Related Experiment Video
Updated: Jul 1, 2025
Patient-Specific Polyvinyl Alcohol Phantom Fabrication with Ultrasound and X-Ray Contrast for Brain Tumor Surgery Planning
Published on: July 14, 2020
BOOSTING SKULL-STRIPPING PERFORMANCE FOR PEDIATRIC BRAIN IMAGES
William Kelley1,2, Nathan Ngo1,2, Adrian V Dalca1,2,3,4
1Athinoula A. Martinos Center for Biomedical Imaging, Charlestown, MA 02129, USA.
Insights
Pediatric skull-stripping tools are needed for brain development research. Developmental SynthStrip (d-SynthStrip) offers a robust, fast solution outperforming existing methods for analyzing pediatric brain images.
Area of Science:
- Neuroimaging
- Medical Image Analysis
- Pediatric Neuroscience
Background:
- Skull-stripping is crucial for analyzing brain images, but adult-specific tools fail with pediatric data due to developmental variations and image artifacts.
- Existing tools are inadequate for the unique challenges of pediatric neuroimaging, hindering large-scale studies of brain development.
Approach:
- Developed developmental SynthStrip (d-SynthStrip), a novel skull-stripping model specifically for pediatric brain images.
- Utilized a framework exposing neural networks to synthesized, highly variable images derived from label maps to enhance robustness.
Key Points:
- d-SynthStrip significantly outperforms existing pediatric skull-stripping methods across various scan types and age groups.
- The model achieves a runtime of under one minute, making it highly efficient for processing large datasets.
- The tool demonstrates superior accuracy and robustness in handling the complexities of developing brains.
Conclusions:
- d-SynthStrip provides a well-tested, efficient, and accurate solution for pediatric skull-stripping.
- This advancement supports multi-institutional efforts to understand perinatal brain development through improved data processing.
- The d-SynthStrip model is publicly available for research use.
Abstract:
Skull-stripping is the removal of background and non-brain anatomical features from brain images. While many skull-stripping tools exist, few target pediatric populations. With the emergence of multi-institutional pediatric data acquisition efforts to broaden the understanding of perinatal brain development, it is essential to develop robust and well-tested tools ready for the relevant data processing. However, the broad range of neuroanatomical variation in the developing brain, combined with additional challenges such as high motion levels, as well as shoulder and chest signal in the images, leaves many adult-specific tools ill-suited for pediatric skull-stripping. Building on an existing framework for robust and accurate skull-stripping, we propose developmental SynthStrip (d-SynthStrip), a skull-stripping model tailored to pediatric images. This framework exposes networks to highly variable images synthesized from label maps. Our model substantially outperforms pediatric baselines across scan types and age cohorts. In addition, the <1-minute runtime of our tool compares favorably to the fastest baselines. We distribute our model at https://w3id.org/synthstrip.
