G-CASCADE: Efficient Cascaded Graph Convolutional Decoding for 2D Medical Image Segmentation

TL;DR

G-CASCADE introduces a novel graph convolutional decoder that enhances 2D medical image segmentation by refining multi-stage features with global receptive fields, outperforming existing methods in accuracy and efficiency.

Contribution

The paper proposes G-CASCADE, a new graph convolution-based decoder that improves segmentation accuracy and efficiency for medical images, compatible with hierarchical transformer encoders.

Findings

Outperforms state-of-the-art methods on five medical segmentation tasks.

Achieves higher DICE scores with significantly fewer parameters and FLOPs.

Compatible with various hierarchical encoders for general segmentation tasks.

Abstract

In recent years, medical image segmentation has become an important application in the field of computer-aided diagnosis. In this paper, we are the first to propose a new graph convolution-based decoder namely, Cascaded Graph Convolutional Attention Decoder (G-CASCADE), for 2D medical image segmentation. G-CASCADE progressively refines multi-stage feature maps generated by hierarchical transformer encoders with an efficient graph convolution block. The encoder utilizes the self-attention mechanism to capture long-range dependencies, while the decoder refines the feature maps preserving long-range information due to the global receptive fields of the graph convolution block. Rigorous evaluations of our decoder with multiple transformer encoders on five medical image segmentation tasks (i.e., Abdomen organs, Cardiac organs, Polyp lesions, Skin lesions, and Retinal vessels) show that our model outperforms other state-of-the-art (SOTA) methods. We also demonstrate that our decoder achieves better DICE scores than the SOTA CASCADE decoder with 80.8% fewer parameters and 82.3% fewer FLOPs. Our decoder can easily be used with other hierarchical encoders for general-purpose semantic and medical image segmentation tasks.