Dataset Information

Using machine learning-based lesion behavior mapping to identify anatomical networks of cognitive dysfunction: Spatial neglect and attention.

ABSTRACT: Previous lesion behavior studies primarily used univariate lesion behavior mapping techniques to map the anatomical basis of spatial neglect after right brain damage. These studies led to inconsistent results and lively controversies. Given these inconsistencies, the idea of a wide-spread network that might underlie spatial orientation and neglect has been pushed forward. In such case, univariate lesion behavior mapping methods might have been inherently limited in detecting the presumed network due to limited statistical power. By comparing various univariate analyses with multivariate lesion-mapping based on support vector regression, we aimed to validate the network hypothesis directly in a large sample of 203 newly recruited right brain damaged patients. If the exact same correction factors and parameter combinations (FDR correction and dTLVC for lesion size control) were used, both univariate as well as multivariate approaches uncovered the same complex network pattern underlying spatial neglect. At the cortical level, lesion location dominantly affected the temporal cortex and its borders into inferior parietal and occipital cortices. Beyond, frontal and subcortical gray matter regions as well as white matter tracts connecting these regions were affected. Our findings underline the importance of a right network in spatial exploration and attention and specifically in the emergence of the core symptoms of spatial neglect.

SUBMITTER: Wiesen D

PROVIDER: S-EPMC6765420 | biostudies-literature | 2019 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Using machine learning-based lesion behavior mapping to identify anatomical networks of cognitive dysfunction: Spatial neglect and attention.

Wiesen Daniel D Sperber Christoph C Yourganov Grigori G Rorden Christopher C Karnath Hans-Otto HO

NeuroImage 20190709

Previous lesion behavior studies primarily used univariate lesion behavior mapping techniques to map the anatomical basis of spatial neglect after right brain damage. These studies led to inconsistent results and lively controversies. Given these inconsistencies, the idea of a wide-spread network that might underlie spatial orientation and neglect has been pushed forward. In such case, univariate lesion behavior mapping methods might have been inherently limited in detecting the presumed network ...[more]

PMID: 31295567

Similar Datasets

Project description:BackgroundVoxel-based lesion symptom mapping (VLSM) assesses the relation of lesion location at a voxel level with a specific clinical or functional outcome measure at a population level. Spatial normalization, that is, mapping the patient images into an atlas coordinate system, is an essential pre-processing step of VLSM. However, no consensus exists on the optimal registration approach to compute the transformation nor are downstream effects on VLSM statistics explored. In this work, we evaluate four registration approaches commonly used in VLSM pipelines: affine (AR), nonlinear (NLR), nonlinear with cost function masking (CFM), and enantiomorphic registration (ENR). The evaluation is based on a standard VLSM scenario: the analysis of statistical relations of brain voxels and regions in imaging data acquired early after stroke onset with follow-up modified Rankin Scale (mRS) values.Materials and methodsFluid-attenuated inversion recovery (FLAIR) MRI data from 122 acute ischemic stroke patients acquired between 2 and 3 days after stroke onset and corresponding lesion segmentations, and 30 days mRS values from a European multicenter stroke imaging study (I-KNOW) were available and used in this study. The relation of the voxel location with follow-up mRS was assessed by uni- as well as multi-variate statistical testing based on the lesion segmentations registered using the four different methods (AR, NLR, CFM, ENR; implementation based on the ANTs toolkit).ResultsThe brain areas evaluated as important for follow-up mRS were largely consistent across the registration approaches. However, NLR, CFM, and ENR led to distortions in the patient images after the corresponding nonlinear transformations were applied. In addition, local structures (for instance the lateral ventricles) and adjacent brain areas remained insufficiently aligned with corresponding atlas structures even after nonlinear registration.ConclusionsFor VLSM study designs and imaging data similar to the present work, an additional benefit of nonlinear registration variants for spatial normalization seems questionable. Related distortions in the normalized images lead to uncertainties in the VLSM analyses and may offset the theoretical benefits of nonlinear registration.

Project description:The aim of this work was to quantitatively model cross-sectional relationships between structural connectome disruptions caused by cerebral infarction and measures of clinical performance. Imaging biomarkers of 41 ischemic stroke patients (72.0 ± 12.0 years, 20 female) were related to their baseline performance in 18 cognitive, physical and daily life activity assessments. Individual estimates of structural connectivity disruption in gray matter regions were computed using the Change in Connectivity (ChaCo) score. ChaCo scores were utilized because they can be calculated using routinely collected clinical magnetic resonance imagings. Partial Least Squares Regression (PLSR) was used to predict various acute impairment and activity measures from ChaCo scores and patient demographics. Statistical methods of cross-validation, bootstrapping and multiple comparisons correction were implemented to minimize over-fitting and Type I errors. Multiple linear regression models based on lesion volume and lateralization information were constructed for comparison. All models based on connectivity disruption had lower Akaike Information Criterion and almost all had better goodness-of-fit values (R(2) : 0.26-0.92) than models based on lesion characteristics (R(2) : 0.06-0.50). Confidence intervals of PLSR coefficients identified brain regions important in predicting each clinical assessment. Appropriate mapping of eloquent functions, that is, language and motor, and replication of results across pathologies provided validation of this method. Models of complex functions provided new insights into brain-behavior relationships. In addition to the potential applications in prognostication and rehabilitation development, this quantitative approach provides insight into the structural networks underlying complex functions like activities of daily living and cognition. Quantitative analysis of big data will be invaluable in understanding complex brain-behavior relationships.

Dataset Information

Using machine learning-based lesion behavior mapping to identify anatomical networks of cognitive dysfunction: Spatial neglect and attention.

Publications

Using machine learning-based lesion behavior mapping to identify anatomical networks of cognitive dysfunction: Spatial neglect and attention.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets