Enhancing precision in multiple sclerosis lesion segmentation: A U-net based machine learning approach with data augmentation
Segmentation of Multiple Sclerosis (MS) lesions from Magnetic Resonance Imaging (MRI) data presents a significant challenge due to the necessity for large volumes of training data and a sophisticated training process. Traditional MRI datasets often lack the extensive sample sizes required for effect...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Neuroimage: Reports |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666956025000030 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832572998325895168 |
|---|---|
| author | Oezdemir Cetin Berkay Canel Gamze Dogali Unal Sakoglu |
| author_facet | Oezdemir Cetin Berkay Canel Gamze Dogali Unal Sakoglu |
| author_sort | Oezdemir Cetin |
| collection | DOAJ |
| description | Segmentation of Multiple Sclerosis (MS) lesions from Magnetic Resonance Imaging (MRI) data presents a significant challenge due to the necessity for large volumes of training data and a sophisticated training process. Traditional MRI datasets often lack the extensive sample sizes required for effective training, necessitating the exploration of alternative methods for accurate segmentation. This study proposes a robust machine learning algorithm designed to identify MS lesions using both single-modal and multi-modal MRI data. The proposed algorithm employs Convolutional Neural Networks (CNNs) in the form of U-Net architecture, a renowned model for biomedical image segmentation. To address the issue of insufficient training data, data augmentation techniques have been implemented, enhancing the diversity and volume of the training set. The dataset for this study was created from MRI data of 20 subjects. The algorithm's effectiveness was evaluated using the DSC score, a statistical tool that measures the similarity between two samples. The model achieved a DSC score of 0.7960 in the training set and 0.7912 in the test set, demonstrating its effectiveness in performing segmentation of MS from multi-modal MRI data. The predicted locations of MS lesions were compared with the corresponding layers of white matter, gray matter, and cerebrospinal fluid within the brain. This innovative approach aims to enhance the accuracy and efficiency of MS lesion segmentation, contributing to advancements in precision medicine and the overall understanding of MS. |
| format | Article |
| id | doaj-art-2fc77fc92b6248e89f1a41d5377b2471 |
| institution | Kabale University |
| issn | 2666-9560 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Neuroimage: Reports |
| spelling | doaj-art-2fc77fc92b6248e89f1a41d5377b24712025-02-02T05:29:27ZengElsevierNeuroimage: Reports2666-95602025-03-0151100235Enhancing precision in multiple sclerosis lesion segmentation: A U-net based machine learning approach with data augmentationOezdemir Cetin0Berkay Canel1Gamze Dogali2Unal Sakoglu3Department of Electrical Engineering and Information Technology, Technische Universität Darmstadt, Darmstadt, Germany; Corresponding author. Merckstrasse 25, 64283, Darmstadt, Germany.Department of Electrical Engineering and Information Technology, Technische Universität Darmstadt, Darmstadt, GermanyDepartment of Electrical Engineering and Information Technology, Technische Universität Darmstadt, Darmstadt, GermanyComputer Engineering, University of Houston - Clear Lake, Houston, TX, USASegmentation of Multiple Sclerosis (MS) lesions from Magnetic Resonance Imaging (MRI) data presents a significant challenge due to the necessity for large volumes of training data and a sophisticated training process. Traditional MRI datasets often lack the extensive sample sizes required for effective training, necessitating the exploration of alternative methods for accurate segmentation. This study proposes a robust machine learning algorithm designed to identify MS lesions using both single-modal and multi-modal MRI data. The proposed algorithm employs Convolutional Neural Networks (CNNs) in the form of U-Net architecture, a renowned model for biomedical image segmentation. To address the issue of insufficient training data, data augmentation techniques have been implemented, enhancing the diversity and volume of the training set. The dataset for this study was created from MRI data of 20 subjects. The algorithm's effectiveness was evaluated using the DSC score, a statistical tool that measures the similarity between two samples. The model achieved a DSC score of 0.7960 in the training set and 0.7912 in the test set, demonstrating its effectiveness in performing segmentation of MS from multi-modal MRI data. The predicted locations of MS lesions were compared with the corresponding layers of white matter, gray matter, and cerebrospinal fluid within the brain. This innovative approach aims to enhance the accuracy and efficiency of MS lesion segmentation, contributing to advancements in precision medicine and the overall understanding of MS.http://www.sciencedirect.com/science/article/pii/S2666956025000030Multiple sclerosisU-NetMulti-modal MRISegmentationLesion detection |
| spellingShingle | Oezdemir Cetin Berkay Canel Gamze Dogali Unal Sakoglu Enhancing precision in multiple sclerosis lesion segmentation: A U-net based machine learning approach with data augmentation Neuroimage: Reports Multiple sclerosis U-Net Multi-modal MRI Segmentation Lesion detection |
| title | Enhancing precision in multiple sclerosis lesion segmentation: A U-net based machine learning approach with data augmentation |
| title_full | Enhancing precision in multiple sclerosis lesion segmentation: A U-net based machine learning approach with data augmentation |
| title_fullStr | Enhancing precision in multiple sclerosis lesion segmentation: A U-net based machine learning approach with data augmentation |
| title_full_unstemmed | Enhancing precision in multiple sclerosis lesion segmentation: A U-net based machine learning approach with data augmentation |
| title_short | Enhancing precision in multiple sclerosis lesion segmentation: A U-net based machine learning approach with data augmentation |
| title_sort | enhancing precision in multiple sclerosis lesion segmentation a u net based machine learning approach with data augmentation |
| topic | Multiple sclerosis U-Net Multi-modal MRI Segmentation Lesion detection |
| url | http://www.sciencedirect.com/science/article/pii/S2666956025000030 |
| work_keys_str_mv | AT oezdemircetin enhancingprecisioninmultiplesclerosislesionsegmentationaunetbasedmachinelearningapproachwithdataaugmentation AT berkaycanel enhancingprecisioninmultiplesclerosislesionsegmentationaunetbasedmachinelearningapproachwithdataaugmentation AT gamzedogali enhancingprecisioninmultiplesclerosislesionsegmentationaunetbasedmachinelearningapproachwithdataaugmentation AT unalsakoglu enhancingprecisioninmultiplesclerosislesionsegmentationaunetbasedmachinelearningapproachwithdataaugmentation |