همایش ملی بیوانفورماتیک ایران

صفحه اصلی / 4th international edition and 13th Iranian Conference on Bioinformatics

A Transformer-based Model for Diagnosis of Multiple Sclerosis using MRI Images

نویسندگان :

Elham Bagheri¹ Leila Safari²

1- Department of Electrical and Computer Engineering University of Zanjan, 2- Department of Electrical and Computer Engineering University of Zanjan,

کلمات کلیدی :

Multiple Sclerosis (MS)،Diagnosis،MRI images،Transformer Based Models،Vision Transformer(ViT)

چکیده :

Multiple Sclerosis (MS) is an autoimmune inflammatory disease that leads to the degradation of myelin in the central nervous system (brain and spinal cord), resulting in issues with movement, sensation, and balance. This disease has significant effects on individuals’ quality of life. In this study, a Vision Transformer (ViT)-based model is proposed for diagnosing MS using MRI images. One of the primary challenges in this research is the lack of a standard dataset for implementing the proposed model. To address this issue, the two techniques of transfer learning and fine-tuning have been employed. Two relatively large datasets, including over 21,000 general image samples and 5,000 pneumonia images, were used for pre-training the proposed model. Additionally, a smaller dataset containing 3,427 MRI images associated with MS, labeled with patient classes and healthy classes in both axial and sagittal views ( four classes in total), was used to fine-tune the ViT model for MS diagnosis. The results of MRI image classification with pre-trained models show an accuracy of 0.100 for the two-class scenario with both pre-training datasets, 0.96 for the four-class scenario with the pneumonia dataset, and 0.95 for the four-class scenario with the general dataset. These results indicate that dataset selection for fine-tuning the model in ViT implementation is highly significant. Moreover, the high performance of the proposed method confirms the effectiveness of the emerging ViT model and its notable superiority over traditional neural network architectures, such as deep convolutional networks.

لیست مقالات

لیست مقالات بایگانی شده

Investigation and comparison of TYDC2 gene expression in different tissues (root, leaf, capsule and petal) of medicinal plant poppy (Papaver somniferum L.) in terms of bioinformatics

Nazila Bagheri - Alireza Tarinejad - Mohammad Majidi - Karim Hasanpour

Enhancing NAFLD Diagnosis with AI: Insights from the Persian Fasa Cohort Through Advanced Machine Learning Techniques

Marzie Shadpirouz - Mohammad Reza Zabihi - Zahra Salehi - Kiarash Zare - Mohammad Mehdi Naghizadeh - Kaveh Kavousi

Dissecting the impact of smoking on epigenetic mechanisms that influencing Lung cancer susceptibility

Mahboobeh Golchinpour - Alireza Fotuhi Siahpirani

Fully Convolutional Neural Networks for Volumetric Segmentation of Ultrasound Images: An Effective Tool for Automated Estimation of Fetal Head Circumference

Seyed Vahab Shojaedini - Mohammad Momenian

Towards Efficient Recombinant Protein Production: In-silico screening of signal peptides for secretory production of recombinant factor C in mammalian cells

Maryam Latifi - Kosar Asadi - Mansoureh Shahbazi Dastjerdeh

Gut Proteomics Reflecting Extraintestinal Organ Involvement in IBD

Leila Ghanbari Maman - Sadegh Rizi - Mahdi Anvari - Anna Meyfour - Kaveh Kavousi

Biomechanical Characterization of Realistic Bacterial Membranes Across Different Biofilm Ages: A Molecular Dynamics Study

Fatemeh Ebrahimi Tarki - Mahboobeh Zarrabi - Mahkame Sharbatdar

Computational Analysis of the D92V Mutation in the EF-hand II Loop of the Mnemiopsin 2 Photoprotein

Hanieh Ramezani - Vahab Jafarian - Akram Shirdel - Khosrow Khalifeh - Fatemeh Khatami

In silico vaccine design for breast cancer

Zohre Sadeghi - Zahra Davoudi

The key role of genes involved in proline biosynthesis and photosynthesis in drought response during Soybean flowering stage

Zeinab Shamabadi - Maryam Pasandideh Arjmand - Mohammad Mohsenzadeh Golfazani - Habibollah Samizadeh lahiji

بیشتر