Explainable attention based breast tumor segmentation using a combination of UNet, ResNet, DenseNet, and EfficientNet models
Abstract This study utilizes the Breast Ultrasound Image (BUSI) dataset to present a deep learning technique for breast tumor segmentation based on a modified UNet architecture. To improve segmentation accuracy, the model integrates attention mechanisms, such as the Convolutional Block Attention Mod...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-84504-y |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841544667957559296 |
|---|---|
| author | Shokofeh Anari Soroush Sadeghi Ghazaal Sheikhi Ramin Ranjbarzadeh Malika Bendechache |
| author_facet | Shokofeh Anari Soroush Sadeghi Ghazaal Sheikhi Ramin Ranjbarzadeh Malika Bendechache |
| author_sort | Shokofeh Anari |
| collection | DOAJ |
| description | Abstract This study utilizes the Breast Ultrasound Image (BUSI) dataset to present a deep learning technique for breast tumor segmentation based on a modified UNet architecture. To improve segmentation accuracy, the model integrates attention mechanisms, such as the Convolutional Block Attention Module (CBAM) and Non-Local Attention, with advanced encoder architectures, including ResNet, DenseNet, and EfficientNet. These attention mechanisms enable the model to focus more effectively on relevant tumor areas, resulting in significant performance improvements. Models incorporating attention mechanisms outperformed those without, as reflected in superior evaluation metrics. The effects of Dice Loss and Binary Cross-Entropy (BCE) Loss on the model’s performance were also analyzed. Dice Loss maximized the overlap between predicted and actual segmentation masks, leading to more precise boundary delineation, while BCE Loss achieved higher recall, improving the detection of tumor areas. Grad-CAM visualizations further demonstrated that attention-based models enhanced interpretability by accurately highlighting tumor areas. The findings denote that combining advanced encoder architectures, attention mechanisms, and the UNet framework can yield more reliable and accurate breast tumor segmentation. Future research will explore the use of multi-modal imaging, real-time deployment for clinical applications, and more advanced attention mechanisms to further improve segmentation performance. |
| format | Article |
| id | doaj-art-608f34dcdbcc491bae7dfe3ddea1eb3f |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-608f34dcdbcc491bae7dfe3ddea1eb3f2025-01-12T12:20:47ZengNature PortfolioScientific Reports2045-23222025-01-0115113910.1038/s41598-024-84504-yExplainable attention based breast tumor segmentation using a combination of UNet, ResNet, DenseNet, and EfficientNet modelsShokofeh Anari0Soroush Sadeghi1Ghazaal Sheikhi2Ramin Ranjbarzadeh3Malika Bendechache4Department of Accounting, Economic and Financial Sciences, Islamic Azad UniversitySchool of Electrical and Computer Engineering, University of TehranFinal International UniversitySchool of Computing of Computing, Faculty of Engineering and Computing, Dublin City UniversityADAPT Research Centre, School of Computer Science, University of GalwayAbstract This study utilizes the Breast Ultrasound Image (BUSI) dataset to present a deep learning technique for breast tumor segmentation based on a modified UNet architecture. To improve segmentation accuracy, the model integrates attention mechanisms, such as the Convolutional Block Attention Module (CBAM) and Non-Local Attention, with advanced encoder architectures, including ResNet, DenseNet, and EfficientNet. These attention mechanisms enable the model to focus more effectively on relevant tumor areas, resulting in significant performance improvements. Models incorporating attention mechanisms outperformed those without, as reflected in superior evaluation metrics. The effects of Dice Loss and Binary Cross-Entropy (BCE) Loss on the model’s performance were also analyzed. Dice Loss maximized the overlap between predicted and actual segmentation masks, leading to more precise boundary delineation, while BCE Loss achieved higher recall, improving the detection of tumor areas. Grad-CAM visualizations further demonstrated that attention-based models enhanced interpretability by accurately highlighting tumor areas. The findings denote that combining advanced encoder architectures, attention mechanisms, and the UNet framework can yield more reliable and accurate breast tumor segmentation. Future research will explore the use of multi-modal imaging, real-time deployment for clinical applications, and more advanced attention mechanisms to further improve segmentation performance.https://doi.org/10.1038/s41598-024-84504-yBreast tumor segmentationUNetGrad-CAMNon-local attentionAttention mechanisms |
| spellingShingle | Shokofeh Anari Soroush Sadeghi Ghazaal Sheikhi Ramin Ranjbarzadeh Malika Bendechache Explainable attention based breast tumor segmentation using a combination of UNet, ResNet, DenseNet, and EfficientNet models Scientific Reports Breast tumor segmentation UNet Grad-CAM Non-local attention Attention mechanisms |
| title | Explainable attention based breast tumor segmentation using a combination of UNet, ResNet, DenseNet, and EfficientNet models |
| title_full | Explainable attention based breast tumor segmentation using a combination of UNet, ResNet, DenseNet, and EfficientNet models |
| title_fullStr | Explainable attention based breast tumor segmentation using a combination of UNet, ResNet, DenseNet, and EfficientNet models |
| title_full_unstemmed | Explainable attention based breast tumor segmentation using a combination of UNet, ResNet, DenseNet, and EfficientNet models |
| title_short | Explainable attention based breast tumor segmentation using a combination of UNet, ResNet, DenseNet, and EfficientNet models |
| title_sort | explainable attention based breast tumor segmentation using a combination of unet resnet densenet and efficientnet models |
| topic | Breast tumor segmentation UNet Grad-CAM Non-local attention Attention mechanisms |
| url | https://doi.org/10.1038/s41598-024-84504-y |
| work_keys_str_mv | AT shokofehanari explainableattentionbasedbreasttumorsegmentationusingacombinationofunetresnetdensenetandefficientnetmodels AT soroushsadeghi explainableattentionbasedbreasttumorsegmentationusingacombinationofunetresnetdensenetandefficientnetmodels AT ghazaalsheikhi explainableattentionbasedbreasttumorsegmentationusingacombinationofunetresnetdensenetandefficientnetmodels AT raminranjbarzadeh explainableattentionbasedbreasttumorsegmentationusingacombinationofunetresnetdensenetandefficientnetmodels AT malikabendechache explainableattentionbasedbreasttumorsegmentationusingacombinationofunetresnetdensenetandefficientnetmodels |