Multivariate lesion-symptom mapping using support vector regression.

Multivariate lesion-symptom mapping using support vector regression.
复制标题

DOI:
10.1002/hbm.22590
复制
发表时间:
2014-12
影响因子:
4.8
通讯作者:
Wang, Ze
Wang, Ze
中科院分区:
医学2区
文献类型:
--
作者:
Zhang, Yongsheng;Kimberg, Daniel Y.;Coslett, H. Branch;Schwartz, Myrna F.;Wang, Ze

文献摘要

参考文献

被引文献

相似文献

病变分析是研究大脑功能的经典方法。由于大脑功能是功能相关体素集合相干激活的结果,因此病变-症状关系通常由多个体素同时贡献。尽管基于体素的病变症状图谱(VLSM)对理解大脑-行为关系做出了重大贡献,但更好地理解多个大脑区域所贡献的大脑-行为关系需要多变量病变症状图谱(MLSM)。本文的目的是使用基于机器学习的多元回归算法:支持向量回归(SVR)来开发 MLSM。在所提出的 SVR-LSM 中,使用非线性函数对与整个病变图而不是每个孤立体素的症状关系进行建模,因此从本质上考虑了体素间的相关性,从而产生了一种可能更灵敏的方法来检查病变-症状关系。为了探索 VLSM 和 SVR-LSM 的相对优点,我们在分析合成数据集时使用了这两种方法。 SVR-LSM 在检测综合损伤-行为关系方面表现出比 VLSM 高得多的灵敏度和特异性。当应用于脑损伤患者的病变数据和语言测量时,SVR-LSM 再现了 VLSM 先前发现的基本模式,并且在识别病变与行为关系方面表现出比 VLSM 更高的灵敏度。我们的数据还显示了使用病变数据来预测连续行为评分的可能性。
Lesion analysis is a classic approach to study brain functions. Because brain function is a result of coherent activations of a collection of functionally related voxels, lesion-symptom relations are generally contributed by multiple voxels simultaneously. Although voxel-based lesion symptom mapping (VLSM) has made substantial contributions to the understanding of brain-behavior relationships, a better understanding of the brain-behavior relationship contributed by multiple brain regions needs a multivariate lesion symptom mapping (MLSM). The purpose of this paper was to develop an MLSM using a machine learning-based multivariate regression algorithm: support vector regression (SVR). In the proposed SVR-LSM, the symptom relation to the entire lesion map as opposed to each isolated voxel is modeled using a non-linear function, so the inter-voxel correlations are intrinsically considered, resulting in a potentially more sensitive way to examine lesion-symptom relationships. To explore the relative merits of VLSM and SVR-LSM we used both approaches in the analysis of a synthetic dataset. SVR-LSM showed much higher sensitivity and specificity for detecting the synthetic lesion-behavior relations than VLSM. When applied to lesion data and language measures from patients with brain damages, SVR-LSM reproduced the essential pattern of previous findings identified by VLSM and showed higher sensitivity than VLSM for identifying the lesion-behavior relations. Our data also showed the possibility of using lesion data to predict continuous behavior scores.
DOI: 10.1093/brain/aws354
发表时间: 2013-02
期刊: Brain : a journal of neurology
影响因子: --
作者:
Kümmerer D;Hartwigsen G;Kellmeyer P;Glauche V;Mader I;Klöppel S;Suchan J;Karnath HO;Weiller C;Saur D
通讯作者: Saur D
DOI: 10.1109/tnn.1997.641482
发表时间: 1997-01-01
影响因子: --
作者:
Cherkassky, V
通讯作者: Cherkassky, V
DOI: 10.1093/brain/aws336
发表时间: 2013-02-01
期刊: BRAIN
影响因子: 14.5
作者:
Mesulam, M. -Marsel;Wieneke, Christina;Rogalski, Emily J.
通讯作者: Rogalski, Emily J.
DOI: 10.1162/jocn.2007.19.7.1067
发表时间: 2007-07-01
影响因子: 3.2
作者:
Kimberg, Daniel Y.;Coslett, H. Branch;Schwartz, Myrna F.
通讯作者: Schwartz, Myrna F.
DOI: 10.1016/j.neuroimage.2005.01.048
发表时间: 2005-06-01
期刊: NEUROIMAGE
影响因子: 5.7
作者:
LaConte, S;Strother, S;Hu, XP
通讯作者: Hu, XP