论文标题
3D医疗图像重建和分割的有效折叠注意力
Efficient Folded Attention for 3D Medical Image Reconstruction and Segmentation
论文作者
论文摘要
最近，已经开发了基于深度神经网络的3D医学图像重建（MIR）和细分（MIS），并取得了令人鼓舞的结果，并且已进一步设计了注意机制，以捕获全球上下文信息以提高性能。但是，大尺寸的3D音量图像对传统注意方法构成了巨大的计算挑战。在本文中，我们提出了一种折叠的注意（FA）方法，以提高3D医学图像上传统注意方法的计算效率。主要的想法是，我们应用张量折叠和展开的操作，并使用四个排列进行构建四个小附近矩阵，以近似原始的亲和力矩阵。通过FA的四个连续的亚科模块，功能张量中的每个元素都可以从所有其他元素中汇总空间通道信息。与传统的注意方法相比，随着准确性的适度提高，FA可以大大降低计算复杂性和GPU记忆消耗。我们证明了我们方法对3D miR和MIS的两个具有挑战性的任务的优越性，这是定量敏感性映射和多发性硬化病变细分。
Recently, 3D medical image reconstruction (MIR) and segmentation (MIS) based on deep neural networks have been developed with promising results, and attention mechanism has been further designed to capture global contextual information for performance enhancement. However, the large size of 3D volume images poses a great computational challenge to traditional attention methods. In this paper, we propose a folded attention (FA) approach to improve the computational efficiency of traditional attention methods on 3D medical images. The main idea is that we apply tensor folding and unfolding operations with four permutations to build four small sub-affinity matrices to approximate the original affinity matrix. Through four consecutive sub-attention modules of FA, each element in the feature tensor can aggregate spatial-channel information from all other elements. Compared to traditional attention methods, with moderate improvement of accuracy, FA can substantially reduce the computational complexity and GPU memory consumption. We demonstrate the superiority of our method on two challenging tasks for 3D MIR and MIS, which are quantitative susceptibility mapping and multiple sclerosis lesion segmentation.
