[论文解读] Accurate Automatic Segmentation of Amygdala Subnuclei and Modeling of Uncertainty via Bayesian Fully Convolutional Neural Network

Yilin Liu, Gengyan Zhao+6 more|arXiv (Cornell University)|Feb 19, 2019

Nuclear Physics and Applications参考文献 47被引用 5

一句话总结

该论文提出一种具有空洞双路结构的3D贝叶斯全卷积神经网络，以实现对杏仁核及其亚核的精确自动分割，利用大感受野和空洞卷积提升边界定位精度。该方法在Dice分数和对称表面距离指标上达到最先进性能，同时通过建模不确定性以检测非典型数据模式。

ABSTRACT

Recent advances in deep learning have improved the segmentation accuracy of subcortical brain structures, which would be useful in neuroimaging studies of many neurological disorders. However, most of the previous deep learning work does not investigate the specific difficulties that exist in segmenting extremely small but important brain regions such as the amygdala and its subregions. To tackle this challenging task, a novel 3D Bayesian fully convolutional neural network was developed to apply a dilated dualpathway approach that retains fine details and utilizes both local and more global contextual information to automatically segment the amygdala and its subregions at high precision. The proposed method provides insights on network design and sampling strategy that target segmentations of small 3D structures. In particular, this study confirms that a large context, enabled by a large field of view, is beneficial for segmenting small objects; furthermore, precise contextual information enabled by dilated convolutions allows for better boundary localization, which is critical for examining the morphology of the structure. In addition, it is demonstrated that the uncertainty information estimated from our network may be leveraged to identify atypicality in data. Our method was compared with two state-of-the-art deep learning models and a traditional multi-atlas approach, and exhibited excellent performance as measured both by Dice overlap as well as average symmetric surface distance. To the best of our knowledge, this work is the first deep learning-based approach that targets the subregions of the amygdala.

研究动机与目标

• 为解决在3D MRI扫描中分割极小且形态复杂的杏仁核亚核的挑战。
• 通过利用上下文信息和空洞卷积，提升小脑结构的边界定位精度。
• 开发一种深度学习框架，量化预测不确定性，以识别非典型神经解剖结构。
• 证明所提出的架构在分割皮层下结构方面优于现有的深度学习和多模板方法。
• 提供一种新颖的、全自动的高精度杏仁核亚区分割方法，此前深度学习尚未实现此目标。

提出的方法

• 设计了一种具有空洞双路结构的3D贝叶斯全卷积神经网络（FCN），以捕捉局部和全局上下文特征。
• 采用空洞卷积扩展感受野，同时不降低分辨率，从而保留小结构的精细空间细节。
• 通过大视野范围整合广泛的上下文信息，提升对微小亚核的分割精度。
• 对网络权重应用贝叶斯推断，以估计预测不确定性，实现不确定性感知的分割。
• 优化采样策略，以提升在小而复杂结构（如杏仁核亚核）上的泛化能力和鲁棒性。
• 在带有专家标注亚核标签的3D T1加权MRI扫描上端到端训练该模型。

实验结果

研究问题

• RQ1 与现有深度学习和多模板方法相比，具有空洞卷积的3D贝叶斯FCN是否能在小杏仁核亚核分割中实现更优的分割精度？
• RQ2 通过空洞卷积实现的大感受野是否能改善皮层下结构的边界定位？
• RQ3 贝叶斯网络生成的不确定性估计是否能有效识别非典型或模糊的神经解剖病例？
• RQ4 双路结构是否能有效平衡小3D结构的局部细节与全局上下文信息？
• RQ5 所提出的方法是否能实现无需人工干预的可靠、自动化的杏仁核亚核分割？

主要发现

• 所提方法在所有对比方法中取得了最高的Dice相似系数（DSC），显著优于两种最先进深度学习模型和一种传统多模板方法。
• 该网络在平均对称表面距离（ASSD）方面表现更优，表明其在亚核边界定位上更具准确性。
• 贝叶斯网络生成的不确定性图成功突出了具有非典型形态或模糊组织对比的区域。
• 空洞卷积的使用在保持空间分辨率的同时实现了大感受野，这对微小亚核的精确分割至关重要。
• 双路结构有效融合了局部纹理特征与全局上下文信息，增强了分割的鲁棒性。
• 本工作首次提出一种专门针对杏仁核亚核自动分割并具备不确定性量化能力的深度学习方法。