Background & aim: MS is a disease of the central nervous system in which the body makes a defensive attack on its tissues. The disease can affect the brain and spinal cord and cause a wide range of potential symptoms, including balance, motor and vision problems. MRI and FMRI images are a very important tool in the diagnosis and treatment of MS. The aim of the present study was to determine and diagnose early diagnosis of MS in MRI images of the brain using deep learning techniques.

Methods: The present experimental study was conducted at Kazerun Azad University in 2020. 1000 images were from BRATS data sets and in the two groups of learning and testing, 70 to 30% were included in the study and a deep four-layer deep learning network based on the network. Convulsive neuralgia is simulated in MATLAB environment. In the deep learning structure, which itself had the ability to extract features, we used another method to do so. For the reason that deep learning, although capable of extracting features was also conducted by chance. In order for the previous steps to be definite, the researchers used another algorithm inside the iteration loops and inside the torsion layer to reduce the dimensions of the feature during the training, secondly to select the best features and thirdly to extract the features definitively.1000 MRI images of BRATS data set in the two groups of learning and testing in the ratio of 70 to 30% were included in the study. A four-layer deep learning network based on convolutional neural network is simulated in MATLAB environment. In the deep learning structure, which had ability itself to extract features, another method was used to do this. For the reason that deep learning has the ability to extract features, but did so randomly. In order for the previous steps to be definitive, another algorithm was used inside the iterative loops and inside the torsion layer to reduce the dimensions of the feature during the training, secondly to select the best features and thirdly to extract the features definitively.

Results: The graphical representation of the ROC curve indicated that the degree of sensitivity or correct prediction against incorrect prediction in this binary classification system in which the separation threshold varies was significant. The area below this curve was 0.8592 and the accuracy of the proposed method was 98.6891 and the sensitivity was 94.8766.

Conclusion: Due to the prevalence of MS disease, early diagnosis and presentation of an intelligent method based on fMRI imaging is essential for treatment. This intelligent method tries to be able to help diagnose and treat more accurately, better identify the features and patterns affecting the disease than previous methods as a physician assistant. Finally, the results obtained from the present study revealed that the efficiency of the proposed method was evaluated at an excellent level and showed its optimality as much as possible. In addition, the obtained results indicated the speed of training and testing of data in high volume and fast convergence of the algorithm. It is correspondingly easier to expand and generalize.