Efficient Brain Extraction of MRI Scans with Mild to Moderate Neuropathology

2026-02-09

AI Summary

This study addresses the challenge of accurately delineating the brain boundary in MRI scans containing mild to moderate neuropathological abnormalities, where existing brain extraction methods often fail. To overcome this limitation, the authors propose a robust brain extraction approach based on an enhanced U-Net architecture, incorporating a novel signed distance transform (SDT) loss function. The model is trained on silver-standard annotations to consistently segment the brain surface, including sulcal cerebrospinal fluid while excluding the subarachnoid space and meninges. Evaluated on an internal test set, the method achieves a Dice coefficient of 0.964 ± 0.006 and a mean symmetric surface distance of 1.4 ± 0.2 mm; on an external dataset, it attains a Dice score of 0.958 ± 0.006, demonstrating performance that matches or exceeds current state-of-the-art techniques.

Technology Category

• Humans and AI: Brain-Sensing and Analysis
• Computer Vision: Segmentation
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Skull stripping magnetic resonance images (MRI) of the human brain is an important process in many image processing techniques, such as automatic segmentation of brain structures. Numerous methods have been developed to perform this task, however, they often fail in the presence of neuropathology and can be inconsistent in defining the boundary of the brain mask. Here, we propose a novel approach to skull strip T1-weighted images in a robust and efficient manner, aiming to consistently segment the outer surface of the brain, including the sulcal cerebrospinal fluid (CSF), while excluding the full extent of the subarachnoid space and meninges. We train a modified version of the U-net on silver-standard ground truth data using a novel loss function based on the signed-distance transform (SDT). We validate our model both qualitatively and quantitatively using held-out data from the training dataset, as well as an independent external dataset. The brain masks used for evaluation partially or fully include the subarachnoid space, which may introduce bias into the comparison; nonetheless, our model demonstrates strong performance on the held-out test data, achieving a consistent mean Dice similarity coefficient (DSC) of 0.964$\pm$0.006 and an average symmetric surface distance (ASSD) of 1.4mm$\pm$0.2mm. Performance on the external dataset is comparable, with a DSC of 0.958$\pm$0.006 and an ASSD of 1.7$\pm$0.2mm. Our method achieves performance comparable to or better than existing state-of-the-art methods for brain extraction, particularly in its highly consistent preservation of the brain's outer surface. The method is publicly available on GitHub.

Problem

• brain extraction
• skull stripping
• neuropathology
• MRI
• brain mask

Innovation

• skull stripping
• U-Net
• signed-distance transform
• brain extraction
• neuropathology