M3Net: A multi-scale multi-view framework for multi-phase pancreas segmentation based on cross-phase non-local attention
M3Net: A multi-scale multi-view framework for multi-phase pancreas segmentation based on cross-phase non-local attention
复制标题
M3Net：基于跨阶段非局部注意力的多阶段胰腺分割的多尺度多视图框架
DOI：
10.1016/j.media.2021.102232
复制
发表时间：
2021-10-23
影响因子：
10.9
通讯作者：
Jin, Zhengyu
中科院分区：
文献类型：
--
作者：
Qu, Taiping;Wang, Xiheng;Jin, Zhengyu
ct上动脉和静脉相视觉信息的互补有助于更好地将胰腺与其周围结构区分开来。然而，在计算机辅助胰腺分割中，交叉相位上下文信息的探索仍处于研究阶段。本文提出了一种集成多尺度多视图信息的胰腺多相分割框架M(3)Net。M(3)Net的核心是建立在一个双路径网络上的，在这个网络中，单个分支被设置为两个阶段。引入跨相交互连接桥接两个分支，以交织和整合两相互补的视觉信息。此外，我们进一步设计了两种非局部关注模块，以增强跨阶段的高级特征表示。首先，我们设计了一个位置关注模块来生成可靠的跨相位特征相关性，以抑制不对准区域。其次，使用深度关注模块捕获通道依赖关系，然后增强特征表示。实验数据包括224张切片厚度为1 mm的内部ct（106张正常，118张异常）和66张切片厚度为5 mm的外部ct（29张正常，37张异常）。我们在内部数据上的平均DSC为91.19%，在外部数据上的平均DSC为86.34%，取得了新的最先进的性能。(C) 2021 Elsevier B.V.版权所有
The complementation of arterial and venous phases visual information of CTs can help better distinguish the pancreas from its surrounding structures. However, the exploration of cross-phase contextual information is still under research in computer-aided pancreas segmentation. This paper presents M(3)Net, a framework that integrates multi-scale multi-view information for multi-phase pancreas segmentation. The core of M(3)Net is built upon a dual-path network in which individual branches are set up for two phases. Cross-phase interactive connections bridging the two branches are introduced to interleave and integrate dual-phase complementary visual information. Besides, we further devise two types of non-local attention modules to enhance the high-level feature representation across phases. First, we design a location attention module to generate cross-phase reliable feature correlations to suppress the misalignment regions. Second, the depth-wise attention module is used to capture the channel dependencies and then strengthen feature representations. The experiment data consists of 224 internal CTs (106 normal and 118 abnormal) with 1 mm slice thickness, and 66 external CTs (29 normal and 37 abnormal) with 5 mm slice thickness. We achieve new state-of-the-art performance with average DSC of 91.19% on internal data, and promising result with average DSC of 86.34% on external data. (C) 2021 Elsevier B.V. All rights reserved.