Anand Pandit1, Emma Robinson2, Paul Aljabar3, Ioannis S. Gousias1, Daniel Rueckert3, Serena J. Counsell1, David Edwards1
1Centre for the Developing Brain, MRC/Imperial College, London, United Kingdom; 2FMRIB, University of Oxford, Oxford, United Kingdom; 3Department of Computing, Imperial College, London, United Kingdom
In this study we combine a novel probabilistic tractography framework with Elastic Net LASSO regression in order to identify the structural connectivity patterns which are most predictive of neurodevelopmental outcome in prematurely born two-year old infants. Specific connections are shown to be responsible for effective neurological function. This work represents the first combined application of the tractography framework and regression method to this type of imaging data.