Statistical machine learning to identify traumatic brain injury (TBI) from structural disconnections of white matter networks
详细信息 查看全文
- 作者：Jhimli Mitraa ; e ; jhimli.mitra@case.edu" class="auth_mail" title="E-mail the corresponding author ; Kai-kai Shena ; kaikai.shen@csiro.au" class="auth_mail" title="E-mail the corresponding author ; Soumya Ghosea ; e ; soumya.ghose@case.edu" class="auth_mail" title="E-mail the corresponding author ; Pierrick Bourgeata ; pierrick.bourgeat@csiro.au" class="auth_mail" title="E-mail the corresponding author ; Jurgen Frippa ; jurgen.fripp@csiro.au" class="auth_mail" title="E-mail the corresponding author ; Olivier Salvadoa ; olivier.salvado@csiro.au" class="auth_mail" title="E-mail the corresponding author ; Kerstin Pannekd ; kerstin.pannek@gmail.com" class="auth_mail" title="E-mail the corresponding author ; D. Jamie Taylorc ; jamie.taylor@health.sa.gov.au" class="auth_mail" title="E-mail the corresponding author ; Jane L. Mathiasb ; jane.mathias@adelaide.edu.au" class="auth_mail" title="E-mail the corresponding author ; Stephen Rosea ; stephen.rose@csiro.au" class="auth_mail" title="E-mail the corresponding author
- 关键词：Diffusion tractography ; Structural network connections ; Traumatic brain injury ; Network-based statistics ; Machine learning
- 刊名：NeuroImage
- 出版年：2016
- 出版时间：1 April 2016
- 年：2016
- 卷：129
- 期：Complete
- 页码：247-259
- 全文大小：2488 K
文摘
- class="listitem" id="list_l0005">
- class="label">•
Method to identify diffuse axonal injury in mild traumatic brain injury (mTBI) patients from structural connectivity patterns.
- class="label">•
Network-based statistics (NBS) is used to find significant network differences in mTBI and controls.
- class="label">•
Fractional anisotropy (FA) features of the different structural connections obtained from NBS used as features.
- class="label">•
Random forest classifier discriminates between mTBI and controls based on FA features.
- class="label">•
Discriminative and significant network differences obtained from feature importance of random forest.