Biomarkers.

Area of Science:

• Neuroimaging
• Medical Image Analysis
• Computational Neuroscience

Background:

• Manual brain segmentation is the gold standard but is time-consuming and has low inter-rater reliability.
• Automated segmentation pipelines offer faster and more reliable alternatives, but performance varies.
• QyScore® is a medical imaging platform designed for grey and white matter segmentation.

Purpose of the Study:

• To compare the performance of QyScore® against state-of-the-art segmentation pipelines: FreeSurfer, FSL, and ANTs.
• To evaluate segmentation accuracy across multiple brain regions.

Main Methods:

• 54 T1-weighted MRI images were used for segmentation.
• Segmentations were performed using QyScore® v1.13, FreeSurfer v7.4.1, FSL v6.0.6.2, and ANTs v2.5 with default parameters.
• Consensus manual segmentations by three expert neuroradiologists served as ground truth.
• Dice Similarity Coefficients (DSC) were used to compare segmentation accuracy.

Main Results:

• QyScore® achieved the highest segmentation accuracy for whole brain grey matter, white matter, brainstem, amygdala, putamen, and lateral ventricles.
• FSL performed best for hippocampal segmentation, followed closely by QyScore®.
• QyScore® and ANTs demonstrated robust preprocessing, with no errors, unlike FreeSurfer and FSL which required parameter optimization for a significant percentage of subjects.

Conclusions:

• QyScore® exhibits excellent segmentation accuracy across most brain regions, outperforming other leading pipelines.
• QyScore® and ANTs are robust, processing diverse medical images without errors.
• QyScore®'s accuracy and robustness make it valuable for clinical diagnosis and monitoring in healthcare and clinical trials.