Large-kernel Attention for Efficient and Robust Brain Lesion Segmentation
This work addresses brain lesion segmentation for medical imaging applications, representing an incremental improvement by combining CNN and transformer advantages.
The authors tackled the problem of brain lesion segmentation by proposing an all-convolutional transformer block variant of U-Net, achieving performance competitive with state-of-the-art models while maintaining parameter efficiency and transformer inductive biases.
Vision transformers are effective deep learning models for vision tasks, including medical image segmentation. However, they lack efficiency and translational invariance, unlike convolutional neural networks (CNNs). To model long-range interactions in 3D brain lesion segmentation, we propose an all-convolutional transformer block variant of the U-Net architecture. We demonstrate that our model provides the greatest compromise in three factors: performance competitive with the state-of-the-art; parameter efficiency of a CNN; and the favourable inductive biases of a transformer. Our public implementation is available at https://github.com/liamchalcroft/MDUNet .