Early Detection of MS in fMRI Images of the Brain Using Deep Learning Techniques

Message:
Article Type:
Research/Original Article (دارای رتبه معتبر)
Abstract:
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.

Language:
Persian
Published:
Armaghane-danesh, Volume:26 Issue: 6, 2022
Pages:
941 to 951
magiran.com/p2403882  
دانلود و مطالعه متن این مقاله با یکی از روشهای زیر امکان پذیر است:
اشتراک شخصی
با عضویت و پرداخت آنلاین حق اشتراک یک‌ساله به مبلغ 1,390,000ريال می‌توانید 70 عنوان مطلب دانلود کنید!
اشتراک سازمانی
به کتابخانه دانشگاه یا محل کار خود پیشنهاد کنید تا اشتراک سازمانی این پایگاه را برای دسترسی نامحدود همه کاربران به متن مطالب تهیه نمایند!
توجه!
  • حق عضویت دریافتی صرف حمایت از نشریات عضو و نگهداری، تکمیل و توسعه مگیران می‌شود.
  • پرداخت حق اشتراک و دانلود مقالات اجازه بازنشر آن در سایر رسانه‌های چاپی و دیجیتال را به کاربر نمی‌دهد.
In order to view content subscription is required

Personal subscription
Subscribe magiran.com for 70 € euros via PayPal and download 70 articles during a year.
Organization subscription
Please contact us to subscribe your university or library for unlimited access!