Ensemble Learning with Residual Transformer for Brain Tumor Segmentation

TL;DR

This paper introduces a novel ensemble learning approach combining residual transformers with a self-adaptive U-Net architecture for improved 3D brain tumor segmentation, achieving state-of-the-art results on BraTS 2021.

Contribution

It proposes a new network architecture integrating Transformers into U-Net with residual connections and ensemble methods for enhanced segmentation accuracy.

Findings

Achieved 87.6% mean Dice score on BraTS 2021 dataset.

Outperformed existing state-of-the-art methods.

Demonstrated effectiveness of combining multiple architectures.

Abstract

Brain tumor segmentation is an active research area due to the difficulty in delineating highly complex shaped and textured tumors as well as the failure of the commonly used U-Net architectures. The combination of different neural architectures is among the mainstream research recently, particularly the combination of U-Net with Transformers because of their innate attention mechanism and pixel-wise labeling. Different from previous efforts, this paper proposes a novel network architecture that integrates Transformers into a self-adaptive U-Net to draw out 3D volumetric contexts with reasonable computational costs. We further add a residual connection to prevent degradation in information flow and explore ensemble methods, as the evaluated models have edges on different cases and sub-regions. On the BraTS 2021 dataset (3D), our model achieves 87.6% mean Dice score and outperforms the state-of-the-art methods, demonstrating the potential for combining multiple architectures to optimize brain tumor segmentation.