TABSurfer: a Hybrid Deep Learning Architecture for Subcortical Segmentation
This provides a faster and more accurate tool for researchers and clinicians analyzing large brain MRI datasets, though it is incremental as it builds on existing deep learning methods.
The authors tackled the problem of automated subcortical segmentation in brain MRI scans by proposing TABSurfer, a hybrid deep learning model that outperformed existing tools like FreeSurfer and FastSurferVINN with significantly shorter processing times and higher accuracy against manual ground truth.
Subcortical segmentation remains challenging despite its important applications in quantitative structural analysis of brain MRI scans. The most accurate method, manual segmentation, is highly labor intensive, so automated tools like FreeSurfer have been adopted to handle this task. However, these traditional pipelines are slow and inefficient for processing large datasets. In this study, we propose TABSurfer, a novel 3D patch-based CNN-Transformer hybrid deep learning model designed for superior subcortical segmentation compared to existing state-of-the-art tools. To evaluate, we first demonstrate TABSurfer's consistent performance across various T1w MRI datasets with significantly shorter processing times compared to FreeSurfer. Then, we validate against manual segmentations, where TABSurfer outperforms FreeSurfer based on the manual ground truth. In each test, we also establish TABSurfer's advantage over a leading deep learning benchmark, FastSurferVINN. Together, these studies highlight TABSurfer's utility as a powerful tool for fully automated subcortical segmentation with high fidelity.