Understanding the developing brain anatomy using MRI
Associate Professor of Research Radiology
University of Southern California
Abstract
Our laboratory, the Computational Imaging of Brain Organization Research Lab (CIBORG) specializes in designing computational methods for
analysis of brain anatomy and function through magnetic resonance imaging
(MRI). These methods are applied to furthering our understanding of
different neurological disorders, as well as normal and abnormal brain
development. We span all ages from before birth at the fetal stages to
elderly adults and every age in between, and in particular, we have been
studying the development of healthy term born and premature brains.
My presentation will cover three topics. First, I will discuss some of the
MRI computational analysis tools that we designed to understand the brain
anatomy of newborns and infants, such as tools for cortical, subcortical
and ventricular morphometry and white matter tract analyses in these
populations. Secondly, I will give some results of our analyses of early
development of brain subcortical structures, the ventricular systems and
white matter networks in preterm vs. healthy term born neonates. Thirdly,
being able to characterize normal brain development and detect abnormal
development during early infancy is of great importance in order to
understand, detect, prevent, or treat neurodevelopmental and
neurodegenerative pathologies as early as possible – before permanent
damage occurs. Hence, we have been studying normally developing term born
infants as a means to understand normal brain growth and of detecting
abnormal patterns of neurodevelopment.
Fetal MRI Analysis
Director, CASMIP Lab
CASMIP Lab: Computer-Aided Surgery and
Medical Image Processing Laboratory
Universidad Hebrea de Jerusalén
Abstract
Reliable evaluation of fetal development is essential to reduce short and long-term risks to the fetus and the mother. MRI is increasingly used to provide accurate fetal structural and functional information. However, fetal MRI diagnosis is hampered by the need to manually extract morphological measures, which requires the segmentation of the fetal envelope. Manual delineation of complex structures, e.g., the fetal envelope is a tedious, error-prone, and time-consuming task. Automatic segmentation often requires expert corrections. Interactive methods are best suited for complex structures since they allow slice-by-slice segmentation validation and correction.We have developed a new method for the interactive segmentation of volumetric medical images based on real-time fine-tuning of a Fully Convolutional Network (FCN).
Análisis computacional del electrocardiograma fetal antenatal
Ramón González Camarena, Juan Carlos Echeverría Arjonilla y Mercedes Jatziri Gaitán González
Unidad Iztapalapa de la Universidad Autónoma Metropolitana
Abstract
El análisis computacional del electrocardiograma (ECG) en obstetricia y perinatología favorece, en términos cuantitativos, la evaluación clínica de las condiciones de bienestar maternas y fetales. A partir de este tipo de análisis es posible obtener información acerca de la morfología del ECG o de la dinámica de las fluctuaciones temporales del ECG, reconocidas como una manifestación de los mecanismos de regulación o control fisiológico.
En esta ponencia se describirán diversos trabajos que se han desarrollado o que están en curso en la Unidad Iztapalapa de la Universidad Autónoma Metropolitana, en colaboración con el Instituto Nacional de Perinatología, relacionados específicamente con el procesamiento y modelado del ECG fetal antenatal obtenido a partir del ECG abdominal.