Robustness of Probabilistic U-Net for Automated Segmentation of White Matter Hyperintensities in Different Datasets of Brain MRI
Robustness of Probabilistic U-Net for Automated Segmentation of White Matter Hyperintensities in Different Datasets of Brain MRI
复制标题
用于脑 MRI 不同数据集中白质高信号自动分割的概率 U-Net 的鲁棒性
DOI：
10.1109/icacsis53237.2021.9631365
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Laksmita Rahadianti
中科院分区：
文献类型：
--
作者：
Rizal Maulana;M. F. Rachmadi;Laksmita Rahadianti
白质高信号(WMH)是T2-FLAIR脑MRI中常见的白区(即高信号)，是小血管病变(SVD)的特征。WMH的详细测量(例如，它们的体积、位置、分布)对于临床研究至关重要，但由于WMH的不适定边界，分割WMH是具有挑战性的。在这项研究中，我们研究了概率U网和其他确定性深度学习模型(即U网及其变体)用于WMH自动分割的稳健性。特别是，我们感兴趣的是基于U网的深度学习模型，特别是概率U网，用于从不同的数据集中分割脑MRI中的WMH。因此，我们进行了两个不同的实验，即k重交叉验证实验(即，使用相同的数据集进行训练和测试)和跨数据集实验(即，在不同的数据集上进行测试)。基于我们的实验，概率U网在k重交叉验证实验中表现优于其他测试模型。另一方面，我们发现概率U网在不同的数据集上测试时捕获了不同类型的不确定性。
White Matter Hyperintensities (WMHs) are neu-roradiological features often seen in T2-FLAIR brain MRI as white regions (i.e., hyperintensities) and characteristic of small vessel disease (SVD). Detailed measurements of WMHs (e.g., their volumes, locations, distributions) are vital for clinical research, but segmenting WMHs is challenging due to WMHs' ill-posed boundaries. In this study, we investigate the robustness of Probabilistic U-Net and other deterministic deep learning models (i.e., U-Net and its variations) for automatic segmentation of WMHs. In particular, we are interested in the robustness of U-Net based deep learning models, especially the Probabilistic U-Net, for segmenting WMHs in brain MRI from different datasets. Thus, we performed two different experiments, which are k- fold cross validation experiment (i.e., training and testing using the same dataset) and cross dataset experiment (i.e., testing in different dataset). Based on our experiments, Probabilistic U-Net outperformed other tested models in k-fold cross validation experiment. On the other hand, we found that Probabilistic U-Net captured different types of uncertainty when tested in different dataset.