改进解码器设计，提升医学图像分割精度
Optimizing Medical Image Segmentation with Advanced Decoder Design
- 采用可学习插值与注意力门控替代传统上采样和跳接
- 在两个数据集上均超越现有最优方法，显著提升细节分割能力
- 适合需要高精度分割的医学影像研究者参考
U-Net 因其简洁灵活的结构被广泛应用于医学图像分割。为应对医学任务中尺度与复杂性挑战，近年来涌现出多种 U-Net 变体，尤其是基于视觉变换器（ViT）的方法，如 Swin UNETR，受到广泛关注。然而，这些改进多集中于编码器，忽视了解码器在优化分割细节中的关键作用，导致设计失衡，限制了性能进一步提升。为此，我们系统分析了上采样方式、跳跃连接与特征提取模块等解码器组件的作用及现有方法的不足。据此提出 Swin DER（Swin UNETR Decoder Enhanced and Refined），针对性优化上述三类组件：采用名为 Onsampling 的可学习插值算法进行上采样；以空间-通道并行注意力门控（SCP AG）替代传统跳跃连接；并在解码器特征提取模块中引入可变形卷积与注意力机制。实验表明，该模型在 Synapse 和 MSD 脑肿瘤分割任务上均优于现有最先进方法。代码已开源：https://github.com/WillBeanYang/Swin-DER
原文摘要 · Abstract (English)
U-Net is widely used in medical image segmentation due to its simple and flexible architecture design. To address the challenges of scale and complexity in medical tasks, several variants of U-Net have been proposed. In particular, methods based on Vision Transformer (ViT), represented by Swin UNETR, have gained widespread attention in recent years. However, these improvements often focus on the encoder, overlooking the crucial role of the decoder in optimizing segmentation details. This design imbalance limits the potential for further enhancing segmentation performance. To address this issue, we analyze the roles of various decoder components, including upsampling method, skip connection, and feature extraction module, as well as the shortcomings of existing methods. Consequently, we propose Swin DER (i.e., Swin UNETR Decoder Enhanced and Refined) by specifically optimizing the design of these three components. Swin DER performs upsampling using learnable interpolation algorithm called offset coordinate neighborhood weighted up sampling (Onsampling) and replaces traditional skip connection with spatial-channel parallel attention gate (SCP AG). Additionally, Swin DER introduces deformable convolution along with attention mechanism in the feature extraction module of the decoder. Our model design achieves excellent results, surpassing other state-of-the-art methods on both the Synapse and the MSD brain tumor segmentation task. Code is available at: https://github.com/WillBeanYang/Swin-DER
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。