[论文解读] Automatic acute ischemic stroke lesion segmentation using semi-supervised learning

Bin Zhao, Shuxue Ding+5 more|arXiv (Cornell University)|Aug 10, 2019

Acute Ischemic Stroke Management参考文献 42被引用 6

一句话总结

本文提出了一种半监督深度学习框架，用于在弥散加权磁共振成像（DWI）中自动分割急性缺血性卒中（AIS）病灶，结合了弱监督双路径分类网络、DWI上的K-均值聚类以及区域生长法，仅使用15例完全标注的受试者即实现了高精度分割。该方法在临床测试集上实现了0.642的平均Dice系数和0.822的病灶级F1分数，显著降低了对昂贵专家标注的依赖。

ABSTRACT

Ischemic stroke is a common disease in the elderly population, which can cause long-term disability and even death. However, the time window for treatment of ischemic stroke in its acute stage is very short. To fast localize and quantitively evaluate the acute ischemic stroke (AIS) lesions, many deep-learning-based lesion segmentation methods have been proposed in the literature, where a deep convolutional neural network (CNN) was trained on hundreds of fully labeled subjects with accurate annotations of AIS lesions. Despite that high segmentation accuracy can be achieved, the accurate labels should be annotated by experienced clinicians, and it is therefore very time-consuming to obtain a large number of fully labeled subjects. In this paper, we propose a semi-supervised method to automatically segment AIS lesions in diffusion weighted images and apparent diffusion coefficient maps. By using a large number of weakly labeled subjects and a small number of fully labeled subjects, our proposed method is able to accurately detect and segment the AIS lesions. In particular, our proposed method consists of three parts: 1) a double-path classification net (DPC-Net) trained in a weakly-supervised way is used to detect the suspicious regions of AIS lesions; 2) a pixel-level K-Means clustering algorithm is used to identify the hyperintensive regions on the DWIs; and 3) a region-growing algorithm combines the outputs of the DPC-Net and the K-Means to obtain the final precise lesion segmentation. In our experiment, we use 460 weakly labeled subjects and 15 fully labeled subjects to train and fine-tune the proposed method. By evaluating on a clinical dataset with 150 fully labeled subjects, our proposed method achieves a mean dice coefficient of 0.642, and a lesion-wise F1 score of 0.822.

研究动机与目标

• 减少对昂贵、耗时的专家标注在急性缺血性卒中病灶分割中的依赖。
• 在有限完全标注数据下，提升弥散加权成像中的分割精度。
• 开发一种稳健的自动化方法，适用于急性卒中临床环境中的部署。
• 整合弱监督检测与聚类及区域生长法，实现精确的病灶勾画。

提出的方法

• 采用弱监督方式训练双路径分类网络（DPC-Net），从弥散加权图像中检测可疑AIS区域。
• 采用像素级K-均值聚类算法识别表观弥散系数（ADC）图上的高信号区域。
• 利用区域生长算法融合DPC-Net和K-均值的输出，以优化病灶边界。
• 使用460例弱标注和15例完全标注受试者对模型进行训练和微调。
• 该方法结合图像强度模式与空间上下文信息，提升分割的鲁棒性。
• 半监督学习使模型在完全标注数据极少的情况下仍能实现高性能。

实验结果

研究问题

• RQ1 是否能够通过半监督深度学习方法，在完全标注数据极少的情况下实现高精度的AIS病灶分割？
• RQ2 将弱监督分类与聚类及区域生长法结合，在病灶分割中是否具有显著效果？
• RQ3 当仅使用15例完全标注受试者进行训练时，所提方法是否仍能保持高性能？
• RQ4 与单模态方法相比，DPC-Net与K-均值的融合如何提升病灶检测性能？
• RQ5 该方法在包含完全标注病灶的临床测试集上的表现如何？

主要发现

• 所提方法在150例完全标注受试者的测试集上实现了0.642的平均Dice系数。
• 病灶级F1分数达到0.822，表明在病灶水平检测上表现优异。
• 该方法仅使用15例完全标注受试者即表现出鲁棒性，显著减轻了标注负担。
• DPC-Net、K-均值与区域生长法的融合在病灶定位和边界准确性方面优于基线方法。
• 半监督框架有效利用了460例弱标注受试者，增强了模型的泛化能力。
• 结果证实了在极少数专家标注数据下实现高精度卒中病灶分割的可行性。