TY - GEN
T1 - Corneal Endothelial Cell Segmentation with Multiple Long-range Dependencies
AU - Zeng, Lingxi
AU - Zhang, Yinglin
AU - Higashita, Risa
AU - Liu, Jiang
N1 - Publisher Copyright:
© 2023 Copyright held by the owner/author(s).
PY - 2023/11/9
Y1 - 2023/11/9
N2 - Corneal endothelial cell segmentation is an important task in ophthalmology, but it is challenging due to variations in image characteristics across different datasets. Existing deep learning methods have limitations in capturing long-range dependencies that are critical for accurate segmentation. To address this issue, we propose a novel multiple long-range dependencies network (MLD-Net) that effectively incorporates different types of long-range dependency information to achieve robust segmentation across datasets. The network employs dilated convolutions and attention gates to capture spatial and layer-level dependencies, respectively. The entire network is densely connected, facilitating the sharing of long-range dependency information across multiple scales. We demonstrate the effectiveness of MLD-Net on four different corneal endothelium microscope image datasets: SREP, BiolmLab, Rodrep, and TM-EM3000. Our experimental results show that MLD-Net outperforms existing state-of-the-art methods, achieving robustness and high accuracy in corneal endothelial cell segmentation.
AB - Corneal endothelial cell segmentation is an important task in ophthalmology, but it is challenging due to variations in image characteristics across different datasets. Existing deep learning methods have limitations in capturing long-range dependencies that are critical for accurate segmentation. To address this issue, we propose a novel multiple long-range dependencies network (MLD-Net) that effectively incorporates different types of long-range dependency information to achieve robust segmentation across datasets. The network employs dilated convolutions and attention gates to capture spatial and layer-level dependencies, respectively. The entire network is densely connected, facilitating the sharing of long-range dependency information across multiple scales. We demonstrate the effectiveness of MLD-Net on four different corneal endothelium microscope image datasets: SREP, BiolmLab, Rodrep, and TM-EM3000. Our experimental results show that MLD-Net outperforms existing state-of-the-art methods, achieving robustness and high accuracy in corneal endothelial cell segmentation.
KW - Corneal Endothelial Cell
KW - Deep Learning
KW - Long-range Dependency
KW - Segmentation
UR - http://www.scopus.com/inward/record.url?scp=85187648123&partnerID=8YFLogxK
U2 - 10.1145/3637732.3637778
DO - 10.1145/3637732.3637778
M3 - Conference contribution
AN - SCOPUS:85187648123
T3 - ACM International Conference Proceeding Series
SP - 67
EP - 72
BT - ICBBE 2023 - Proceedings of the 2023 10th International Conference on Biomedical and Bioinformatics Engineering
PB - Association for Computing Machinery
T2 - 10th International Conference on Biomedical and Bioinformatics Engineering, ICBBE 2023
Y2 - 9 November 2023 through 12 November 2023
ER -