in 2016, 79% of mothers were interested in trying or learning about telemedicine for non-emergency medical issues and 40% of those owning smartphones have downloaded at least one health or wellness app. Given the current growth potential of mHealth and its high acceptance by parents, a mobile app is perfectly situated to bridge the gap in pediatric care. In this project image analysis will be used to enable real-time decision support, customized recommendations, and low cost scaling up of the technology. The current focus of the project is on characterizing infant head malformations, more specifically flat head syndrome. Even though flat head syndrome is a common condition among infants, there is little awareness among parents about this condition and other health conditions closely related, e.g. torticollis, and developmental delay. Through early identification and patient-specific repositioning recommendations, the proposed technology will significantly lower the number of severe cases that need intensive therapies, and the associated diagnostic and treatment costs. This Small Business Innovation Research (SBIR) Phase I project aims to develop algorithms and tools that accurately calculate head shape parameters used in diagnosis and treatment planning for flat head syndrome. Moderate to severe flat head syndrome affects 20-30% of infants in the first few months after birth. If left untreated, it can cause physical and psychological discomfort, and developmental delays. A customized app will acquire photos of the infant's head, assess the shape of the head, and then recommend infant-specific re-positioning instructions. The app will follow up with parents on a regular basis to ensure compliance and therapeutic progress through monitoring. The information will also be sent to the infant's electronic health records for review by the infant's pediatrician. The developed algorithms will also differentiate between flat head syndrome and craniosynostosis, a condition that may cause similar head malformations, but can lead to more serious and permanent health complications including damage to the brain. In addition, the longitudinal dataset, collected by parents through the app, can be used to generate an infant's head growth patterns, and thus monitor development and enable early identification of the infant's risk of other health conditions. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.