SFB-net for cardiac segmentation: Bridging the semantic gap with attention

Abstract

In the past few years, deep learning algorithms have been widely used for cardiac image segmentation. However, most of these architectures rely on convolutions that hardly model long-range dependencies, limiting their ability to extract contextual information. In order to tackle this issue, this article introduces the Swin Filtering Block network (SFB-net) which takes advantage of both conventional and swin transformer layers. The former are used to introduce spatial attention at the bottom of the network, while the latter are applied to focus on high level semantically rich features between the encoder and decoder. An average Dice score of 92.4 was achieved on the ACDC dataset. To the best of our knowledge, this result outperforms any other work on this dataset. The average Dice score of 87.99 obtained on the M\&M's dataset demonstrates that the proposed method generalizes well to data from different vendors and centres.

References in corpus (7)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Attention U-Net: Learning Where to Look for the Pancreas
• TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation
• Gaussian Error Linear Units (GELUs)
• Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation
• CoAtNet: Marrying Convolution and Attention for All Data Sizes
• nnFormer: Interleaved Transformer for Volumetric Segmentation