FastSurfer-CC: A robust, accurate, and comprehensive framework for corpus callosum morphometry

TL;DR

FastSurfer-CC presents a robust, automated framework for comprehensive corpus callosum morphometry by integrating mid-sagittal plane positioning, AC/PC localization, CC and fornix segmentation, thickness profiling, and a shape-aware sub-segmentation scheme. It leverages a combination of registration-based plane finding, DenseNet AC/PC localization, and a VINN-based segmentation network to deliver accurate, sub-voxel morphometrics with rapid processing times (<10s on typical hardware). The study demonstrates superior accuracy and robustness across components versus state-of-the-art tools, and shows markedly increased sensitivity in Huntington's disease group analyses, uncovering substantial thickness differences and additional metrics (volume, perimeter, circularity, intercallosal length) that CCSeg misses. By providing an open-source, end-to-end pipeline, FastSurfer-CC offers a practical, scalable solution for aging and neurological disease research, enabling precise CC morphometry in large-scale studies and clinical trials.

Abstract

The corpus callosum, the largest commissural structure in the human brain, is a central focus in research on aging and neurological diseases. It is also a critical target for interventions such as deep brain stimulation and serves as an important biomarker in clinical trials, including those investigating remyelination therapies. Despite extensive research on corpus callosum segmentation, few publicly available tools provide a comprehensive and automated analysis pipeline. To address this gap, we present FastSurfer-CC, an efficient and fully automated framework for corpus callosum morphometry. FastSurfer-CC automatically identifies mid-sagittal slices, segments the corpus callosum and fornix, localizes the anterior and posterior commissures to standardize head positioning, generates thickness profiles and subdivisions, and extracts eight shape metrics for statistical analysis. We demonstrate that FastSurfer-CC outperforms existing specialized tools across the individual tasks. Moreover, our method reveals statistically significant differences between Huntington's disease patients and healthy controls that are not detected by the current state-of-the-art.

Figures (11)

• Figure 1: Thickness of an example corpus callosum, shown on a 3D surface model.
• Figure 2: Choice of mid-sagittal plane affects the shape and thickness of corpus callosum segmentation.
• Figure 3: Overview of previously proposed sub-division schemes. To the left is the anatomical anterior.
• Figure 4: Overview of the proposed pipeline for corpus callosum morphometry.
• Figure 5: Final state of thickness estimation, where the intercallosal line and thickness levelpaths are calculated on the corpus callosum mesh. The solution to the Laplace solution is shown as a gradient from yellow to red.