Research
Print page Print page
Switch language
The Capital Region of Denmark - a part of Copenhagen University Hospital
Published

Visualization of nonlinear kernel models in neuroimaging by sensitivity maps

Research output: Contribution to journalJournal articleResearchpeer-review

  1. Optimization of preprocessing strategies in Positron Emission Tomography (PET) neuroimaging: A [11C]DASB PET study

    Research output: Contribution to journalJournal articleResearchpeer-review

  2. Alteration of functional brain architecture in 22q11.2 deletion syndrome - Insights into susceptibility for psychosis

    Research output: Contribution to journalReviewResearchpeer-review

  3. Disease-informed brain mapping teaches important lessons about the human brain

    Research output: Contribution to journalEditorialResearchpeer-review

  4. Functional neuroimaging of recovery from motor conversion disorder: A case report

    Research output: Contribution to journalReviewResearchpeer-review

  5. The role of dopamine in the brain - lessons learned from Parkinson's disease

    Research output: Contribution to journalReviewResearchpeer-review

  1. Functional neuroimaging of recovery from motor conversion disorder: A case report

    Research output: Contribution to journalReviewResearchpeer-review

  2. Getting to grips with endoscopy - Learning endoscopic surgical skills induces bi-hemispheric plasticity of the grasping network

    Research output: Contribution to journalJournal articleResearchpeer-review

  3. Unmixing Oscillatory Brain Activity by EEG Source Localization and Empirical Mode Decomposition

    Research output: Contribution to journalJournal articleResearchpeer-review

  4. A principled approach to conductivity uncertainty analysis in electric field calculations

    Research output: Contribution to journalJournal articleResearchpeer-review

  5. Modeling Temporal Dynamics in Functional Brain Connectivity

    Research output: Book/ReportPh.D. thesisResearch

View graph of relations
There is significant current interest in decoding mental states from neuroimages. In this context kernel methods, e.g., support vector machines (SVM) are frequently adopted to learn statistical relations between patterns of brain activation and experimental conditions. In this paper we focus on visualization of such nonlinear kernel models. Specifically, we investigate the sensitivity map as a technique for generation of global summary maps of kernel classification models. We illustrate the performance of the sensitivity map on functional magnetic resonance (fMRI) data based on visual stimuli. We show that the performance of linear models is reduced for certain scan labelings/categorizations in this data set, while the nonlinear models provide more flexibility. We show that the sensitivity map can be used to visualize nonlinear versions of kernel logistic regression, the kernel Fisher discriminant, and the SVM, and conclude that the sensitivity map is a versatile and computationally efficient tool for visualization of nonlinear kernel models in neuroimaging.
Original languageEnglish
JournalNeuroImage
Volume55
Issue number3
Pages (from-to)1120-1131
DOIs
Publication statusPublished - Apr 2011

ID: 32535432