EUVIMEDEUVIMED entdecken
Open Access

Deep Learning‐Based Method for Damage Severity Grading of Black Shell Disease in Hong Kong Oyster ( Crassostrea hongkongensis ) Caused by Polydora Complex

Yuxiang Wang iD, Shengli Fu iD, Jingyue Zhang iD, Tuo Yao iD, Jie Lu iD, Haoyi Jiang, Jiadong Li iD, Lingtong Ye iD

Journal of Fish Diseases · 2026-09 · 49 (9)

DOI: 10.1111/jfd.70170 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Fish Diseases, online erschienen am 26.03.2026. Verfasst von Yuxiang Wang und 7 weiteren Autor:innen. Beteiligte Einrichtung: South China Sea Fisheries Research Institute, Chinese Academy of Fishery Sciences/Key Laboratory of Aquatic Product Processing, Ministry of Agricultu…. Hauptthemen laut MEDLINE: Deep Learning, Crassostrea, Polychaeta. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Hainan Province Science and Technology Special Fund, Central Public-interest Scientific Institution Basal Research Fund, South China Sea Fisheries Research Institute, CAFS, Fund of Key Laboratory of South China Sea Fishery Resources Exploitation & Utilization, Ministry of Agriculture and Rural Affairs, P. R. China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The Polydora complex is a globally widespread polychaete parasite known for secreting acidic substances to bore tunnels into oyster shells. This process leads to the formation of dark brown crusts on the inner shell surface, a condition commonly referred to as “black shell disease”. Not only does this disease degrade the quality of shellfish, but it also causes substantial mortalities, with the Hong Kong oyster ( Crassostrea hongkongensis ) being one of its primary hosts. In this study, an improved Deeplabv3+ semantic segmentation model integrated with an attention mechanism was developed to identify and classify the severity of Polydora ‐induced disease in oysters. First, through systematic data collection and enhancement techniques, a comprehensive dataset of 4590 shellfish disease images was constructed, fully meeting the training requirements of convolutional neural networks (CNNs). Second, transfer learning was employed by leveraging pre‐trained model weights, which validated the suitability of the self‐constructed dataset for model training. Comparative analysis of multiple segmentation models confirmed Deeplabv3+ as the optimal baseline, achieving a mean Intersection over Union (MioU) of 88.76% and an average precision of 94%. To further enhance performance, the Deeplabv3+ model was upgraded by incorporating the Convolutional Block Attention Module (CBAM), a dual‐module mechanism integrating channel and spatial attention. Compared to the original model, the improved version exhibited significant performance gains: MioU increased by 1.19%, average precision rose by 1.78%, and mFscore improved by 0.68%. Finally, an efficient and user‐friendly web‐based system was designed for grading and identifying Polydora disease severity. This system can accurately segment the diseased regions on the inner oyster shell, calculate their proportion relative to the total inner shell area, and precisely grade the disease severity, thereby providing robust technical support for the monitoring and prevention of oyster black shell disease.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningCrassostreaPolychaetaAnimalsAnimal ShellsImage Processing, Computer-AssistedHong Kong

Stichwörter der Autor:innen

Crassostrea hongkongensisPolydoradeep learningdisease diagnosis systemsemantic segmentation

Autor:innen und Institutionen

  • South China Sea Fisheries Research Institute, Chinese Academy of Fishery Sciences/Key Laboratory of Aquatic Product Processing, Ministry of Agriculture and Rural Affairs/Key Laboratory of South China Sea Fishery Resourc…
  • School of Fisheries, Guangdong Ocean University, Zhanjiang, P. R. China.
  • Sanya Tropical Fisheries Research Institute, Sanya, P. R. China.
  • College of Fisheries and Life Fishery, Shanghai Ocean University, Shanghai, P. R. China.
  • School of Life Sciences, South China Normal University, Guangzhou, P. R. China.

ORCID-Profile: Yuxiang Wang, Shengli Fu, Jingyue Zhang, Tuo Yao, Jie Lu, Jiadong Li, Lingtong Ye

Förderung

  • Hainan Province Science and Technology Special Fund
  • Central Public-interest Scientific Institution Basal Research Fund, South China Sea Fisheries Research Institute, CAFS
  • Fund of Key Laboratory of South China Sea Fishery Resources Exploitation & Utilization, Ministry of Agriculture and Rural Affairs, P. R. China
  • Hainan Provincial Natural Science Foundation of China
  • Shellfish & Algae Industry Innovation Team of Guangdong Modern Agricultural Technology System
  • the earmarked fund for CARS

Zitieren

APA

Wang, Y., Fu, S., Zhang, J., Yao, T., Lu, J., Jiang, H., Li, J., & Ye, L. (2026). Deep Learning‐Based Method for Damage Severity Grading of Black Shell Disease in Hong Kong Oyster ( Crassostrea hongkongensis ) Caused by Polydora Complex. Journal of Fish Diseases, 49(9). https://doi.org/10.1111/jfd.70170

Vancouver

Wang Y, Fu S, Zhang J, Yao T, Lu J, Jiang H, et al. Deep Learning‐Based Method for Damage Severity Grading of Black Shell Disease in Hong Kong Oyster ( Crassostrea hongkongensis ) Caused by Polydora Complex. Journal of Fish Diseases. 2026;49(9). doi:10.1111/jfd.70170

BibTeX
@article{Wang2026,
  author = {Wang, Yuxiang and Fu, Shengli and Zhang, Jingyue and Yao, Tuo and Lu, Jie and Jiang, Haoyi and Li, Jiadong and Ye, Lingtong},
  title = {Deep Learning‐Based Method for Damage Severity Grading of Black Shell Disease in Hong Kong Oyster ( Crassostrea hongkongensis ) Caused by Polydora Complex},
  journal = {Journal of Fish Diseases},
  year = {2026},
  volume = {49},
  number = {9},
  doi = {10.1111/jfd.70170}
}
Kostenlos starten →