AgileFormer：用于医学图像分割的空间敏捷Transformer UNet
AgileFormer: Spatially Agile Transformer UNet for Medical Image Segmentation
AI总结：
针对现有ViT-UNet难以应对医学图像中目标外观异质的问题，提出融合可变形块嵌入、空间动态多头注意力、可变形位置编码的AgileFormer架构，在三个公开数据集分割任务上验证了有效性。
摘要：
过去几十年中，深度神经网络，尤其是卷积神经网络，已在各类医学图像分割任务中取得了当前最优性能。近来，视觉Transformer（ViT）的出现深刻改变了深度分割模型的发展格局，凭借其出色的性能与可扩展性，ViT相关研究受到越来越多的关注。但我们认为，当前基于视觉Transformer的UNet（ViT-UNet）分割模型的设计，可能无法有效应对医学图像分割任务中感兴趣目标异质的外观（例如形状和大小各异）。为解决这一挑战，我们提出一种结构化方法，为ViT-UNet引入空间动态组件，这一改造让模型能够有效捕获具有不同外观的目标对象特征。该方法通过三个核心组件实现：（1）可变形块嵌入（deformable patch embedding）；（2）空间动态多头注意力（spatially dynamic multi-head attention）；（3）可变形位置编码（deformable positional encoding）。我们将这些组件整合到一种名为AgileFormer的全新架构中，它是专为医学图像分割设计的空间敏捷ViT-UNet。我们在三个分割任务上使用公开数据集开展实验，验证了所提方法的有效性。代码可在https://github.com/sotiraslab/AgileFormer获取。
英文摘要：
In the past decades, deep neural networks, particularly convolutional neural networks, have achieved state-of-the-art performance in a variety of medical image segmentation tasks. Recently, the introduction of the vision transformer (ViT) has significantly altered the landscape of deep segmentation models. There has been a growing focus on ViTs, driven by their excellent performance and scalability. However, we argue that the current design of the vision transformer-based UNet (ViT-UNet) segmentation models may not effectively handle the heterogeneous appearance (e.g., varying shapes and sizes) of objects of interest in medical image segmentation tasks. To tackle this challenge, we present a structured approach to introduce spatially dynamic components to the ViT-UNet. This adaptation enables the model to effectively capture features of target objects with diverse appearances. This is achieved by three main components: \textbf{(i)} deformable patch embedding; \textbf{(ii)} spatially dynamic multi-head attention; \textbf{(iii)} deformable positional encoding. These components were integrated into a novel architecture, termed AgileFormer. AgileFormer is a spatially agile ViT-UNet designed for medical image segmentation. Experiments in three segmentation tasks using publicly available datasets demonstrated the effectiveness of the proposed method. The code is available at \href{https://github.com/sotiraslab/AgileFormer}{https://github.com/sotiraslab/AgileFormer}.
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。
