Accurate white matter lesion segmentation by k nearest neighbor classification with tissue type priors (kNN-TTPs).
Accurate white matter lesion segmentation by k nearest neighbor classification with tissue type priors (kNN-TTPs).
复制标题
DOI：
10.1016/j.nicl.2013.10.003
复制
发表时间：
2013
影响因子：
4.2
通讯作者：
Vrenken, Hugo
中科院分区：
文献类型：
--
作者：
Steenwijk, Martijn D.;Pouwels, Petra J. W.;Daams, Marita;van Dalen, Jan Willem;Caan, Matthan W. A.;Richard, Edo;Barkhof, Frederik;Vrenken, Hugo
白质（WM）病变的分割和体积量化在监测和研究多发性硬化症（MS）或脑血管疾病等神经系统疾病中发挥着重要作用。这通常是使用 2D 磁共振图像交互式完成的。采集技术的最新发展允许使用更薄的切片进行 3D 成像，但每个对象的大量图像使得手动描绘病变轮廓不可行。这就需要一种可靠的自动化方法。在这里，我们的目标是通过优化强度归一化和使用空间组织类型先验（TTP）来改进 WM 病变的 k 最近邻（kNN）分类。 kNN-TTP 方法使用 kNN 分类，以 3.0 T 3DFLAIR 和 3DT1 强度以及 MNI 归一化空间坐标作为特征。此外，TTP 是通过健康对照数据的非线性配准来计算的。使用方差缩放、鲁棒范围归一化或直方图匹配对强度特征进行归一化。然后，根据完全手动创建的参考分割，在 20 名多发性硬化症患者中进行留一法实验，对算法进行训练和评估。每种归一化方法的性能都在特征集中有和没有 TTP 的情况下进行了评估。使用类内系数（ICC）评估体积一致性，并使用Dice相似性指数（SI）评估体素空间一致性。最后，使用老年高血压受试者的独立样本评估了该方法在不同扫描仪和患者群体中的稳健性。强度归一化方法对分割性能有很大影响，当不使用 TTP 时，平均 SI 值范围为 0.66 至 0.72。独立于归一化方法，将 TTP 作为特征包含在内可以提高性能，特别是通过减少病变检测误差。使用方差缩放强度特征并在特征集中包含 TTP 实现了最佳性能：这产生了 ICC = 0.93 和平均 SI = 0.75 ± 0.08。在患有高血压的老年受试者的独立样本中验证该方法，得到更高的 ICC = 0.96 和 SI = 0.84 ± 0.14。添加 TTP 提高了基于 kNN 的 MS 病变分割方法的性能。使用方差缩放进行强度归一化并在特征集中包含 TTP 实现了最佳性能，无论使用的扫描仪或病变的病理基质如何，都与各种病变严重程度的参考分割表现出极好的一致性。强度归一化对病变分割性能有很大影响。将组织类型先验作为特征包含在内可以提高分割性能。使用方差缩放和组织类型先验实现了最佳性能。
The segmentation and volumetric quantification of white matter (WM) lesions play an important role in monitoring and studying neurological diseases such as multiple sclerosis (MS) or cerebrovascular disease. This is often interactively done using 2D magnetic resonance images. Recent developments in acquisition techniques allow for 3D imaging with much thinner sections, but the large number of images per subject makes manual lesion outlining infeasible. This warrants the need for a reliable automated approach. Here we aimed to improve k nearest neighbor (kNN) classification of WM lesions by optimizing intensity normalization and using spatial tissue type priors (TTPs). The kNN-TTP method used kNN classification with 3.0 T 3DFLAIR and 3DT1 intensities as well as MNI-normalized spatial coordinates as features. Additionally, TTPs were computed by nonlinear registration of data from healthy controls. Intensity features were normalized using variance scaling, robust range normalization or histogram matching. The algorithm was then trained and evaluated using a leave-one-out experiment among 20 patients with MS against a reference segmentation that was created completely manually. The performance of each normalization method was evaluated both with and without TTPs in the feature set. Volumetric agreement was evaluated using intra-class coefficient (ICC), and voxelwise spatial agreement was evaluated using Dice similarity index (SI). Finally, the robustness of the method across different scanners and patient populations was evaluated using an independent sample of elderly subjects with hypertension. The intensity normalization method had a large influence on the segmentation performance, with average SI values ranging from 0.66 to 0.72 when no TTPs were used. Independent of the normalization method, the inclusion of TTPs as features increased performance particularly by reducing the lesion detection error. Best performance was achieved using variance scaled intensity features and including TTPs in the feature set: this yielded ICC = 0.93 and average SI = 0.75 ± 0.08. Validation of the method in an independent sample of elderly subjects with hypertension, yielded even higher ICC = 0.96 and SI = 0.84 ± 0.14. Adding TTPs increases the performance of kNN based MS lesion segmentation methods. Best performance was achieved using variance scaling for intensity normalization and including TTPs in the feature set, showing excellent agreement with the reference segmentations across a wide range of lesion severity, irrespective of the scanner used or the pathological substrate of the lesions. Intensity normalization has a large influence on lesion segmentation performance. Inclusion of tissue type priors as features increases segmentation performance. Best performance was achieved using variance scaling and tissue type priors.
登录
查看更多内容
影响因子：
5.7
作者：
Admiraal-Behloul, F;van den Heuvel, DMJ;Relber, JHC
通讯作者：
Relber, JHC
影响因子：
11.2
作者：
Polman CH;Reingold SC;Banwell B;Clanet M;Cohen JA;Filippi M;Fujihara K;Havrdova E;Hutchinson M;Kappos L;Lublin FD;Montalban X;O'Connor P;Sandberg-Wollheim M;Thompson AJ;Waubant E;Weinshenker B;Wolinsky JS
通讯作者：
Wolinsky JS
影响因子：
4.8
作者：
DICE, LR
通讯作者：
DICE, LR
影响因子：
158.5
作者：
Polman, CH;O'Connor, PW;Sandrock, AW
通讯作者：
Sandrock, AW
影响因子：
4.6
作者：
Akselrod-Ballin, Ayelet;Galun, Meirav;Brandt, Achi
通讯作者：
Brandt, Achi