TransLK-Net: Entangling Transformer and Large Kernel for Progressive and Collaborative Feature Encoding and Decoding in Medical Image Segmentation

TL;DR

TransLK-Net introduces a novel encoder-decoder architecture combining transformer and large kernel convolutions with attention mechanisms for improved medical image segmentation, addressing limitations of CNNs and ViTs.

Contribution

It proposes PTLK and CTLK modules that integrate multi-scale local features and global information efficiently, along with an Attention Entanglement mechanism for progressive feature enhancement.

Findings

Enhanced segmentation accuracy on medical images

Effective multi-scale feature capture and global context modeling

Reduced computational complexity compared to traditional self-attention

Abstract

Convolutional neural networks (CNNs) and vision transformers (ViTs) are widely employed for medical image segmentation, but they are still challenged by their intrinsic characteristics. CNNs are limited from capturing varying-scaled features and global contextual information due to the employment of fixed-sized kernels. In contrast, ViTs employ self-attention and MLP for global information modeling, but they lack mechanisms to learn spatial-wise local information. Additionally, self-attention leads the network to show high computational complexity. To tackle these limitations, we propose Progressively Entangled Transformer Large Kernel (PTLK) and Collaboratively Entangled Transformer Large Kernel (CTLK) modules to leverage the benefits of self-attention and large kernel convolutions and overcome shortcomings. Specifically, PTLK and CTLK modules employ the Multi-head Large Kernel to capture multi-scale local features and the Efficient Decomposed Self-attention to model global information efficiently. Subsequently, they employ the Attention Entanglement mechanism to enable local and global features to enhance and calibrate each other progressively and collaboratively. Additionally, an Attention-gated Channel MLP (AG-MLP) module is proposed to equip the standard MLP module with the capabilities of modeling spatial information. PTLK and CTLK modules are further incorporated as a Cross Entanglement Decoding (CED) block for efficient feature fusion and decoding. Finally, we propose a novel network for volumetric medical image segmentation that employs an encoder-decoder architecture, termed TransLK-Net. The encoder employs a hierarchical ViT architecture whose block is built by incorporating PTLK and CTLK with AG-MLP into a ViT block, and the decoder employs the CED block.