SFB-net用混合结构提升心脏图像分割精度，解决长距离依赖问题。
SFB-net for cardiac segmentation: Bridging the semantic gap with attention
- 结合卷积与Swin Transformer，分层引入空间与语义注意力
- ACDC数据集平均Dice达92.4，优于现有方法；M&M's上达87.99
- 适合需高精度分割的医学影像研究者，尤其关注跨中心泛化
近年来，深度学习广泛应用于心脏图像分割。然而，多数架构依赖卷积，难以建模长程依赖，限制了上下文信息提取。本文提出Swin Filtering Block网络（SFB-net），融合传统卷积层与Swin Transformer层：前者在网络底层引入空间注意力，后者用于编码器与解码器间聚焦高层语义特征。在ACDC数据集上平均Dice分数达92.4，据我们所知为当前最优结果；在来自不同厂商和中心的M&M's数据集上，平均Dice分数为87.99，表明该方法具有良好的跨域泛化能力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。