2019/11/15 by Kelly Payette, Ueli Moehrlen, Payette, Kelly +12
Medicine · Neuroscience · #Cerebrospinal fluid and hydrocephalus #FOS: Electrical engineering #Fetal and Pediatric Neurological Disorders #Image and Video Processing (eess.IV) #Prenatal Screening and Diagnostics #Spinal Dysraphism and Malformations #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1911.06542
openalex publication_date 2019/11/15 · openalex created_date 2022/07/26 · openalex updated_date 2026/07/28
Open spina bifida (SB) is one of the most common congenital defects and can\nlead to impaired brain development. Emerging fetal surgery methods have shown\nconsiderable success in the treatment of patients with this severe anomaly.\nAfterwards, alterations in the brain development of these fetuses have been\nobserved. Currently no longitudinal studies exist to show the effect of fetal\nsurgery on brain development. In this work, we present a fetal MRI\nneuro-imaging analysis pipeline for fetuses with SB, including automated fetal\nventricle segmentation and deformation-based morphometry, and demonstrate its\napplicability with an analysis of ventricle enlargement in fetuses with SB.\nUsing a robust super-resolution algorithm, we reconstructed fetal brains at\nboth pre-operative and post-operative time points and trained a U-Net CNN in\norder to automatically segment the ventricles. We investigated the change of\nventricle shape post-operatively, and the impacts of lesion size, type, and GA\nat operation on the change in ventricle shape. No impact was found, except for\nmoderately larger ventriculomegaly progression in myeloschisis patients.\nPrenatal ventricle volume growth was also investigated. Our method allows for\nthe quantification of longitudinal morphological changes to fully quantify the\nimpact of prenatal SB repair and could be applied to predict postnatal\noutcomes.\n