Multiple sclerosis diagnosis with brain MRI retrieval: A deep learning approach
Multiple Sclerosis (MS) is an auto-immune disorder affecting the central nervous system, affecting 2.8 million people worldwide. Early diagnosis is crucial due to its profound social and economic impacts. MRI is commonly used for monitoring abnormalities. This study proposes a novel Content-Based Me...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Results in Control and Optimization |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666720725000190 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832087402211966976 |
|---|---|
| author | R.M. Haggag Eman M. Ali M.E. Khalifa Mohamed Taha |
| author_facet | R.M. Haggag Eman M. Ali M.E. Khalifa Mohamed Taha |
| author_sort | R.M. Haggag |
| collection | DOAJ |
| description | Multiple Sclerosis (MS) is an auto-immune disorder affecting the central nervous system, affecting 2.8 million people worldwide. Early diagnosis is crucial due to its profound social and economic impacts. MRI is commonly used for monitoring abnormalities. This study proposes a novel Content-Based Medical Image Retrieval (CBMIR) framework using Convolutional Neural Networks (CNN) and Transfer Learning (TL) for MS diagnosis using MRI data. Our framework utilizes The Inception V3 model that is pre-trained on ImageNet and RadImageNet datasets, and we modified the model by adding a new block of six layers to reduce the features’ dimensionality in the feature extraction phase. Fine-tuning the hyper-parameters for the whole system was done using the Bayesian optimizer. We experiment with Nine different distance metrics to measure query and database image similarity. Experiments on four public MS-MRI datasets demonstrated the end-to-end deep learning framework’s generalizability without extensive pre-processing, with mAP scores of 86.20%, 93.77%, 94.18%, and 90.46%, respectively demonstrating its effectiveness in retrieval. Moreover, a comparison with related CBMIR systems confirmed the effectiveness of our model. |
| format | Article |
| id | doaj-art-a21ca75507a44a70a5b8c050757139cb |
| institution | Kabale University |
| issn | 2666-7207 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Results in Control and Optimization |
| spelling | doaj-art-a21ca75507a44a70a5b8c050757139cb2025-02-06T05:12:54ZengElsevierResults in Control and Optimization2666-72072025-03-0118100533Multiple sclerosis diagnosis with brain MRI retrieval: A deep learning approachR.M. Haggag0Eman M. Ali1M.E. Khalifa2Mohamed Taha3Faculty of Computers and Artificial Intelligence, Benha University, Egypt; Corresponding author.Faculty of Computers and Artificial Intelligence, Benha University, EgyptFaculty of Computer and Information Sciences, Ain Shams University, EgyptFaculty of Computers and Artificial Intelligence, Benha University, EgyptMultiple Sclerosis (MS) is an auto-immune disorder affecting the central nervous system, affecting 2.8 million people worldwide. Early diagnosis is crucial due to its profound social and economic impacts. MRI is commonly used for monitoring abnormalities. This study proposes a novel Content-Based Medical Image Retrieval (CBMIR) framework using Convolutional Neural Networks (CNN) and Transfer Learning (TL) for MS diagnosis using MRI data. Our framework utilizes The Inception V3 model that is pre-trained on ImageNet and RadImageNet datasets, and we modified the model by adding a new block of six layers to reduce the features’ dimensionality in the feature extraction phase. Fine-tuning the hyper-parameters for the whole system was done using the Bayesian optimizer. We experiment with Nine different distance metrics to measure query and database image similarity. Experiments on four public MS-MRI datasets demonstrated the end-to-end deep learning framework’s generalizability without extensive pre-processing, with mAP scores of 86.20%, 93.77%, 94.18%, and 90.46%, respectively demonstrating its effectiveness in retrieval. Moreover, a comparison with related CBMIR systems confirmed the effectiveness of our model.http://www.sciencedirect.com/science/article/pii/S2666720725000190Multiple sclerosisCBMIRCNNTransfer learningRadImageNetInception V3 |
| spellingShingle | R.M. Haggag Eman M. Ali M.E. Khalifa Mohamed Taha Multiple sclerosis diagnosis with brain MRI retrieval: A deep learning approach Results in Control and Optimization Multiple sclerosis CBMIR CNN Transfer learning RadImageNet Inception V3 |
| title | Multiple sclerosis diagnosis with brain MRI retrieval: A deep learning approach |
| title_full | Multiple sclerosis diagnosis with brain MRI retrieval: A deep learning approach |
| title_fullStr | Multiple sclerosis diagnosis with brain MRI retrieval: A deep learning approach |
| title_full_unstemmed | Multiple sclerosis diagnosis with brain MRI retrieval: A deep learning approach |
| title_short | Multiple sclerosis diagnosis with brain MRI retrieval: A deep learning approach |
| title_sort | multiple sclerosis diagnosis with brain mri retrieval a deep learning approach |
| topic | Multiple sclerosis CBMIR CNN Transfer learning RadImageNet Inception V3 |
| url | http://www.sciencedirect.com/science/article/pii/S2666720725000190 |
| work_keys_str_mv | AT rmhaggag multiplesclerosisdiagnosiswithbrainmriretrievaladeeplearningapproach AT emanmali multiplesclerosisdiagnosiswithbrainmriretrievaladeeplearningapproach AT mekhalifa multiplesclerosisdiagnosiswithbrainmriretrievaladeeplearningapproach AT mohamedtaha multiplesclerosisdiagnosiswithbrainmriretrievaladeeplearningapproach |