[论文解读] PGL: Prior-Guided Local Self-supervised Learning for 3D Medical Image Segmentation

Yutong Xie, Jianpeng Zhang+3 more|arXiv (Cornell University)|Nov 25, 2020

Advanced Neural Network Applications参考文献 40被引用 35

一句话总结

PGL 引入了一个先验引导的局部自监督学习框架，用于学习三维医学影像中的区域级表示，在使用有限标注进行微调时提升下游分割性能。

ABSTRACT

It has been widely recognized that the success of deep learning in image segmentation relies overwhelmingly on a myriad amount of densely annotated training data, which, however, are difficult to obtain due to the tremendous labor and expertise required, particularly for annotating 3D medical images. Although self-supervised learning (SSL) has shown great potential to address this issue, most SSL approaches focus only on image-level global consistency, but ignore the local consistency which plays a pivotal role in capturing structural information for dense prediction tasks such as segmentation. In this paper, we propose a PriorGuided Local (PGL) self-supervised model that learns the region-wise local consistency in the latent feature space. Specifically, we use the spatial transformations, which produce different augmented views of the same image, as a prior to deduce the location relation between two views, which is then used to align the feature maps of the same local region but being extracted on two views. Next, we construct a local consistency loss to minimize the voxel-wise discrepancy between the aligned feature maps. Thus, our PGL model learns the distinctive representations of local regions, and hence is able to retain structural information. This ability is conducive to downstream segmentation tasks. We conducted an extensive evaluation on four public computerized tomography (CT) datasets that cover 11 kinds of major human organs and two tumors. The results indicate that using pre-trained PGL model to initialize a downstream network leads to a substantial performance improvement over both random initialization and the initialization with global consistency-based models. Code and pre-trained weights will be made available at: https://git.io/PGL.

研究动机与目标

• 通过减少对密集标注数据的依赖，推动注释高效的3D医学影像分割。
• 开发一种自监督方法，捕捉局部、区域级的结构信息，而不仅仅是全局特征的一致性。
• 利用空间变换先验在增强视图之间对齐局部特征。
• 在跨器官和肿瘤的多个公开CT数据集上评估PGL，以评估其可迁移性和鲁棒性。

提出的方法

• 使用数据增强模块为每个3D图像生成两个增强视图。
• 引入一个先验引导的双路径架构，包含在线网络和目标网络，以学习局部特征对齐。
• 用局部结构感知的投影器和先验引导的对齐器替换传统的全局投影器。
• 结合裁剪/缩放和翻转先验，通过在3D空间中的RoIAlign对齐来自相应局部区域的特征。
• 定义局部一致性损失，最小化来自两个视图的对齐局部特征的体素级差异（在线路径上有一个预测器）。
• 通过指数移动平均更新目标网络权重，以提供稳定的目标信号（BYOL 风格）。

实验结果

研究问题

• RQ1 局部、先验引导的自监督学习能否捕捉有益于3D医学影像分割的区域级结构信息？
• RQ2 空间变换先验（裁剪/缩放和翻转）是否比全局SSL方法改善局部表征的质量？
• RQ3 在标注有限的多样化CT数据集上，PGL预训练对下游分割性能有何影响？

主要发现

• PGL 预训练在四个CT数据集（肝脏、脾脏、KiTS、BCV）上始终优于随机初始化的下游分割。
• PGL 相对于随机初始化的平均 Dice 增益：肝脏 +2.08，脾脏 +2.37，KiTS +2.72，BCV +2.20。
• PGL 在作为预训练策略时优于 Models Genesis 和 BYOL，其中 BYOL 为最强的全局SSL基线，PGL 实现更高的平均 Dice 增益（例如，平均比 BYOL 高出 +1.23%）。
• 裁剪/缩放和翻转先验的联合使用产生最佳分割性能，消融实验显示在移除任一或两者先验时性能下降。
• 该方法对有限标注具有鲁棒性，在下游带标签数据稀缺时提供更大的增益。