Related Experiment Video
Updated: Jun 6, 2026
08:49
Whole-Brain Single-Cell Imaging and Analysis of Intact Neonatal Mouse Brains Using MRI, Tissue Clearing, and Light-Sheet Microscopy
Published on: August 1, 2022
Brain volume segmentation in newborn infants using multi-modal MRI with a low inter-slice resolution.
Ivana Despotovic1, Ewout Vansteenkiste, Wilfried Philips
1Faculty of Electrical Engineering, Ghent University, TELIN-IPI-IBBT, Sint-Pietersnieuwstraat 41, 9000, Belgium. ivana.despotovic@telin.ugent.be
Summary
This study presents a novel algorithm for segmenting neonatal brain volumes from MRI scans. The method accurately reconstructs 3D brain models, aiding in the study of early brain development and disorders.
Area of Science:
- Medical imaging
- Neuroscience
- Computational anatomy
Background:
- Neonatal brain volume segmentation from MRI is crucial for understanding development and detecting disorders.
- Existing segmentation techniques, often designed for adults, are inadequate for the unique challenges of neonatal brains, such as rapid growth and poor image quality.
- Accurate segmentation is essential for quantitative analysis and 3D reconstruction of the developing neonatal brain.
Purpose of the Study:
- To develop and validate an effective algorithm for brain volume segmentation in neonates using T1-weighted and T2-weighted MRI.
- To address the limitations of existing adult-focused segmentation methods when applied to neonatal neuroimaging.
- To enable precise 3D brain reconstruction and facilitate the study of early brain development and potential abnormalities.
Main Methods:
- The proposed algorithm integrates intensity and edge information for robust segmentation.
- It involves three main stages: image pre-processing, core brain segmentation, and 3D brain reconstruction.
- The method is specifically designed to handle low inter-slice resolution in neonatal MRI data.
Main Results:
- The algorithm demonstrated performance comparable to manual segmentation on real neonatal brain MRI datasets (gestational age 39-41 weeks).
- Experimental results confirmed the method's effectiveness and superior accuracy compared to adult-based segmentation techniques.
- The segmentation approach successfully generated accurate 3D reconstructions of neonatal brain volumes.
Conclusions:
- The developed algorithm provides an accurate and effective solution for neonatal brain volume segmentation from MRI.
- This method overcomes the limitations of existing techniques, offering a valuable tool for neonatal neuroimaging research and clinical applications.
- The improved segmentation accuracy facilitates better analysis of brain growth, developmental changes, and early detection of neurological disorders in neonates.
