DA-UNet: A Direction-Aware U-Net for Leaf Vein Segmentation in Tissue-Cultured Plantlets
Electronics · 06.04.2026 · 15 (7) · 1531
DOI: 10.3390/electronics15071531 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 06.04.2026. Verfasst von Qiuze Wu und 3 weiteren Autor:innen. Die Arbeit nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
For the automation of Agrobacterium-mediated genetic transformation of tissue-cultured plantlets, accurate leaf vein segmentation is essential. The thin, low-contrast structure of leaf veins frequently leads to fragmented segmentation outputs, despite the proposal of various methodologies for vein segmentation. To address this issue, we propose Direction-Aware U-Net (DA-UNet), an improved U-Net architecture that incorporates a Direction-Aware Context Pooling (DACPool) module and Topology-aware Segmentation loss (TopoSeg loss). The DACPool module explicitly exploits vein orientation to aggregate directional contextual information, while the TopoSeg loss jointly optimizes pixel-level accuracy and topological continuity. DA-UNet achieves efficient leaf vein segmentation with improved continuity and structural integrity, according to evaluations on the self-constructed Tissue-Cultured Plantlet Vein Dataset 2025 (TCPVD2025). Comparative experiment results show that the improved model outperforms PSPNet, DeepLabV3+, U-Net, TransUNet, Swin-UNet, CCNet, and SegNeXt, as evidenced by Recall, Dice, and CONNECT scores of 71.35%, 69.08%, and −2.25, while maintaining competitive Precision of 66.98%. Ablation experiment results provide further evidence for the efficacy of the TopoSeg loss and the DACPool module. The results demonstrate the effectiveness of the proposed vein segmentation framework for generating outputs that are both accurate and structurally consistent, thus enabling reliable automated processes for plant genetic transformation.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Wu, Q., Yang, Q., Meng, D., & Yan, X. (2026). DA-UNet: A Direction-Aware U-Net for Leaf Vein Segmentation in Tissue-Cultured Plantlets. Electronics, 15(7), 1531. https://doi.org/10.3390/electronics15071531
Vancouver
Wu Q, Yang Q, Meng D, Yan X. DA-UNet: A Direction-Aware U-Net for Leaf Vein Segmentation in Tissue-Cultured Plantlets. Electronics. 2026;15(7):1531. doi:10.3390/electronics15071531
BibTeX
@article{Wu2026,
author = {Wu, Qiuze and Yang, Qing and Meng, Dong and Yan, Xiaofei},
title = {DA-UNet: A Direction-Aware U-Net for Leaf Vein Segmentation in Tissue-Cultured Plantlets},
journal = {Electronics},
year = {2026},
volume = {15},
number = {7},
pages = {1531},
doi = {10.3390/electronics15071531}
}
EUVIMED