HRDecoder: High-Resolution Decoder Network for Fundus Image Lesion Segmentation
Ding, Ziyuan; Liang, Yixiong; Kan, Shichao; Liu, Qing (2024-10-03)
Avaa tiedosto
Sisältö avataan julkiseksi: 03.10.2025
Springer
03.10.2024
Ding, Z., Liang, Y., Kan, S., Liu, Q. (2024). HRDecoder: High-Resolution Decoder Network for Fundus Image Lesion Segmentation. In: Linguraru, M.G., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2024. MICCAI 2024. Lecture Notes in Computer Science, vol 15009. Springer, Cham. https://doi.org/10.1007/978-3-031-72114-4_32
https://rightsstatements.org/vocab/InC/1.0/
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG. This is a post-peer-review, pre-copyedit version of an article published in Medical Image Computing and Computer Assisted Intervention – MICCAI 2024: 27th International Conference, Marrakesh, Morocco, October 6–10, 2024, Proceedings, Part IX. The final authenticated version is available online at: https://doi.org/10.1007/978-3-031-72114-4_32
https://rightsstatements.org/vocab/InC/1.0/
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG. This is a post-peer-review, pre-copyedit version of an article published in Medical Image Computing and Computer Assisted Intervention – MICCAI 2024: 27th International Conference, Marrakesh, Morocco, October 6–10, 2024, Proceedings, Part IX. The final authenticated version is available online at: https://doi.org/10.1007/978-3-031-72114-4_32
https://rightsstatements.org/vocab/InC/1.0/
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:oulu-202412057077
https://urn.fi/URN:NBN:fi:oulu-202412057077
Tiivistelmä
Abstract
High resolution is crucial for precise segmentation in fundus images, yet handling high-resolution inputs incurs considerable GPU memory costs, with diminishing performance gains as overhead increases. To address this issue while tackling the challenge of segmenting tiny objects, recent studies have explored local-global feature fusion methods. These methods preserve fine details using local regions and capture context information from downscaled global images. However, the necessity of multiple forward passes inevitably incurs significant computational overhead, greatly affecting inference speed. In this paper, we propose HRDecoder, a simple High-Resolution Decoder network for fundus image segmentation. It integrates a High-resolution Representation Learning (HRL) module to capture fine-grained local features and a High-resolution Feature Fusion (HFF) module to fuse multi-scale local-global feature maps. HRDecoder effectively improves the overall segmentation accuracy of fundus lesions while maintaining reasonable memory usage, computational overhead, and inference speed. Experimental results on the IDRID and DDR datasets demonstrate the effectiveness of our method. The code is available at https://github.com/CVIU-CSU/HRDecoder.
High resolution is crucial for precise segmentation in fundus images, yet handling high-resolution inputs incurs considerable GPU memory costs, with diminishing performance gains as overhead increases. To address this issue while tackling the challenge of segmenting tiny objects, recent studies have explored local-global feature fusion methods. These methods preserve fine details using local regions and capture context information from downscaled global images. However, the necessity of multiple forward passes inevitably incurs significant computational overhead, greatly affecting inference speed. In this paper, we propose HRDecoder, a simple High-Resolution Decoder network for fundus image segmentation. It integrates a High-resolution Representation Learning (HRL) module to capture fine-grained local features and a High-resolution Feature Fusion (HFF) module to fuse multi-scale local-global feature maps. HRDecoder effectively improves the overall segmentation accuracy of fundus lesions while maintaining reasonable memory usage, computational overhead, and inference speed. Experimental results on the IDRID and DDR datasets demonstrate the effectiveness of our method. The code is available at https://github.com/CVIU-CSU/HRDecoder.
Kokoelmat
- Avoin saatavuus [38841]