- ► First submission deadline, team merger, July 13, 2014
- ► Final submission deadline July 20, 2014
September 21-24, 2014 Reims, France
This year's task is to diagnose schizophrenia using multimodal features from MRI scans. Schizophrenia is a severe and disabling mental illnesses which has no well-established, non-invasive diagnosis biomarker. Currently, due to its symptom overlap with other mental illnesses (like bipolar disorder), it can only be diagnosed subjectively, by process of elimination. In this competition, you are invited to make an attempt to automatically diagnose subjects with schizophrenia based on multimodal features derived from their brain magnetic resonance imaging (MRI) scans. The features made available in this competition are a result from current state-of-the art developments in neuroimaging and MRI data processing. Two modalities of MRI scans are used to obtain these features: functional and structural MRI. One challenge in this competition is how to optimally combine this type of multimodal information and select features that enhance diagnosis. Optional additional information is provided that could be helpful with this particular aspect of the task.
Please visit the Kaggle competition website for full details about the competition and submission instructions at
Selection of winning teams is based on:
Notice that members of the 2014 MLSP Competition Committee (and everyone belonging to any of the labs of the 2014 MLSP Competition Committee) are not eligible for awards.