Diagnosis of Multiple Sclerosis (MS) Using Convolutional Neural Network (CNN) from MRIs

This paper presents a novel fully automated process of features extraction and classification of Multiple sclerosis (MS) daisies from magnetic resonance images (MRI). This hybrid method uses convolution neural network (CNN) for features extraction and a multilayer neural network for classification two classes normal and MS. The convolution neural network for recognition of Multiple sclerosis is considered in this paper showed that CNN has strong potential for detection of MS. The process of feature extraction form flair MRI is done by using CNN increases the performance of recognition. CNN due to lack of sensitivity to noise is good for performance diagnosis. Our result shows that CNN provides high detection rates without using any lesion segmentation. This fully automated method produces reliable MRI analysis and classification while is considering variability.