Deep-learning histopathradiomics enables high-throughput quantification of pollutant-induced tissue injury in marine mussels
Environmental Pollution · 2026-12 · 411 · 129285
DOI: 10.1016/j.envpol.2026.129285 ↗Kurz gefasst
Fachartikel in der Zeitschrift Environmental Pollution, 2026-12. Verfasst von Ruoxuan Zhao und 7 weiteren Autor:innen. Beteiligte Einrichtung: Ocean College, Zhejiang University, Zhoushan, 316000, China. Hauptthemen laut MEDLINE: Water Pollutants, Chemical, Mytilus, Deep Learning, Environmental Monitoring. Die Arbeit nennt 84 Literaturangaben. Gefördert von: Zhejiang University, National Natural Science Foundation of China.
Abstract (Originalsprache)
Quantitative tissue-level biomarkers are important for assessing pollutant-induced biological effects, yet conventional histopathology remains largely manual, low-throughput, and observer-dependent. We developed a deep learning-based histopathradiomics workflow for high-throughput morphometric quantification in the marine mussel Mytilus galloprovincialis. Benzo[a]pyrene (BaP) was used as a benchmark stressor to provide a biologically defined tissue-injury context for workflow evaluation. An optimized Res-UNet achieved Dice coefficients of 0.9159 ± 0.0788 for gill epithelium and 0.8687 ± 0.1612 for digestive tubule walls, enabling automated quantification of 1264 gill filaments and 1437 digestive tubules within minutes. The resulting gill epithelial area and digestive tubule wall area showed injury-related patterns consistent with semi-quantitative pathology and manual thickness-based morphometry. The current binary framework focuses on predefined structural endpoints rather than the full spectrum of histopathological lesions. Without further model optimization, application to an independent sulfamethoxazole (SMX) + BaP dataset retained comparable tissue-injury patterns across exposure scenarios and independent experimental and histological batches, supporting cross-scenario applicability. Overall, this workflow transforms established histopathological biomarkers into scalable and biologically interpretable morphometric endpoints, while reducing repeated manual delineation and providing a practical basis for standardized tissue-level effect assessment in marine sentinel organisms.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Ocean College, Zhejiang University, Zhoushan, 316000, China.
- Shaoxing People's Hospital, School of Medicine, Shaoxing University, Shaoxing, 312000, China.
- Ocean College, Zhejiang University, Zhoushan, 316000, China. Electronic address: diyanan@zju.edu.cn.
Förderung
- Zhejiang University
- National Natural Science Foundation of China
Zitieren
APA
Zhao, R., Xu, J., Fang, Q., Chen, S., Li, T., Li, S., Lu, L., & Di, Y. (2026). Deep-learning histopathradiomics enables high-throughput quantification of pollutant-induced tissue injury in marine mussels. Environmental Pollution, 411, 129285. https://doi.org/10.1016/j.envpol.2026.129285
Vancouver
Zhao R, Xu J, Fang Q, Chen S, Li T, Li S, et al. Deep-learning histopathradiomics enables high-throughput quantification of pollutant-induced tissue injury in marine mussels. Environmental Pollution. 2026;411:129285. doi:10.1016/j.envpol.2026.129285
BibTeX
@article{Zhao2026,
author = {Zhao, Ruoxuan and Xu, Jianzhou and Fang, Qing and Chen, Siyu and Li, Taiwei and Li, Shuimei and Lu, Liangying and Di, Yanan},
title = {Deep-learning histopathradiomics enables high-throughput quantification of pollutant-induced tissue injury in marine mussels},
journal = {Environmental Pollution},
year = {2026},
volume = {411},
pages = {129285},
doi = {10.1016/j.envpol.2026.129285}
}
EUVIMED