An Efficient Retinal Fluid Segmentation Network Based on Large Receptive Field Context Capture for Optical Coherence Tomography Images
Optical Coherence Tomography (OCT) is a crucial imaging modality for diagnosing and monitoring retinal diseases. However, the accurate segmentation of fluid regions and lesions remains challenging due to noise, low contrast, and blurred edges in OCT images. Although feature modeling with wide or glo...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/27/1/60 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588593916280832 |
|---|---|
| author | Hang Qi Weijiang Wang Hua Dang Yueyang Chen Minli Jia Xiaohua Wang |
| author_facet | Hang Qi Weijiang Wang Hua Dang Yueyang Chen Minli Jia Xiaohua Wang |
| author_sort | Hang Qi |
| collection | DOAJ |
| description | Optical Coherence Tomography (OCT) is a crucial imaging modality for diagnosing and monitoring retinal diseases. However, the accurate segmentation of fluid regions and lesions remains challenging due to noise, low contrast, and blurred edges in OCT images. Although feature modeling with wide or global receptive fields offers a feasible solution, it typically leads to significant computational overhead. To address these challenges, we propose LKMU-Lite, a lightweight U-shaped segmentation method tailored for retinal fluid segmentation. LKMU-Lite integrates a Decoupled Large Kernel Attention (DLKA) module that captures both local patterns and long-range dependencies, thereby enhancing feature representation. Additionally, it incorporates a Multi-scale Group Perception (MSGP) module that employs Dilated Convolutions with varying receptive field scales to effectively predict lesions of different shapes and sizes. Furthermore, a novel Aggregating-Shift decoder is proposed, reducing model complexity while preserving feature integrity. With only 1.02 million parameters and a computational complexity of 3.82 G FLOPs, LKMU-Lite achieves state-of-the-art performance across multiple metrics on the ICF and RETOUCH datasets, demonstrating both its efficiency and generalizability compared to existing methods. |
| format | Article |
| id | doaj-art-f64e824966c84dba8fac9830e05f9ca6 |
| institution | Kabale University |
| issn | 1099-4300 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj-art-f64e824966c84dba8fac9830e05f9ca62025-01-24T13:31:51ZengMDPI AGEntropy1099-43002025-01-012716010.3390/e27010060An Efficient Retinal Fluid Segmentation Network Based on Large Receptive Field Context Capture for Optical Coherence Tomography ImagesHang Qi0Weijiang Wang1Hua Dang2Yueyang Chen3Minli Jia4Xiaohua Wang5School of Integrated Circuits and Electronics, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Integrated Circuits and Electronics, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Integrated Circuits and Electronics, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Integrated Circuits and Electronics, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Integrated Circuits and Electronics, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Integrated Circuits and Electronics, Beijing Institute of Technology, Beijing 100081, ChinaOptical Coherence Tomography (OCT) is a crucial imaging modality for diagnosing and monitoring retinal diseases. However, the accurate segmentation of fluid regions and lesions remains challenging due to noise, low contrast, and blurred edges in OCT images. Although feature modeling with wide or global receptive fields offers a feasible solution, it typically leads to significant computational overhead. To address these challenges, we propose LKMU-Lite, a lightweight U-shaped segmentation method tailored for retinal fluid segmentation. LKMU-Lite integrates a Decoupled Large Kernel Attention (DLKA) module that captures both local patterns and long-range dependencies, thereby enhancing feature representation. Additionally, it incorporates a Multi-scale Group Perception (MSGP) module that employs Dilated Convolutions with varying receptive field scales to effectively predict lesions of different shapes and sizes. Furthermore, a novel Aggregating-Shift decoder is proposed, reducing model complexity while preserving feature integrity. With only 1.02 million parameters and a computational complexity of 3.82 G FLOPs, LKMU-Lite achieves state-of-the-art performance across multiple metrics on the ICF and RETOUCH datasets, demonstrating both its efficiency and generalizability compared to existing methods.https://www.mdpi.com/1099-4300/27/1/60optical coherence tomographylarge kernel attentionmulti-scale perceptionlightweightretinal fluid segmentationdeep learning |
| spellingShingle | Hang Qi Weijiang Wang Hua Dang Yueyang Chen Minli Jia Xiaohua Wang An Efficient Retinal Fluid Segmentation Network Based on Large Receptive Field Context Capture for Optical Coherence Tomography Images Entropy optical coherence tomography large kernel attention multi-scale perception lightweight retinal fluid segmentation deep learning |
| title | An Efficient Retinal Fluid Segmentation Network Based on Large Receptive Field Context Capture for Optical Coherence Tomography Images |
| title_full | An Efficient Retinal Fluid Segmentation Network Based on Large Receptive Field Context Capture for Optical Coherence Tomography Images |
| title_fullStr | An Efficient Retinal Fluid Segmentation Network Based on Large Receptive Field Context Capture for Optical Coherence Tomography Images |
| title_full_unstemmed | An Efficient Retinal Fluid Segmentation Network Based on Large Receptive Field Context Capture for Optical Coherence Tomography Images |
| title_short | An Efficient Retinal Fluid Segmentation Network Based on Large Receptive Field Context Capture for Optical Coherence Tomography Images |
| title_sort | efficient retinal fluid segmentation network based on large receptive field context capture for optical coherence tomography images |
| topic | optical coherence tomography large kernel attention multi-scale perception lightweight retinal fluid segmentation deep learning |
| url | https://www.mdpi.com/1099-4300/27/1/60 |
| work_keys_str_mv | AT hangqi anefficientretinalfluidsegmentationnetworkbasedonlargereceptivefieldcontextcaptureforopticalcoherencetomographyimages AT weijiangwang anefficientretinalfluidsegmentationnetworkbasedonlargereceptivefieldcontextcaptureforopticalcoherencetomographyimages AT huadang anefficientretinalfluidsegmentationnetworkbasedonlargereceptivefieldcontextcaptureforopticalcoherencetomographyimages AT yueyangchen anefficientretinalfluidsegmentationnetworkbasedonlargereceptivefieldcontextcaptureforopticalcoherencetomographyimages AT minlijia anefficientretinalfluidsegmentationnetworkbasedonlargereceptivefieldcontextcaptureforopticalcoherencetomographyimages AT xiaohuawang anefficientretinalfluidsegmentationnetworkbasedonlargereceptivefieldcontextcaptureforopticalcoherencetomographyimages AT hangqi efficientretinalfluidsegmentationnetworkbasedonlargereceptivefieldcontextcaptureforopticalcoherencetomographyimages AT weijiangwang efficientretinalfluidsegmentationnetworkbasedonlargereceptivefieldcontextcaptureforopticalcoherencetomographyimages AT huadang efficientretinalfluidsegmentationnetworkbasedonlargereceptivefieldcontextcaptureforopticalcoherencetomographyimages AT yueyangchen efficientretinalfluidsegmentationnetworkbasedonlargereceptivefieldcontextcaptureforopticalcoherencetomographyimages AT minlijia efficientretinalfluidsegmentationnetworkbasedonlargereceptivefieldcontextcaptureforopticalcoherencetomographyimages AT xiaohuawang efficientretinalfluidsegmentationnetworkbasedonlargereceptivefieldcontextcaptureforopticalcoherencetomographyimages |