Ensemble Learning with Residual Transformer for Brain Tumor Segmentation
This work addresses the problem of accurately segmenting complex brain tumors for medical imaging applications, representing an incremental improvement through architectural combination.
The paper tackled brain tumor segmentation by proposing a novel network architecture that integrates Transformers into a self-adaptive U-Net with residual connections and ensemble methods, achieving an 87.6% mean Dice score on the BraTS 2021 dataset and outperforming state-of-the-art methods.
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.