FLDO-LKNet: An Efficient Method for Segmenting Stone Cells in Rubber Tree Bark with Robustness to Staining Differences and Morphological and Scale Changes
Plants · 16.07.2026 · 15 (14) · 2178
DOI: 10.3390/plants15142178 ↗Kurz gefasst
Fachartikel in der Zeitschrift Plants, online erschienen am 16.07.2026. Verfasst von Yeling Peng und 10 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer and Mathematics, Central South University of Forestry and Technology, Changsha 410004, China. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Chinese Academy of Tropical Agricultural Sciences.
Abstract (Originalsprache)
Stone cells are an important structural component of rubber tree bark and are closely associated with traits such as cracking propensity, bark hardness, stress tolerance and latex production. However, high-precision segmentation methods that are robust to staining variations, morphological diversity, and scale changes are still missing. To address these challenges in stone-cell histological images, such as the inconsistent staining intensity, the diverse shapes and sizes of cells, and the interference of cell debris, we proposed an automated semantic segmentation network called FLDO-LKNet, which formulates stone-cell delineation as a pixel-wise semantic segmentation task. Specifically, we introduce an LDFE module to recalibrate backbone features at the channel level, thereby mitigating the effects of staining differences. A KCFA attention mechanism is designed to better capture complex morphology and scale variation. In addition, we develop an FLDO optimization algorithm with a performance-feedback-based dynamic learning rate adjustment strategy to enhance robustness against training instability caused by debris interference. We further construct a dataset of 1084 stone-cell images collected from CATAS to support model training and evaluation. Experimental results demonstrate that FLDO-LKNet achieves 75.18% mIoU, 98.5% accuracy, and 82.21% sensitivity. Overall, as a dedicated semantic segmentation network, the proposed method enables high-precision pixel-level segmentation of stone cells, which may facilitate subsequent studies of stone-cell development and genetic functions and shows potential for agricultural applications.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Computer and Mathematics, Central South University of Forestry and Technology, Changsha 410004, China.
- State Centre for Rubber Breeding, Rubber Research Institute, Chinese Academy of Tropical Agricultural Sciences, Haikou 571101, China.
- College of Mechanical and Intelligent Manufacturing, Central South University of Forestry and Technology, Changsha 410004, China.
- College of Electronic Information and Physics, Central South University of Forestry and Technology, Changsha 410004, China.
- Department of Electronic Engineering, Tsinghua University, Beijing 100084, China.
ORCID-Profile: Yeling Peng, Yuanyuan Zhang, Meixi Pan
Förderung
- Chinese Academy of Tropical Agricultural Sciences
Zitieren
APA
Peng, Y., Zhang, Y., Zeng, H., Zeng, Y., Pan, M., Peng, Z., Liu, Y., Xia, Y., Wang, P., He, M., & Hu, Y. (2026). FLDO-LKNet: An Efficient Method for Segmenting Stone Cells in Rubber Tree Bark with Robustness to Staining Differences and Morphological and Scale Changes. Plants, 15(14), 2178. https://doi.org/10.3390/plants15142178
Vancouver
Peng Y, Zhang Y, Zeng H, Zeng Y, Pan M, Peng Z, et al. FLDO-LKNet: An Efficient Method for Segmenting Stone Cells in Rubber Tree Bark with Robustness to Staining Differences and Morphological and Scale Changes. Plants. 2026;15(14):2178. doi:10.3390/plants15142178
BibTeX
@article{Peng2026,
author = {Peng, Yeling and Zhang, Yuanyuan and Zeng, Hao and Zeng, Yiqing and Pan, Meixi and Peng, Zhongyang and Liu, Yang and Xia, Yongling and Wang, Peng and He, Mingfang and Hu, Yaowen},
title = {FLDO-LKNet: An Efficient Method for Segmenting Stone Cells in Rubber Tree Bark with Robustness to Staining Differences and Morphological and Scale Changes},
journal = {Plants},
year = {2026},
volume = {15},
number = {14},
pages = {2178},
doi = {10.3390/plants15142178}
}
EUVIMED