[论文解读] DeepLesionBrain: Towards a broader deep-learning generalization for multiple sclerosis lesion segmentation

Reda Abdellah Kamraoui, Vinh‐Thong Ta+4 more|arXiv (Cornell University)|Dec 14, 2020

Digital Imaging for Blood Diseases参考文献 51被引用 73

一句话总结

DLB提出一个面向领域泛化的MS病灶分割框架，使用空间分布的3D CNNs，具备分层专业化学习、图像质量数据增强和模态高效设计（T1w+FLAIR），以提高跨数据集泛化能力。

ABSTRACT

Recently, segmentation methods based on Convolutional Neural Networks (CNNs) showed promising performance in automatic Multiple Sclerosis (MS) lesions segmentation. These techniques have even outperformed human experts in controlled evaluation conditions such as Longitudinal MS Lesion Segmentation Challenge (ISBI Challenge). However state-of-the-art approaches trained to perform well on highly-controlled datasets fail to generalize on clinical data from unseen datasets. Instead of proposing another improvement of the segmentation accuracy, we propose a novel method robust to domain shift and performing well on unseen datasets, called DeepLesionBrain (DLB). This generalization property results from three main contributions. First, DLB is based on a large group of compact 3D CNNs. This spatially distributed strategy ensures a robust prediction despite the risk of generalization failure of some individual networks. Second, DLB includes a new image quality data augmentation to reduce dependency to training data specificity (e.g., acquisition protocol). Finally, to learn a more generalizable representation of MS lesions, we propose a hierarchical specialization learning (HSL). HSL is performed by pre-training a generic network over the whole brain, before using its weights as initialization to locally specialized networks. By this end, DLB learns both generic features extracted at global image level and specific features extracted at local image level. DLB generalization was validated in cross-dataset experiments on MSSEG'16, ISBI challenge, and in-house datasets. During experiments, DLB showed higher segmentation accuracy, better segmentation consistency and greater generalization performance compared to state-of-the-art methods. Therefore, DLB offers a robust framework well-suited for clinical practice.

研究动机与目标

• 解决CNN在未见临床数据集上的MS病灶分割泛化能力差的问题。
• 提出一种在目标域标注缺失的情况下仍能保持性能的领域泛化架构。
• 通过新颖的数据增强和分层特征学习提升对采集变异的鲁棒性。

提出的方法

• 引入一大组紧凑、空间分布的3D CNN，每个CNN对脑区具有重叠的感受野并专门化。
• 在训练过程中应用Image Quality Data Augmentation (IQDA)，以模拟采集和质量变异（模糊、边缘增强、轴向下采样）。
• 采用Hierarchical Specialization Learning (HSL)：先在所有脑区上训练一个通用网络以捕捉全局特征，然后用通用权重初始化区域特定网络以实现局部专业化。
• 使用两模态输入设置（T1w和FLAIR），最大化跨数据集的兼容性，避免依赖额外序列。
• 在跨数据集的MS分割基准上训练和评估以评估领域泛化能力（ISBI、MSSEG’16、内部数据）。
• 用平滑的Generalized Jaccard Loss来解决类别不平衡问题，并通过多数投票聚合重叠区域的预测。

实验结果

研究问题

• RQ1 DeepLesionBrain是否能够在未见领域实现鲁棒的MS病灶分割而不需要目标域标注？
• RQ2 具有重叠感受野的空间分布网络相比单一网络方法是否能提升泛化能力？
• RQ3 IQDA和Hierarchical Specialization Learning是否对跨域鲁棒性和病灶检测精度有显著贡献？
• RQ4 仅使用两种MRI模态（T1w和FLAIR）在采集协议多样的数据集上是否也能实现可靠的MS病灶分割？

主要发现

• DLB在跨数据集测试中实现更高的分割准确性、一致性和泛化性能，相较于现有方法处于优势。
• 具有重叠区域的空间分布网络提供稳健的共识，在域迁移下提高稳定性。
• IQDA降低了对训练数据特定采集和质量变异的敏感性，助力领域泛化。
• HSL实现对通用全局特征和局部专用特征的有效学习，优于单网络或非HSL基线。
• DLB在保持对两种模态（T1w和FLAIR）兼容的同时，在多样数据集上仍保持稳健性能。