Skull stripping tools in pediatric T2-weighted MRI scans: a retrospective evaluation of segmentation performance
Adrian Schulz1, Eric Dragendorf1, Katharina Wendt1
1Peter L. Reichertz Institute for Medical Informatics of TU Braunschweig and Hannover Medical School, Hannover Medical School, Hannover, Germany.
Insights
SynthStrip is recommended for pediatric T2-weighted MRI skull stripping due to its speed and accuracy. While generally robust, it occasionally misses certain brain structures, necessitating further research into segmentation improvements.
Area of Science:
- Medical Imaging
- Neuroimaging
- Pediatric Radiology
Background:
- T2-weighted MRI scans are crucial for assessing brain maturity in infants over 6 months.
- Skull stripping is a vital preprocessing step for automated brain tissue analysis.
- Existing skull stripping tools often lack optimization for T2-weighted scans and pediatric populations.
Purpose of the Study:
- To evaluate the performance of seven common skull stripping tools on pediatric T2-weighted MRI scans.
- To compare segmentation accuracy, computation time, and robustness across different tools and preprocessing strategies.
Main Methods:
- Retrospective analysis of 199 T2-weighted MRI scans from children under 5 years.
- Manual ground truth creation with senior pediatric neuroradiologist oversight.
- Evaluation of seven skull stripping tools (BET, ROBEX, HD-BET, HD-BET-fast, SynthStrip, SynthStrip-noCSF, d-SynthStrip) based on Dice score, Hausdorff distance, sensitivity, and specificity.
Main Results:
- SynthStrip demonstrated the best overall performance with a median Dice score of 0.96.
- Preprocessing improved results for BET, HD-BET, and HD-BET-fast, but not for others.
- SynthStrip showed minor segmentation errors, particularly with superior brain structures and the optic chiasm/pituitary gland.
Conclusions:
- SynthStrip is recommended for pediatric T2-weighted MRI skull stripping due to its balance of speed and accuracy.
- Observed segmentation errors may be attributed to partial volume effects, warranting further investigation.
- Future research should address limitations such as monocentric data and the exclusion of pathological cases.
Introduction:
For brain maturity assessment of infants aged above 6 months, T2-weighted MRI scans are recommended. Prior to automated brain tissue analysis, skull stripping is typically applied. However, most skull stripping tools neither focus on T2-weighted scans nor on pediatric cohorts. Here, we present the evaluation results of seven common skull stripping tools in a comparably large pediatric cohort.
Methods:
This study is based on 199 T2-weighted scans of children under the age of 5 years retrospectively acquired from the clinical routine at Hannover Medical School. We established a manually labeled ground truth under quality control of a senior neuroradiologist specialized in pediatric neuroradiology and evaluated seven skull stripping tools (BET, ROBEX, HD-BET, HD-BET-fast, SynthStrip, SynthStrip-noCSF and d-SynthStrip). Segmentation performance (Dice score, 95th percentile Hausdorff distance, sensitivity, specificity) and computation time were assessed on non-preprocessed and preprocessed scans (zero padding, contrast enhancement, artifact removal and normalization) as well as in different brain regions. For the best performing model, we manually assessed the top and bottom quartile of segmentations with respect to the integrity of different anatomical brain structures.
Results:
Only BET, HD-BET, HD-BET-fast profited from data preprocessing. Considering this, all models had median Dice scores between 0.88 and 0.96, with SynthStrip performing best. All models segmented most accurately in the middle axial slices of the brain. Resampling lowered the performance of all models, except ROBEX. Mean computing times ranged from 2 s (BET) to 132 s (HD-BET) with SynthStrip requiring 7 s. per scan. SynthStrip was prone to not entirely including the Sinus sagittalis superior, the upper Cerebrum, the temporal pole, the Cerebellum and the Chiasma opticum/pituitary gland. In contrast, the petrous bone and the skull in the middle axial slices have often been partly included.
Discussion:
Due to its robustness and quick computation time, we recommend SynthStrip for skull stripping of pediatric T2-weighted MRI scans. We attribute the observed segmentation errors to the partial volume effect, which should be addressed in future research. Limitations of our study include the monocentric setting, the exclusion of pathological cases and the skewed age distribution in our cohort.
