Neuro-TransUNet: Segmentation of stroke lesion in MRI using transformers

TL;DR

Neuro-TransUNet is a novel deep learning framework that combines U-Net and SwinUNETR architectures with advanced data processing to improve stroke lesion segmentation in MRI, outperforming existing methods.

Contribution

The paper introduces Neuro-TransUNet, a new model that integrates spatial and global features for MRI stroke lesion segmentation, along with a comprehensive data pre-processing pipeline.

Findings

Outperforms existing deep learning algorithms in stroke lesion segmentation

Establishes a new benchmark on the ATLAS v2.0 dataset

Ablation studies confirm the effectiveness of the integrated approach

Abstract

Accurate segmentation of the stroke lesions using magnetic resonance imaging (MRI) is associated with difficulties due to the complicated anatomy of the brain and the different properties of the lesions. This study introduces the Neuro-TransUNet framework, which synergizes the U-Net's spatial feature extraction with SwinUNETR's global contextual processing ability, further enhanced by advanced feature fusion and segmentation synthesis techniques. The comprehensive data pre-processing pipeline improves the framework's efficiency, which involves resampling, bias correction, and data standardization, enhancing data quality and consistency. Ablation studies confirm the significant impact of the advanced integration of U-Net with SwinUNETR and data pre-processing pipelines on performance and demonstrate the model's effectiveness. The proposed Neuro-TransUNet model, trained with the ATLAS v2.0 \emph{training} dataset, outperforms existing deep learning algorithms and establishes a new benchmark in stroke lesion segmentation.