[论文解读] When Unseen Domain Generalization is Unnecessary? Rethinking Data Augmentation

Ling Zhang, Xiaosong Wang+8 more|arXiv (Cornell University)|Jun 7, 2019

Domain Adaptation and Few-Shot Learning参考文献 13被引用 39

一句话总结

该论文提出用于3D医学图像分割的深度堆叠变换（DST）增强，以提升对未见域的泛化能力，结果显示DST优于传统增强和基于CycleGAN的域适应，并且在大量源数据下可达到有监督的state-of-the-art。

ABSTRACT

Recent advances in deep learning for medical image segmentation demonstrate expert-level accuracy. However, in clinically realistic environments, such methods have marginal performance due to differences in image domains, including different imaging protocols, device vendors and patient populations. Here we consider the problem of domain generalization, when a model is trained once, and its performance generalizes to unseen domains. Intuitively, within a specific medical imaging modality the domain differences are smaller relative to natural images domain variability. We rethink data augmentation for medical 3D images and propose a deep stacked transformations (DST) approach for domain generalization. Specifically, a series of n stacked transformations are applied to each image in each mini-batch during network training to account for the contribution of domain-specific shifts in medical images. We comprehensively evaluate our method on three tasks: segmentation of whole prostate from 3D MRI, left atrial from 3D MRI, and left ventricle from 3D ultrasound. We demonstrate that when trained on a small source dataset, (i) on average, DST models on unseen datasets degrade only by 11% (Dice score change), compared to the conventional augmentation (degrading 39%) and CycleGAN-based domain adaptation method (degrading 25%); (ii) when evaluation on the same domain, DST is also better albeit only marginally. (iii) When training on large-sized data, DST on unseen domains reaches performance of state-of-the-art fully supervised models. These findings establish a strong benchmark for the study of domain generalization in medical imaging, and can be generalized to the design of robust deep segmentation models for clinical deployment.

研究动机与目标

• 由于协议、供应商和人群差异所引发的医学影像领域泛化挑战的动机。
• 提出一个系统性的增强方法（DST），通过在图像空间堆叠变换来模拟域转变。
• 在三个3D分割任务上评估DST，以量化未见域泛化收益。
• 证明在较大的源数据集下，DST接近或达到最先进的有监督性能。

提出的方法

• 对每个训练图像应用一系列九个堆叠的图像空间变换，每个变换具有两个超参数（概率和幅度）。
• 使用3D分割骨干网络（AH-Net），进行等距重采样和Dice损失优化。
• 在三个任务（前列腺MRI、左心房MRI、左心室超声）上评估对未见域的泛化，使用多个公开数据集。
• 将DST与单一增强、前四名的增强组合以及基于CycleGAN的域适应进行比较。
• 在更大数据设置下，基于一个465-volume MRI数据集进行训练，以评估DST相对于有监督方法的性能。

实验结果

研究问题

• RQ1 深度堆叠变换增强是否能提升3D医学图像分割的无监督域泛化？
• RQ2 DST与传统增强及CycleGAN域适应在未见域上的表现有何差异？
• RQ3 在更大的训练数据下，DST是否能接近最先进的有监督性能？
• RQ4 DST中的哪些增强对MRI和超声任务的泛化贡献最大？

主要发现

• DST显著提升未见域的泛化能力，未见域上平均Dice为80%，相比基线49.8%和CycleGAN的63.5%。
• 在3D MRI中，锐化、对比度、亮度和强度扰动驱动主要收益；空间变换因任务而异。
• DST优于单独增强和前四名组合，说明需要一个全面的增强集合。
• 在更大的训练数据（465体积）下，DST在未见域的Dice结果达到接近最先进有监督方法的0.8%以内。
• 在ProstateX未见数据集上，DST的Dice为91.9%，与本研究中的放射科医师一致性基线相符。