DEAF-Net: Detail-Enhanced Attention Feature Fusion Network for Retinal Vessel Segmentation
Journal of Imaging Informatics in Medicine · 05.08.2024 · 38 (1) · 496-519
DOI: 10.1007/s10278-024-01207-6 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Imaging Informatics in Medicine, online erschienen am 05.08.2024. Verfasst von Pengfei Cai und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic Engineering, Tianjin University of Technology and Education, Tianjin, 300222, China. Hauptthemen laut MEDLINE: Retinal Vessels, Neural Networks, Computer, Image Processing, Computer-Assisted, Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Natural Science Research Project of Tianjin Education Commission, National Natural Science Foundation of China.
Abstract (Originalsprache)
Retinal vessel segmentation is crucial for the diagnosis of ophthalmic and cardiovascular diseases. However, retinal vessels are densely and irregularly distributed, with many capillaries blending into the background, and exhibit low contrast. Moreover, the encoder-decoder-based network for retinal vessel segmentation suffers from irreversible loss of detailed features due to multiple encoding and decoding, leading to incorrect segmentation of the vessels. Meanwhile, the single-dimensional attention mechanisms possess limitations, neglecting the importance of multidimensional features. To solve these issues, in this paper, we propose a detail-enhanced attention feature fusion network (DEAF-Net) for retinal vessel segmentation. First, the detail-enhanced residual block (DERB) module is proposed to strengthen the capacity for detailed representation, ensuring that intricate features are efficiently maintained during the segmentation of delicate vessels. Second, the multidimensional collaborative attention encoder (MCAE) module is proposed to optimize the extraction of multidimensional information. Then, the dynamic decoder (DYD) module is introduced to preserve spatial information during the decoding process and reduce the information loss caused by upsampling operations. Finally, the proposed detail-enhanced feature fusion (DEFF) module composed of DERB, MCAE and DYD modules fuses feature maps from both encoding and decoding and achieves effective aggregation of multi-scale contextual information. The experiments conducted on the datasets of DRIVE, CHASEDB1, and STARE, achieving Sen of 0.8305, 0.8784, and 0.8654, and AUC of 0.9886, 0.9913, and 0.9911 on DRIVE, CHASEDB1, and STARE, respectively, demonstrate the performance of our proposed network, particularly in the segmentation of fine retinal vessels.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Electronic Engineering, Tianjin University of Technology and Education, Tianjin, 300222, China.
- School of Electronic Engineering, Tianjin University of Technology and Education, Tianjin, 300222, China. lby@tute.edu.cn.
- Tianjin Development Zone Jingnuohanhai Data Technology Co., Ltd, Tianjin, China. lby@tute.edu.cn.
- School of Mathematics, Tianjin University, Tianjin, 300072, China.
Förderung
- Natural Science Research Project of Tianjin Education Commission
- National Natural Science Foundation of China
Zitieren
APA
Cai, P., Li, B., Sun, G., Yang, B., Wang, X., Lv, C., & Yan, J. (2024). DEAF-Net: Detail-Enhanced Attention Feature Fusion Network for Retinal Vessel Segmentation. Journal of Imaging Informatics in Medicine, 38(1), 496-519. https://doi.org/10.1007/s10278-024-01207-6
Vancouver
Cai P, Li B, Sun G, Yang B, Wang X, Lv C, et al. DEAF-Net: Detail-Enhanced Attention Feature Fusion Network for Retinal Vessel Segmentation. Journal of Imaging Informatics in Medicine. 2024;38(1):496-519. doi:10.1007/s10278-024-01207-6
BibTeX
@article{Cai2024,
author = {Cai, Pengfei and Li, Biyuan and Sun, Gaowei and Yang, Bo and Wang, Xiuwei and Lv, Chunjie and Yan, Jun},
title = {DEAF-Net: Detail-Enhanced Attention Feature Fusion Network for Retinal Vessel Segmentation},
journal = {Journal of Imaging Informatics in Medicine},
year = {2024},
volume = {38},
number = {1},
pages = {496--519},
doi = {10.1007/s10278-024-01207-6}
}
EUVIMED