PolyRes-Net: A Polyhierarchical Residual Network for Decoding Anatomical Complexity in Medical Image Segmentation
Medical image segmentation entails assigning each pixel in an image to its corresponding class label, a challenging task given the considerable anatomical variations in different cases. The encoder-decoder approach, exemplified by architectures such as U-Net, has emerged as the predominant framework...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10706916/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832583992005623808 |
|---|---|
| author | Amr Magdy Khalid N. Ismail Marghny H. Mohamed Mahmoud Hassaballah Haitham Mahmoud Mohammed M. Abdelsamea |
| author_facet | Amr Magdy Khalid N. Ismail Marghny H. Mohamed Mahmoud Hassaballah Haitham Mahmoud Mohammed M. Abdelsamea |
| author_sort | Amr Magdy |
| collection | DOAJ |
| description | Medical image segmentation entails assigning each pixel in an image to its corresponding class label, a challenging task given the considerable anatomical variations in different cases. The encoder-decoder approach, exemplified by architectures such as U-Net, has emerged as the predominant framework for medical imaging segmentation tasks. In recent years, diverse modifications to the U-Net architecture have been explored, giving rise to distinct models that showcase noteworthy results in comparison to the conventional U-Net design. In this paper, we introduce a novel architectural framework, which we refer to as the Polyhierarchical Residual Network (PolyRes-Net). Each encoder step comprises a Multi-Level Residual Block (MLR-block) designed to extract local and global feature maps. Furthermore, each decoder step is preceded by an attention gate, aiding in the extraction of the most salient features from the preceding layer, while skip connections correspond to the respective encoder steps. Lastly, the multi-scale feature aggregation (MSFA) block consolidates features from various decoder steps. Four benchamar datasets are used for evaluating our model: Krusir-SEG, CVC ClinicDB, 2018 Data Science Bowl, and ISIC-2018 skin lesion segmentation challenge dataset based on two metrics: the Mean Dice Similarity Coefficient (mDSC) and the Mean Intersection Over Union (mIOU). The results of the proposed PolyRes-Net outperformed the state-of-the-art segmentation methods. Specifically, PolyRes-Net achieves the highest mDSC scores of 91.02%, 91.80%, and 89.25% on CVC ClinicDB, 2018 Data Science Bowl, and ISIC-2018 skin lesion segmentation challenge dataset, respectively. Additionally, the highest mIOU scores are 85.60%, 85.32%, and 82.14% for the same datasets, further underscoring the efficacy of the proposed model. |
| format | Article |
| id | doaj-art-a086e78c12324ff6b1938856bd39ca60 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-a086e78c12324ff6b1938856bd39ca602025-01-28T00:01:43ZengIEEEIEEE Access2169-35362025-01-0113153121532310.1109/ACCESS.2024.347587710706916PolyRes-Net: A Polyhierarchical Residual Network for Decoding Anatomical Complexity in Medical Image SegmentationAmr Magdy0Khalid N. Ismail1https://orcid.org/0009-0005-0114-8407Marghny H. Mohamed2Mahmoud Hassaballah3Haitham Mahmoud4https://orcid.org/0000-0001-9313-8663Mohammed M. Abdelsamea5https://orcid.org/0009-0000-5677-6818Department of Computer Science, Faculty of Computers and Information, South Valley University, Qena, EgyptCollege of Computing, Birmingham City University, Birmingham, U.K.Department of Computer Science and Information Technology, Egypt-Japan University of Science and Technology, New Borg El-Arab City, Alexandria, EgyptDepartment of Computer Science, Faculty of Computers and Information, South Valley University, Qena, EgyptCollege of Computing, Birmingham City University, Birmingham, U.K.Department of Computer Science, University of Exeter, Exeter, U.K.Medical image segmentation entails assigning each pixel in an image to its corresponding class label, a challenging task given the considerable anatomical variations in different cases. The encoder-decoder approach, exemplified by architectures such as U-Net, has emerged as the predominant framework for medical imaging segmentation tasks. In recent years, diverse modifications to the U-Net architecture have been explored, giving rise to distinct models that showcase noteworthy results in comparison to the conventional U-Net design. In this paper, we introduce a novel architectural framework, which we refer to as the Polyhierarchical Residual Network (PolyRes-Net). Each encoder step comprises a Multi-Level Residual Block (MLR-block) designed to extract local and global feature maps. Furthermore, each decoder step is preceded by an attention gate, aiding in the extraction of the most salient features from the preceding layer, while skip connections correspond to the respective encoder steps. Lastly, the multi-scale feature aggregation (MSFA) block consolidates features from various decoder steps. Four benchamar datasets are used for evaluating our model: Krusir-SEG, CVC ClinicDB, 2018 Data Science Bowl, and ISIC-2018 skin lesion segmentation challenge dataset based on two metrics: the Mean Dice Similarity Coefficient (mDSC) and the Mean Intersection Over Union (mIOU). The results of the proposed PolyRes-Net outperformed the state-of-the-art segmentation methods. Specifically, PolyRes-Net achieves the highest mDSC scores of 91.02%, 91.80%, and 89.25% on CVC ClinicDB, 2018 Data Science Bowl, and ISIC-2018 skin lesion segmentation challenge dataset, respectively. Additionally, the highest mIOU scores are 85.60%, 85.32%, and 82.14% for the same datasets, further underscoring the efficacy of the proposed model.https://ieeexplore.ieee.org/document/10706916/Medical image segmentationmedical imagingdeep learning |
| spellingShingle | Amr Magdy Khalid N. Ismail Marghny H. Mohamed Mahmoud Hassaballah Haitham Mahmoud Mohammed M. Abdelsamea PolyRes-Net: A Polyhierarchical Residual Network for Decoding Anatomical Complexity in Medical Image Segmentation IEEE Access Medical image segmentation medical imaging deep learning |
| title | PolyRes-Net: A Polyhierarchical Residual Network for Decoding Anatomical Complexity in Medical Image Segmentation |
| title_full | PolyRes-Net: A Polyhierarchical Residual Network for Decoding Anatomical Complexity in Medical Image Segmentation |
| title_fullStr | PolyRes-Net: A Polyhierarchical Residual Network for Decoding Anatomical Complexity in Medical Image Segmentation |
| title_full_unstemmed | PolyRes-Net: A Polyhierarchical Residual Network for Decoding Anatomical Complexity in Medical Image Segmentation |
| title_short | PolyRes-Net: A Polyhierarchical Residual Network for Decoding Anatomical Complexity in Medical Image Segmentation |
| title_sort | polyres net a polyhierarchical residual network for decoding anatomical complexity in medical image segmentation |
| topic | Medical image segmentation medical imaging deep learning |
| url | https://ieeexplore.ieee.org/document/10706916/ |
| work_keys_str_mv | AT amrmagdy polyresnetapolyhierarchicalresidualnetworkfordecodinganatomicalcomplexityinmedicalimagesegmentation AT khalidnismail polyresnetapolyhierarchicalresidualnetworkfordecodinganatomicalcomplexityinmedicalimagesegmentation AT marghnyhmohamed polyresnetapolyhierarchicalresidualnetworkfordecodinganatomicalcomplexityinmedicalimagesegmentation AT mahmoudhassaballah polyresnetapolyhierarchicalresidualnetworkfordecodinganatomicalcomplexityinmedicalimagesegmentation AT haithammahmoud polyresnetapolyhierarchicalresidualnetworkfordecodinganatomicalcomplexityinmedicalimagesegmentation AT mohammedmabdelsamea polyresnetapolyhierarchicalresidualnetworkfordecodinganatomicalcomplexityinmedicalimagesegmentation |