Brain Surface Reconstruction from MRI Images Based on Segmentation Networks Applying Signed Distance Maps

TL;DR

This paper introduces a novel deep learning network for brain surface reconstruction from MRI images that integrates signed distance maps and a Laplacian loss to improve shape accuracy and surface smoothness.

Contribution

The proposed method uniquely combines signed distance fields and a Laplacian loss to enhance brain surface reconstruction accuracy in MRI segmentation.

Findings

Achieves comparable dice scores to existing methods.

Reduces Hausdorff distance and surface distance.

Produces more stable and smooth brain isosurfaces.

Abstract

Whole-brain surface extraction is an essential topic in medical imaging systems as it provides neurosurgeons with a broader view of surgical planning and abnormality detection. To solve the problem confronted in current deep learning skull stripping methods lacking prior shape information, we propose a new network architecture that incorporates knowledge of signed distance fields and introduce an additional Laplacian loss to ensure that the prediction results retain shape information. We validated our newly proposed method by conducting experiments on our brain magnetic resonance imaging dataset (111 patients). The evaluation results demonstrate that our approach achieves comparable dice scores and also reduces the Hausdorff distance and average symmetric surface distance, thus producing more stable and smooth brain isosurfaces.