Kim Kevin,  Nowrangi Rajeev,  Mcgehee Arianna,  Joshi Neil,  Acharya Patricia

Final Pr. ID: Paper #: 020

To assess whether a convolutional neural network (CNN) can be trained via transfer learning to accurately diagnose germinal matrix hemorrhage-intraventricular hemorrhage (GMH-IVH) on cranial ultrasound (CUS) by comparing its performance to that of a board-certified radiologist. Secondary endpoints will include the ability of CNN to grade GMH-IVH severity, identify GMH-IVH on MRI, and assess low-grade GMH-IVH on CUS that cannot reliably be seen by a radiologist. Read More

Authors:  Kim Kevin , Nowrangi Rajeev , Mcgehee Arianna , Joshi Neil , Acharya Patricia

Keywords:  AI, Cranial ultrasound, germinal matrix hemorrhage

Yap Justin Luke,  Concepcion Nathan David

Final Pr. ID: Poster #: EDU-008

The goal is to create an easy-to-use reference for typical appearance of the normal sulcation and gyration of the neonatal brain on ultrasound depending on the weekly age of gestation. This will be a pictorial essay of preterm and term neonates who had an unremarkable cranial ultrasound in the first week of life. Two images will be taken: (a) coronal plane depicting the foramen of Monro and third ventricle, and (b) parasagittal (level of caudothalamic groove) planes will be used as they provide the most information in terms of sulcation and gyration. They are also the easiest to reproduce with less inter-operator variability. Cranial ultrasound (CUS) remains to be the most practical and available imaging modality for evaluating the brain of a neonate. Having a reference atlas or infographic matched for gestational age is a helpful tool for screening a myriad of pathologies and will help clinicians and radiologists involved in the care of neonates monitor the development of the neurocranium. Read More

Authors:  Yap Justin Luke , Concepcion Nathan David

Keywords:  cranial ultrasound, normal sulcation and gyration