Related Experiment Video
Updated: Mar 27, 2026
A Standardized Pipeline for Examining Human Cerebellar Grey Matter Morphometry using Structural Magnetic Resonance Imaging
Published on: February 4, 2022
Improved segmentation of cerebellar structures in children
Priya Lakshmi Narayanan1, Christopher Warton2, Natalie Rosella Boonzaier2
1Department of Human Biology, Faculty of Health Sciences, University of Cape Town, Cape Town, South Africa; MRC/UCT Medical Imaging Research Unit, Division of Biomedical Engineering, University of Cape Town, Cape Town, South Africa.
Insights
A new pediatric cerebellar atlas (CAPCA18) improves automated segmentation of brain structures in children. This atlas offers higher accuracy than existing methods, aiding pediatric neuroimaging research.
Area of Science:
- Neuroimaging
- Pediatric Neuroanatomy
- Medical Image Analysis
Background:
- Accurate localization of the cerebellar cortex in a standard coordinate system is crucial for functional studies and morphometric analyses.
- A significant gap exists in pediatric neuroimaging due to the lack of a dedicated pediatric cerebellar atlas.
Purpose of the Study:
- To develop and validate a novel probabilistic pediatric cerebellar atlas (CAPCA18) for improved automated segmentation.
- To assess the accuracy of different automated segmentation methods using the new atlas.
Main Methods:
- Construction of the Cape Town Pediatric Cerebellar Atlas (CAPCA18) using manual tracings from 18 healthy children (9-13 years).
- Implementation of multi-atlas label fusion techniques: multi-atlas majority voting (MAMV) and multi-atlas generative model (MAGM).
- Comparison of segmentation accuracy against 'gold standard' manual tracings in 14 independent test subjects.
Main Results:
- CAPCA18 demonstrated high spatial overlap (≥73%) with manual segmentations across most cerebellar lobules.
- The multi-atlas generative model (MAGM) achieved the highest segmentation accuracy (mean Dice Similarity Coefficient 0.76).
- MAGM segmentation accuracy in children was comparable to reported adult values.
Conclusions:
- The CAPCA18 atlas significantly enhances the segmentation of cerebellar structures in pediatric populations.
- This age-appropriate atlas and its associated methods provide a valuable tool for pediatric neuroimaging research.
Background:
Consistent localization of cerebellar cortex in a standard coordinate system is important for functional studies and detection of anatomical alterations in studies of morphometry. To date, no pediatric cerebellar atlas is available.
New Method:
The probabilistic Cape Town Pediatric Cerebellar Atlas (CAPCA18) was constructed in the age-appropriate National Institute of Health Pediatric Database asymmetric template space using manual tracings of 16 cerebellar compartments in 18 healthy children (9-13 years) from Cape Town, South Africa. The individual atlases of the training subjects were also used to implement multi atlas label fusion using multi atlas majority voting (MAMV) and multi atlas generative model (MAGM) approaches. Segmentation accuracy in 14 test subjects was compared for each method to 'gold standard' manual tracings.
Results:
Spatial overlap between manual tracings and CAPCA18 automated segmentation was 73% or higher for all lobules in both hemispheres, except VIIb and X. Automated segmentation using MAGM yielded the best segmentation accuracy over all lobules (mean Dice Similarity Coefficient 0.76; range 0.55-0.91; mean Hausdorff distance 0.9 mm; range 0.8-2.7 mm).
Comparison With Existing Methods:
In all lobules, spatial overlap of CAPCA18 segmentations with manual tracings was similar or higher than those obtained with SUIT (spatially unbiased infra-tentorial template), providing additional evidence of the benefits of an age appropriate atlas. MAGM segmentation accuracy was comparable to values reported recently by Park et al. (Neuroimage 2014;95(1):217) in adults (across all lobules mean DSC=0.73, range 0.40-0.89).
Conclusions:
CAPCA18 and the associated multi-subject atlases of the training subjects yield improved segmentation of cerebellar structures in children.
