Comparison of different segmentation algorithms on brain volume and fractal dimension in infant brain MRIs

TL;DR

This study compares segmentation algorithms on infant brain MRIs, showing SynthSeg's superior accuracy and its impact on volume and fractal dimension estimates, highlighting the importance of segmentation quality in developmental neuroimaging.

Contribution

It provides a systematic comparison of segmentation algorithms on infant brain MRI, emphasizing SynthSeg's improved performance and its effects on volumetric and fractal dimension measurements.

Findings

SynthSeg outperformed SamSeg in segmentation accuracy.

Segmentation accuracy increased with age due to better tissue contrast.

Segmentation bias significantly affects fractal dimension estimates.

Abstract

Accurate segmentation of infant brain MRI is essential for quantifying developmental changes in structure and complexity. However, ongoing myelination and reduced tissue contrast make automated segmentation particularly challenging. This study systematically compared segmentation accuracy and its impact on volumetric and fractal dimension (FD) estimates in infant brain MRI using the Baby Open Brains (BOB) dataset (71 scans, 1-9 months). Two methods, SynthSeg and SamSeg, were evaluated against expert annotations using Dice, Intersection over Union, 95th-percentile Hausdorff distance, and Normalised Mutual Information. SynthSeg outperformed SamSeg across all quality metrics (mean Dice > 0.8 for major regions) and provided volumetric estimates closely matching the manual reference (mean +4% [-28% - 71%]). SamSeg systematically overestimated ventricular and whole-brain volumes (mean +76% [-12% - 190%]). Segmentation accuracy improved with age, consistent with increasing tissue contrast during myelination. Fractal dimension a(FD) nalyses revealed significant regional differences between SynthSeg and expert segmentations, and Bland-Altman limits of agreement indicated that segmentation-related FD variability exceeded most group differences reported in developmental cohorts. Volume and FD deviations were positively correlated across structures, indicating that segmentation bias directly affects FD estimation. Overall, SynthSeg provided the most reliable volumetric and FD results for paediatric MRI, yet small morphological differences in volume and FD should be interpreted with caution due to segmentation-related uncertainty.