An attention based residual U-Net with swin transformer for brain MRI segmentation
Brain Tumors are a life-threatening cancer type. Due to the varied types and aggressive nature of these tumors, medical diagnostics faces significant challenges. Effective diagnosis and treatment planning depends on identifying the brain tumor areas from MRI images accurately. Traditional methods te...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Array |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590005625000037 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832087410938216448 |
|---|---|
| author | Tazkia Mim Angona M. Rubaiyat Hossain Mondal |
| author_facet | Tazkia Mim Angona M. Rubaiyat Hossain Mondal |
| author_sort | Tazkia Mim Angona |
| collection | DOAJ |
| description | Brain Tumors are a life-threatening cancer type. Due to the varied types and aggressive nature of these tumors, medical diagnostics faces significant challenges. Effective diagnosis and treatment planning depends on identifying the brain tumor areas from MRI images accurately. Traditional methods tend to use manual segmentation, which is costly, time consuming and prone to errors. Automated segmentation using deep learning approaches has shown potential in detecting tumor region. However, the complexity of the tumor areas which contain various shapes, sizes, fuzzy boundaries, makes this process difficult. Therefore, a robust automated segmentation method in brain tumor segmentation is required. In our paper, we present a hybrid model, 3-Dimension (3D) ResAttU-Net-Swin, which combines residual U-Net, attention mechanism and swin transformer. Residual blocks are introduced in the U-Net structure as encoder and decoder to avoid vanishing gradient problems and improve feature recovery. Attention-based skip connections are used to enhance the feature information transition between the encoder and decoder. The swin transformer obtains broad-scale features from the image data. The proposed hybrid model was evaluated on both the BraTS 2020 and BraTS 2019 datasets. It achieved an average Dice Similarity Coefficients (DSC) of 88.27 % and average Intersection over Union (IoU) of 79.93 % on BraTS 2020. On BraTS 2019, the model achieved an average DSC of 89.20 % and average IoU of 81.40 %. The model obtains higher DSC than the existing methods. The experiment result shows that the proposed methodology, 3D ResAttU-Net-Swin can be a potential for brain tumor segmentation in clinical settings. |
| format | Article |
| id | doaj-art-abf65b2f00cc42b18201b57f7b304d10 |
| institution | Kabale University |
| issn | 2590-0056 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Array |
| spelling | doaj-art-abf65b2f00cc42b18201b57f7b304d102025-02-06T05:12:40ZengElsevierArray2590-00562025-03-0125100376An attention based residual U-Net with swin transformer for brain MRI segmentationTazkia Mim Angona0M. Rubaiyat Hossain Mondal1Institute of Information and Communication Technology, Bangladesh University of Engineering and Technology (BUET), Dhaka, 1205, BangladeshCorresponding author.; Institute of Information and Communication Technology, Bangladesh University of Engineering and Technology (BUET), Dhaka, 1205, BangladeshBrain Tumors are a life-threatening cancer type. Due to the varied types and aggressive nature of these tumors, medical diagnostics faces significant challenges. Effective diagnosis and treatment planning depends on identifying the brain tumor areas from MRI images accurately. Traditional methods tend to use manual segmentation, which is costly, time consuming and prone to errors. Automated segmentation using deep learning approaches has shown potential in detecting tumor region. However, the complexity of the tumor areas which contain various shapes, sizes, fuzzy boundaries, makes this process difficult. Therefore, a robust automated segmentation method in brain tumor segmentation is required. In our paper, we present a hybrid model, 3-Dimension (3D) ResAttU-Net-Swin, which combines residual U-Net, attention mechanism and swin transformer. Residual blocks are introduced in the U-Net structure as encoder and decoder to avoid vanishing gradient problems and improve feature recovery. Attention-based skip connections are used to enhance the feature information transition between the encoder and decoder. The swin transformer obtains broad-scale features from the image data. The proposed hybrid model was evaluated on both the BraTS 2020 and BraTS 2019 datasets. It achieved an average Dice Similarity Coefficients (DSC) of 88.27 % and average Intersection over Union (IoU) of 79.93 % on BraTS 2020. On BraTS 2019, the model achieved an average DSC of 89.20 % and average IoU of 81.40 %. The model obtains higher DSC than the existing methods. The experiment result shows that the proposed methodology, 3D ResAttU-Net-Swin can be a potential for brain tumor segmentation in clinical settings.http://www.sciencedirect.com/science/article/pii/S2590005625000037Brain tumor segmentationMRIDeep learningConvolutional neural networksAttentionSwin transformer |
| spellingShingle | Tazkia Mim Angona M. Rubaiyat Hossain Mondal An attention based residual U-Net with swin transformer for brain MRI segmentation Array Brain tumor segmentation MRI Deep learning Convolutional neural networks Attention Swin transformer |
| title | An attention based residual U-Net with swin transformer for brain MRI segmentation |
| title_full | An attention based residual U-Net with swin transformer for brain MRI segmentation |
| title_fullStr | An attention based residual U-Net with swin transformer for brain MRI segmentation |
| title_full_unstemmed | An attention based residual U-Net with swin transformer for brain MRI segmentation |
| title_short | An attention based residual U-Net with swin transformer for brain MRI segmentation |
| title_sort | attention based residual u net with swin transformer for brain mri segmentation |
| topic | Brain tumor segmentation MRI Deep learning Convolutional neural networks Attention Swin transformer |
| url | http://www.sciencedirect.com/science/article/pii/S2590005625000037 |
| work_keys_str_mv | AT tazkiamimangona anattentionbasedresidualunetwithswintransformerforbrainmrisegmentation AT mrubaiyathossainmondal anattentionbasedresidualunetwithswintransformerforbrainmrisegmentation AT tazkiamimangona attentionbasedresidualunetwithswintransformerforbrainmrisegmentation AT mrubaiyathossainmondal attentionbasedresidualunetwithswintransformerforbrainmrisegmentation |