Sharif Digital Repository

Clinical data from epileptic patients reveal important information about the characteristics of the particular type of epilepsy. Such data is often acquired in a bimodal fashion, e.g. video recordings are collected with the standard Electroencephalogram (EEG) data, in order to help the specialists validate their assessment based on one modality with the other. Manual annotation of the onset of seizures across several days' worth of data is time consuming. This paper proposes an automated epilepsy seizure detection method based on a combination of features from EEG and video data, and compares it against detectors using either modality alone. © 2017 IEEE  

Anatomical image segmentation is one of the foundations for medical planning. Recently, convolutional neural networks (CNN) have achieved much success in segmenting volumetric (3D) images when a large number of fully annotated 3D samples are available. However, rarely a volumetric medical image dataset containing a sufficient number of segmented 3D images is accessible since providing manual segmentation masks is monotonous and time-consuming. Thus, to alleviate the burden of manual annotation, we attempt to effectively train a 3D CNN using a sparse annotation where ground truth on just one 2D slice of the axial axis of each training 3D image is available. To tackle this problem, we propose... 

Anatomical image segmentation is one of the foundations for medical planning. Recently, convolutional neural networks (CNN) have achieved much success in segmenting volumetric (3D) images when a large number of fully annotated 3D samples are available. However, rarely a volumetric medical image dataset containing a sufficient number of segmented 3D images is accessible since providing manual segmentation masks is monotonous and time-consuming. Thus, to alleviate the burden of manual annotation, we attempt to effectively train a 3D CNN using a sparse annotation where ground truth on just one 2D slice of the axial axis of each training 3D image is available. To tackle this problem, we propose...