Computer aided FCD lesion detection based on T1 MRI data

Focal cortical dysplasia (FCD) is a frequent cause of epilepsy and can be detected using brain magnetic resonance imaging (MRI). The FCD lesions in MRI images are characterized by blurring of the gray matter/white matter (GM/WM) junction, cortical thickening and hyper-intensity signal within lesional region compared with other cortical regions. However, detecting FCD lesions by means of visual inspection can be a very difficult task for radiologists because the lesions are very subtle. To assist physicians in detecting the FCD lesions more efficiently and reduce the false positive regions resulted from the existing methods, we propose an algorithm for automated FCD detection based on T1 MRI data.