Multiple sclerosis (MS) is a demyelinating disease which could cause severe motor and cognitive deterioration. Segmenting MS lesions could be highly beneficial for diagnosing, analyzing and monitoring treatment efficacy. To do so, manual segmentation, performed by experts, is the conventional method in hospitals and clinical environments. Although manual segmentation is accurate, it is time consuming, expensive and might not be reliable. The aim of this work was to propose an automatic method for MS lesion segmentation and evaluate it using brain images available within the MICCAI MS segmentation challenge. The proposed method employs supervised artificial neural network based algorithm, exploiting intensity-based and spatial-based features as the input of the network. This method achieved relatively accurate results with acceptable training and testing time for training datasets.