FCD detection

Focal Cortical Dysplasia (FCD) is the leading cause of drug-resistant epilepsy in both children and adults. The FCD lesions vary in size, shape, and location for different patients and make the manual detection time consuming and sensitive to the experience of the observer. Automatic segmentation of FCD lesions is challenging due to the difference in signal strength in images acquired with different machines, noise, and other kind of distortions such as motion artifacts. Not many automated methods were proposed in the literature for the detection and localization of FCD lesions. We use CNNs to automatically segment the FCD regions from MRI images. The preliminary results from the proposed model are shown below.