AFN-Net: Adaptive Fusion Nucleus Segmentation Network Based on Multi-Level U-Net
The task of nucleus segmentation plays an important role in medical image analysis. However, due to the challenge of detecting small targets and complex boundaries in datasets, traditional methods often fail to achieve satisfactory results. Therefore, a novel nucleus segmentation method based on the...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/2/300 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587548685238272 |
|---|---|
| author | Ming Zhao Yimin Yang Bingxue Zhou Quan Wang Fu Li |
| author_facet | Ming Zhao Yimin Yang Bingxue Zhou Quan Wang Fu Li |
| author_sort | Ming Zhao |
| collection | DOAJ |
| description | The task of nucleus segmentation plays an important role in medical image analysis. However, due to the challenge of detecting small targets and complex boundaries in datasets, traditional methods often fail to achieve satisfactory results. Therefore, a novel nucleus segmentation method based on the U-Net architecture is proposed to overcome this issue. Firstly, we introduce a Weighted Feature Enhancement Unit (WFEU) in the encoder decoder fusion stage of U-Net. By assigning learnable weights to different feature maps, the network can adaptively enhance key features and suppress irrelevant or secondary features, thus maintaining high-precision segmentation performance in complex backgrounds. In addition, to further improve the performance of the network under different resolution features, we designed a Double-Stage Channel Optimization Module (DSCOM) in the first two layers of the model. This DSCOM effectively preserves high-resolution information and improves the segmentation accuracy of small targets and boundary regions through multi-level convolution operations and channel optimization. Finally, we proposed an Adaptive Fusion Loss Module (AFLM) that effectively balances different lossy targets by dynamically adjusting weights, thereby further improving the model’s performance in segmentation region consistency and boundary accuracy while maintaining classification accuracy. The experimental results on 2018 Data Science Bowl demonstrate that, compared to state-of-the-art segmentation models, our method shows significant advantages in multiple key metrics. Specifically, our model achieved an IOU score of 0.8660 and a Dice score of 0.9216, with a model parameter size of only 7.81 M. These results illustrate that the method proposed in this paper not only excels in the segmentation of complex shapes and small targets but also significantly enhances overall performance at lower computational costs. This research offers new insights and references for model design in future medical image segmentation tasks. |
| format | Article |
| id | doaj-art-18bfc71e739b45aaaf4edb8b56448bb1 |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-18bfc71e739b45aaaf4edb8b56448bb12025-01-24T13:48:25ZengMDPI AGSensors1424-82202025-01-0125230010.3390/s25020300AFN-Net: Adaptive Fusion Nucleus Segmentation Network Based on Multi-Level U-NetMing Zhao0Yimin Yang1Bingxue Zhou2Quan Wang3Fu Li4School of Computer Science, Yangtze University, Jingzhou 434025, ChinaSchool of Computer Science, Yangtze University, Jingzhou 434025, ChinaSchool of Computer Science, Yangtze University, Jingzhou 434025, ChinaSchool of Internet of Things Engineering, Wuxi University, Wuxi 214105, ChinaSchool of Internet of Things Engineering, Wuxi University, Wuxi 214105, ChinaThe task of nucleus segmentation plays an important role in medical image analysis. However, due to the challenge of detecting small targets and complex boundaries in datasets, traditional methods often fail to achieve satisfactory results. Therefore, a novel nucleus segmentation method based on the U-Net architecture is proposed to overcome this issue. Firstly, we introduce a Weighted Feature Enhancement Unit (WFEU) in the encoder decoder fusion stage of U-Net. By assigning learnable weights to different feature maps, the network can adaptively enhance key features and suppress irrelevant or secondary features, thus maintaining high-precision segmentation performance in complex backgrounds. In addition, to further improve the performance of the network under different resolution features, we designed a Double-Stage Channel Optimization Module (DSCOM) in the first two layers of the model. This DSCOM effectively preserves high-resolution information and improves the segmentation accuracy of small targets and boundary regions through multi-level convolution operations and channel optimization. Finally, we proposed an Adaptive Fusion Loss Module (AFLM) that effectively balances different lossy targets by dynamically adjusting weights, thereby further improving the model’s performance in segmentation region consistency and boundary accuracy while maintaining classification accuracy. The experimental results on 2018 Data Science Bowl demonstrate that, compared to state-of-the-art segmentation models, our method shows significant advantages in multiple key metrics. Specifically, our model achieved an IOU score of 0.8660 and a Dice score of 0.9216, with a model parameter size of only 7.81 M. These results illustrate that the method proposed in this paper not only excels in the segmentation of complex shapes and small targets but also significantly enhances overall performance at lower computational costs. This research offers new insights and references for model design in future medical image segmentation tasks.https://www.mdpi.com/1424-8220/25/2/300U-Netmedical image segmentationsmall target segmentationfeature fusionloss function |
| spellingShingle | Ming Zhao Yimin Yang Bingxue Zhou Quan Wang Fu Li AFN-Net: Adaptive Fusion Nucleus Segmentation Network Based on Multi-Level U-Net Sensors U-Net medical image segmentation small target segmentation feature fusion loss function |
| title | AFN-Net: Adaptive Fusion Nucleus Segmentation Network Based on Multi-Level U-Net |
| title_full | AFN-Net: Adaptive Fusion Nucleus Segmentation Network Based on Multi-Level U-Net |
| title_fullStr | AFN-Net: Adaptive Fusion Nucleus Segmentation Network Based on Multi-Level U-Net |
| title_full_unstemmed | AFN-Net: Adaptive Fusion Nucleus Segmentation Network Based on Multi-Level U-Net |
| title_short | AFN-Net: Adaptive Fusion Nucleus Segmentation Network Based on Multi-Level U-Net |
| title_sort | afn net adaptive fusion nucleus segmentation network based on multi level u net |
| topic | U-Net medical image segmentation small target segmentation feature fusion loss function |
| url | https://www.mdpi.com/1424-8220/25/2/300 |
| work_keys_str_mv | AT mingzhao afnnetadaptivefusionnucleussegmentationnetworkbasedonmultilevelunet AT yiminyang afnnetadaptivefusionnucleussegmentationnetworkbasedonmultilevelunet AT bingxuezhou afnnetadaptivefusionnucleussegmentationnetworkbasedonmultilevelunet AT quanwang afnnetadaptivefusionnucleussegmentationnetworkbasedonmultilevelunet AT fuli afnnetadaptivefusionnucleussegmentationnetworkbasedonmultilevelunet |