Improving Across-Dataset Brain Tissue Segmentation Using Transformer

TL;DR

This paper introduces a CNN-Transformer hybrid model for brain tissue segmentation that generalizes well across diverse MRI datasets, improving reliability and robustness in automated brain MRI analysis.

Contribution

A novel CNN-Transformer hybrid architecture specifically designed for brain tissue segmentation, demonstrating superior cross-dataset generalization in multi-site MRI data.

Findings

Achieved the highest generality across four diverse MRI datasets.

Outperformed existing methods in reliability and robustness.

Validated on datasets with different vendors, field strengths, and conditions.

Abstract

Brain tissue segmentation has demonstrated great utility in quantifying MRI data through Voxel-Based Morphometry and highlighting subtle structural changes associated with various conditions within the brain. However, manual segmentation is highly labor-intensive, and automated approaches have struggled due to properties inherent to MRI acquisition, leaving a great need for an effective segmentation tool. Despite the recent success of deep convolutional neural networks (CNNs) for brain tissue segmentation, many such solutions do not generalize well to new datasets, which is critical for a reliable solution. Transformers have demonstrated success in natural image segmentation and have recently been applied to 3D medical image segmentation tasks due to their ability to capture long-distance relationships in the input where the local receptive fields of CNNs struggle. This study introduces a novel CNN-Transformer hybrid architecture designed for brain tissue segmentation. We validate our model's performance across four multi-site T1w MRI datasets, covering different vendors, field strengths, scan parameters, time points, and neuropsychiatric conditions. In all situations, our model achieved the greatest generality and reliability. Out method is inherently robust and can serve as a valuable tool for brain-related T1w MRI studies. The code for the TABS network is available at: https://github.com/raovish6/TABS.