Background

Manual segmentation is currently the gold standard to assess white matter hyperintensities (WMH), but it is time consuming and subject to intra and inter-operator variability.

Purpose

To compare automatic methods to segment white matter hyperintensities (WMH) in the elderly in order to assist radiologist and researchers in selecting the most relevant method for application on clinical or research data.

Material and Methods

We studied a research dataset composed of 147 patients, including 97 patients from the Alzheimer's Disease Neuroimaging Initiative (ADNI) 2 database and 50 patients from ADNI 3 and a clinical routine dataset comprising 60 patients referred for cognitive impairment at the Pitié-Salpêtrière hospital (imaged using four different MRI machines). We used manual segmentation as the gold standard reference. Both manual and automatic segmentations were performed using FLAIR MRI. We compared seven freely available methods that produce segmentation mask and are usable by a radiologist without a strong knowledge of computer programming: LGA (Schmidt et al., 2012), LPA (Schmidt, 2017), BIANCA (Griffanti et al., 2016), UBO detector (Jiang et al., 2018), W2MHS (Ithapu et al., 2014), nicMSlesion (with and without retraining) (Valverde et al., 2019, Valverde et al., 2017). The primary outcome for assessing segmentation accuracy was the Dice similarity coefficient (DSC) between the manual and the automatic segmentation software. Secondary outcomes included five other metrics.

Results

A deep learning approach, NicMSlesion, retrained on data from the research dataset ADNI, performed best on this research dataset (DSC: 0.595) and its DSC was significantly higher than that of all others. However, it ranked fifth on the clinical routine dataset and its performance severely dropped on data with artifacts. On the clinical routine dataset, the three top-ranked methods were LPA, SLS and BIANCA. Their performance did not differ significantly but was significantly higher than that of other methods.

Conclusion

This work provides an objective comparison of methods for WMH segmentation. Results can be used by radiologists to select a tool.

中文翻译：

---

七种老年患者白质高信号分割软件的比较和验证。

 背景

手动分割目前是评估白质高信号 (WMH) 的黄金标准，但它非常耗时，并且容易受到操作者内部和操作者之间的变异性的影响。

 目的

比较自动分割老年人白质高信号 (WMH) 的方法，以协助放射科医生和研究人员选择最相关的方法应用于临床或研究数据。

 材料与方法

我们研究了由 147 名患者组成的研究数据集，其中包括来自阿尔茨海默病神经影像倡议 (ADNI) 2 数据库的 97 名患者和来自 ADNI 3 数据库的 50 名患者，以及由 60 名在 Pitié-Salpêtrière 医院因认知障碍转诊的患者组成的临床常规数据集（成像）使用四台不同的 MRI 机器）。我们使用手动分割作为黄金标准参考。手动和自动分割均使用 FLAIR MRI 进行。我们比较了七种可免费使用的方法，这些方法可以生成分割掩模，并且无需具备丰富的计算机编程知识即可由放射科医生使用：LGA (Schmidt et al., 2012)、LPA (Schmidt, 2017)、BIANCA (Griffanti et al., 2016) 、UBO 检测器（Jiang 等人，2018）、W2MHS（Ithapu 等人，2014）、nicMSlesion（有或没有再训练）（Valverde 等人，2019、Valverde 等人，2017）。评估分割准确性的主要结果是手动和自动分割软件之间的 Dice 相似系数 (DSC)。次要结果包括其他五个指标。

 结果

深度学习方法 NicMSlesion 根据研究数据集 ADNI 的数据进行了重新训练，在该研究数据集上表现最佳（DSC：0.595），并且其 DSC 显着高于所有其他方法。然而，它在临床常规数据集上排名第五，并且在含有伪影的数据上其性能严重下降。在临床常规数据集上，排名靠前的三种方法是 LPA、SLS 和 BIANCA。它们的性能没有显着差异，但明显高于其他方法。

 结论

这项工作提供了 WMH 分割方法的客观比较。放射科医生可以使用结果来选择工具。