论文标题
3D生物医学图像分割的动态线性变压器
Dynamic Linear Transformer for 3D Biomedical Image Segmentation
论文作者
论文摘要
基于变压器的神经网络由于自我发挥机制的更好的全球信息建模而超过了许多生物医学图像分割任务的有希望的表现。但是，大多数方法仍然是为2D医学图像而设计的，同时忽略了必需的3D卷信息。基于3D变压器的分割方法的主要挑战是由自我发项机制\ cite {vaswani2017发出}引入的二次复杂性。在本文中，我们建议使用具有线性复杂性的编码器模型样式体系结构提出一种用于3D医疗图像分割的新型变压器架构。此外，我们新引入了一个动态令牌概念，以进一步减少自我注意计算的令牌数字。利用全球信息建模，我们提供了来自不同层次结构阶段的不确定性图。我们在多个具有挑战性的CT胰腺细分数据集上评估了此方法。我们有希望的结果表明，我们的新型3D变压器的分段可以使用单个注释提供有希望的高度可行的分割性能和准确的不确定性定量。代码可用https://github.com/freshman97/lintransunet。
Transformer-based neural networks have surpassed promising performance on many biomedical image segmentation tasks due to a better global information modeling from the self-attention mechanism. However, most methods are still designed for 2D medical images while ignoring the essential 3D volume information. The main challenge for 3D transformer-based segmentation methods is the quadratic complexity introduced by the self-attention mechanism \cite{vaswani2017attention}. In this paper, we propose a novel transformer architecture for 3D medical image segmentation using an encoder-decoder style architecture with linear complexity. Furthermore, we newly introduce a dynamic token concept to further reduce the token numbers for self-attention calculation. Taking advantage of the global information modeling, we provide uncertainty maps from different hierarchy stages. We evaluate this method on multiple challenging CT pancreas segmentation datasets. Our promising results show that our novel 3D Transformer-based segmentor could provide promising highly feasible segmentation performance and accurate uncertainty quantification using single annotation. Code is available https://github.com/freshman97/LinTransUNet.
