Multiclass Support Vector Machine-Based Lesion Mapping Predicts Functional Outcome in Ischemic Stroke Patients.
Multiclass Support Vector Machine-Based Lesion Mapping Predicts Functional Outcome in Ischemic Stroke Patients.
复制标题
DOI：
10.1371/journal.pone.0129569
复制
发表时间：
2015
期刊：
影响因子：
3.7
通讯作者：
Fiehler J
中科院分区：
文献类型：
--
作者：
Forkert ND;Verleger T;Cheng B;Thomalla G;Hilgetag CC;Fiehler J
这项研究的目的是调查是否可以使用多分类支持向量机(SVM)来使用缺血性卒中最终梗死灶的体积和位置来预测相关的功能结果。采用68例缺血性卒中患者30天后已知改良Rankin分级(MRS)功能结果的随访MR FLAIR数据集。梗死区被分割，并用于计算预先定义的MNI、哈佛-牛津皮质和皮质下图谱区域中受损体素的百分比，以及使用四个特定问题的VOI，这些VOI是使用基于体素的病变症状图从数据库中识别的。使用来自不同脑区定义的病变重叠值、卒中偏侧性信息以及可选参数梗死体积、入院NIHSS和患者年龄，生成了用于预测相应MRS评分的总共12个支持向量机分类模型。留一交叉验证显示，与没有利用中风位置信息的分类模型相比，包括病变重叠测量方面的中风位置信息导致了更好的MRS预测结果。此外，在所有测试的情况下，可选特征的集成导致了改进的MRS预测结果。特定问题的大脑区域和可选特征的额外集成导致了最好的MRS预测，精确的多值MRS预测准确率为56%，滑动窗口多值MRS预测准确率(MRS±1)为82%，二进制MRS(0-2vs.3-5)预测准确率为85%。因此，基于分级支持向量机的功能性中风预后预测，使用特定问题的大脑区域进行病变重叠量化，可以获得令人振奋的结果，但需要使用独立的数据库进一步验证，以排除潜在的方法偏差和过度匹配的影响。如果结合基于急性期采集的多参数数据集的体素组织结果预测，分级MRS功能结果的预测可能是一个有价值的工具。
The aim of this study was to investigate if ischemic stroke final infarction volume and location can be used to predict the associated functional outcome using a multi-class support vector machine (SVM). Sixty-eight follow-up MR FLAIR datasets of ischemic stroke patients with known modified Rankin Scale (mRS) functional outcome after 30 days were used. The infarct regions were segmented and used to calculate the percentage of lesioned voxels in the predefined MNI, Harvard-Oxford cortical and subcortical atlas regions as well as using four problem-specific VOIs, which were identified from the database using voxel-based lesion symptom mapping. An overall of 12 SVM classification models for predicting the corresponding mRS score were generated using the lesion overlap values from the different brain region definitions, stroke laterality information, and the optional parameters infarct volume, admission NIHSS, and patient age. Leave-one-out cross validations revealed that including information about the stroke location in terms of lesion overlap measurements led to improved mRS prediction results compared to classification models not utilizing the stroke location information. Furthermore, integration of the optional features led to improved mRS prediction results in all cases tested. The problem-specific brain regions and additional integration of the optional features led to the best mRS predictions with a precise multi-value mRS prediction accuracy of 56%, sliding window multi-value mRS prediction accuracy (mRS±1) of 82%, and binary mRS (0-2 vs. 3-5) prediction accuracy of 85%. Therefore, a graded SVM-based functional stroke outcome prediction using the problem-specific brain regions for lesion overlap quantification leads to promising results but needs to be further validated using an independent database to rule out a potential methodical bias and overfitting effects. The prediction of the graded mRS functional outcome could be a valuable tool if combined with voxel-wise tissue outcome predictions based on multi-parametric datasets acquired at the acute phase.
登录
查看更多内容
影响因子：
2.6
作者：
Medina J;Kimberg DY;Chatterjee A;Coslett HB
通讯作者：
Coslett HB
影响因子：
8.3
作者：
Kent, David M.;Selker, Harry P.;Hacke, Werner
通讯作者：
Hacke, Werner
影响因子：
8.3
作者：
Cheng, Bastian;Forkert, Nils Daniel;Thomalla, Goetz
通讯作者：
Thomalla, Goetz
影响因子：
8.3
作者：
Neumann-Haefelin, T;Wittsack, HJ;Freund, HJ
通讯作者：
Freund, HJ
影响因子：
3.5
作者：
Forkert, N. D.;Kaesemann, P.;Thomalla, G.
通讯作者：
Thomalla, G.