Attention gated networks: Learning to leverage salient regions in medical images.
Attention gated networks: Learning to leverage salient regions in medical images.
复制标题
DOI：
10.1016/j.media.2019.01.012
复制
发表时间：
2019-04
影响因子：
10.9
通讯作者：
Rueckert D
中科院分区：
文献类型：
--
作者：
Schlemper J;Oktay O;Schaap M;Heinrich M;Kainz B;Glocker B;Rueckert D
提出了一种用于医学图像分析的注意力门（AG）模型，该模型可以自动学习关注不同形状和大小的目标结构。用AGs训练的模型隐式学习抑制输入图像中的不相关区域，同时突出显示对特定任务有用的显著特征。这使我们能够在使用卷积神经网络（cnn）时消除使用显式外部组织/器官定位模块的必要性。AGs可以很容易地集成到标准CNN模型中，如VGG或U-Net架构，计算开销最小，同时提高模型灵敏度和预测精度。提出的AG模型在各种任务上进行了评估，包括医学图像分类和分割。对于分类，我们展示了AGs在胎儿超声筛查的扫描平面检测中的使用案例。我们表明，所提出的注意机制可以提供有效的目标定位，同时通过减少误报来提高整体预测性能。对于分割，我们在两个大型3D CT腹部数据集上进行了评估，并对多个器官进行了手动注释。实验结果表明，AG模型在保持计算效率的同时，能够在不同的数据集和训练规模下持续提高基础架构的预测性能。此外，AGs引导模型激活集中在突出区域周围，这为如何进行模型预测提供了更好的见解。建议的AG模型的源代码是公开的。
We propose a novel attention gate (AG) model for medical image analysis that automatically learns to focus on target structures of varying shapes and sizes. Models trained with AGs implicitly learn to suppress irrelevant regions in an input image while highlighting salient features useful for a specific task. This enables us to eliminate the necessity of using explicit external tissue/organ localisation modules when using convolutional neural networks (CNNs). AGs can be easily integrated into standard CNN models such as VGG or U-Net architectures with minimal computational overhead while increasing the model sensitivity and prediction accuracy. The proposed AG models are evaluated on a variety of tasks, including medical image classification and segmentation. For classification, we demonstrate the use case of AGs in scan plane detection for fetal ultrasound screening. We show that the proposed attention mechanism can provide efficient object localisation while improving the overall prediction performance by reducing false positives. For segmentation, the proposed architecture is evaluated on two large 3D CT abdominal datasets with manual annotations for multiple organs. Experimental results show that AG models consistently improve the prediction performance of the base architectures across different datasets and training sizes while preserving computational efficiency. Moreover, AGs guide the model activations to be focused around salient regions, which provides better insights into how model predictions are made. The source code for the proposed AG models is publicly available.