Year: 2025
Type: conference-paper
Abstract: Segmentation of magnetic resonance images (MRI) facilitates analysis of human brain development by delineating anatomical structures. However, in infants and young children, accurate segmentation is challenging due to development and imaging constraints. Pediatric brain MRI is notoriously difficult to acquire, with inconsistent availability of imaging modalities, substantial non-head anatomy in the field of view, and frequent motion artifacts. This has led to specialized segmentation models that are often limited to specific image types or narrow age groups, or that are fragile for more variable images such as those acquired clinically. We address this method fragmentation with BabySeg, a deep learning brain segmentation framework for infants and young children that supports diverse MRI protocols, including repeat scans and image types unavailable during training. Our approach builds on recent domain randomization techniques, which synthesize training images far beyond realistic bounds to promote dataset shift invariance. We also describe a mechanism that enables models to flexibly pool and interact features from any number of input scans. We demonstrate state-of-the-art performance that matches or exceeds the accuracy of several existing methods for various age cohorts and input configurations using a single model, in a fraction of the runtime required by many existing tools.
Authors: Malte Hoffmann, Lilla Zöllei, Adrian V. Dalca
Institution: Athinoula A. Martinos Center for Biomedical Imaging
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funders: Massachusetts General Hospital, Massachusetts Life Sciences Center, National Institutes of Health, National Institute on Aging, National Cancer Institute, National Institute of Neurological Disorders and Stroke, National Institute of Biomedical Imaging and Bioengineering, National Institute of Child Health and Human Development, National Center for Research Resources, Eunice Kennedy Shriver National Institute of Child Health and Human Development, HORIZON EUROPE Health
Awards: G2058387751, G2227408383, G393103480, G4513379049, Computeserver Structural &Functional Image Analysis, Extension of a longitudinal cognitive and brain imaging study of early-treated perinatally HIV infected children through adolescence, Deep Learning Algorithms for FreeSurfer, A Storage Area Network for Structural and Functional Image Analysis, An Acquisition and Analysis Pipeline for Integrating MRI and Neuropathology in TBI-related Dementia and VCID, Fast motion-robust fetal neuroimaging with MRI, Fast and Robust Deep Learning for Medical imaging: Segmentation and Registration methods invariant to contrast and resolution, Development of next generation 2HG and metabolic MR imaging for precision oncology of mutant IDH and wildtype glioma patients, Continuous longitudinal atlas construction for the study of brain development, Silicon Graphics Prism Extreme 128P/1TB
OpenAlex ID: W4417087279