HBFormer：一种混合桥变压器用于微肿瘤和微型器官分割
HBFormer: A Hybrid-Bridge Transformer for Microtumor and Miniature Organ Segmentation
AI总结：
HBFormer通过混合编码器-解码器与Swin Transformer结合，提出桥机制融合多尺度特征，实现微肿瘤和微型器官的高精度分割。
摘要：
医学图像分割是现代临床诊断的基石。尽管基于移位窗口自注意力机制的视觉Transformer在该领域建立了新的基准，但它们常常受到一个关键限制的阻碍：其局部化注意力机制难以有效融合局部细节与全局上下文。这一缺陷在诸如微肿瘤和微型器官分割等具有挑战性的任务中尤为有害，其中精细边界定义和广泛上下文理解都是至关重要的。为了解决这一差距，我们提出了HBFormer，一种新的混合桥Transformer架构。HBFormer的“混合”设计将经典的U型编码器-解码器框架与强大的Swin Transformer主干相结合，以实现稳健的层次特征提取。核心创新在于其“桥”机制，这是一个复杂的多尺度特征整合枢纽。该桥通过我们新的多尺度特征融合（MFF）解码器来体现其架构。与传统对称设计不同，MFF解码器被设计成融合编码器中的多尺度特征与全局上下文信息。它通过通道和空间注意力模块的协同组合来实现这一点，这些模块由一系列扩张和深度卷积构成。这些组件协同工作，以创建一个强大的特征桥，能够明确捕捉长距离依赖关系，并以极高的精度细化对象边界。在具有挑战性的医学图像分割数据集上进行了全面实验，包括多器官、肝肿瘤和膀胱肿瘤基准测试，证明HBFormer在微肿瘤和微型器官分割中实现了最先进的结果。代码和模型可在：https://github.com/lzeeorno/HBFormer上获得。
英文摘要：
Medical image segmentation is a cornerstone of modern clinical diagnostics. While Vision Transformers that leverage shifted window-based self-attention have established new benchmarks in this field, they are often hampered by a critical limitation: their localized attention mechanism struggles to effectively fuse local details with global context. This deficiency is particularly detrimental to challenging tasks such as the segmentation of microtumors and miniature organs, where both fine-grained boundary definition and broad contextual understanding are paramount. To address this gap, we propose HBFormer, a novel Hybrid-Bridge Transformer architecture. The 'Hybrid' design of HBFormer synergizes a classic U-shaped encoder-decoder framework with a powerful Swin Transformer backbone for robust hierarchical feature extraction. The core innovation lies in its 'Bridge' mechanism, a sophisticated nexus for multi-scale feature integration. This bridge is architecturally embodied by our novel Multi-Scale Feature Fusion (MFF) decoder. Departing from conventional symmetric designs, the MFF decoder is engineered to fuse multi-scale features from the encoder with global contextual information. It achieves this through a synergistic combination of channel and spatial attention modules, which are constructed from a series of dilated and depth-wise convolutions. These components work in concert to create a powerful feature bridge that explicitly captures long-range dependencies and refines object boundaries with exceptional precision. Comprehensive experiments on challenging medical image segmentation datasets, including multi-organ, liver tumor, and bladder tumor benchmarks, demonstrate that HBFormer achieves state-of-the-art results, showcasing its outstanding capabilities in microtumor and miniature organ segmentation. Code and models are available at: https://github.com/lzeeorno/HBFormer.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
