Deep aerenchyma: a transformer-based pipeline for scalable phenotyping of rice root aerenchyma lacunae across environments
Abstract
Background: Quantification of rice root anatomical traits such as cortical aerenchyma lacunae is key to understanding rice adaptation to diverse water regimes and to support climate-smart breeding. Aerenchyma lacunae contributes to rice internal gas transport and influences methane emissions from flooded systems and can also limit rice water conductivity. It could be an interesting anatomical trait for breeding, however, large-scale anatomical phenotyping remains limited because manual analysis of root cross-sections is labor-intensive, subjective, and difficult to scale across heterogeneous imaging conditions. Existing pipelines often require parameter tuning and do not generalize well across environments. Results: We developed a deep learning pipeline based on a vision transformer architecture to automatically segment rice root cross-sections and quantify cortical aerenchyma lacunae. The model was trained on 1,760 annotated images collected across multiple countries, growth stages, cultivation systems, and experimental contexts, using a collaboratively defined annotation protocol. The final model achieved high segmentation accuracy, with mean intersection over union values exceeding 0.92 for cortical tissues and lacunae. Quantification of the lacuna-to-cortex ratio showed strong agreement with manual annotations, with a coefficient of determination of 0.98 on an independent test set. An independent expert review indicated that model predictions were at least as consistent as manual annotations and reduced large annotation inconsistencies. The pipeline is released as open-source software and includes an interactive online demonstrator, and is accompanied by an online test dataset to support testing and reproducibility. Application across six experimental use cases revealed reproducible differences in aerenchyma lacunae across genotypes, water regimes, environments, and developmental stages. Conclusions: This work provides a robust, scalable, and transferable tool for automated root anatomical phenotyping under heterogeneous experimental conditions. Transformer-based segmentation enables consistent and high-throughput quantification of lacunae, facilitating integration of these anatomical traits into breeding, physiological studies, and climate-smart crop improvement programs.
Related
- Vision Transformers Enable Advanced Plant Phenotyping in Controlled Environments
- Identification of potential donors for bruchid (Callosobruchus maculatus) resistance in blackgram through multi-environments phenotyping and biochemical profiling
- A robust and scalable image analysis framework for phenotyping human thoracic aorta
- A high-throughput UAV millimetric imaging pipeline for plant density phenotyping reveals high heritability in wheat-pea sole crops and intercrops.
- EXCON: a scalable, reproducible Nextflow pipeline for CAFE-based gene EXpansion and CONtraction analysis
BibTeX
@article{atef2026deep,
title = {{Deep aerenchyma: a transformer-based pipeline for scalable phenotyping of rice root aerenchyma lacunae across environments}},
author = {Hani Atef and Laura Fierro-Dominguez and Paula Andrea Lozano-Montaña and Sergi Navarro Sanz and Julie Bals and Benoît Clerget and Christophe Perin and Maria Camila Rebolledo and Romain Fernandez},
journal = {Plant Methods},
year = {2026},
month = jun,
doi = {10.1186/s13007-026-01546-1},
url = {https://hal.inrae.fr/hal-05761345v1},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Deep aerenchyma: a transformer-based pipeline for scalable phenotyping of rice root aerenchyma lacunae across environments
AU - Hani Atef
AU - Laura Fierro-Dominguez
AU - Paula Andrea Lozano-Montaña
AU - Sergi Navarro Sanz
AU - Julie Bals
AU - Benoît Clerget
AU - Christophe Perin
AU - Maria Camila Rebolledo
AU - Romain Fernandez
PY - 2026
DA - 2026/06/30
JO - Plant Methods
DO - 10.1186/s13007-026-01546-1
UR - https://hal.inrae.fr/hal-05761345v1
AB - Background: Quantification of rice root anatomical traits such as cortical aerenchyma lacunae is key to understanding rice adaptation to diverse water regimes and to support climate-smart breeding. Aerenchyma lacunae contributes to rice internal gas transport and influences methane emissions from flooded systems and can also limit rice water conductivity. It could be an interesting anatomical trait for breeding, however, large-scale anatomical phenotyping remains limited because manual analysis of root cross-sections is labor-intensive, subjective, and difficult to scale across heterogeneous imaging conditions. Existing pipelines often require parameter tuning and do not generalize well across environments. Results: We developed a deep learning pipeline based on a vision transformer architecture to automatically segment rice root cross-sections and quantify cortical aerenchyma lacunae. The model was trained on 1,760 annotated images collected across multiple countries, growth stages, cultivation systems, and experimental contexts, using a collaboratively defined annotation protocol. The final model achieved high segmentation accuracy, with mean intersection over union values exceeding 0.92 for cortical tissues and lacunae. Quantification of the lacuna-to-cortex ratio showed strong agreement with manual annotations, with a coefficient of determination of 0.98 on an independent test set. An independent expert review indicated that model predictions were at least as consistent as manual annotations and reduced large annotation inconsistencies. The pipeline is released as open-source software and includes an interactive online demonstrator, and is accompanied by an online test dataset to support testing and reproducibility. Application across six experimental use cases revealed reproducible differences in aerenchyma lacunae across genotypes, water regimes, environments, and developmental stages. Conclusions: This work provides a robust, scalable, and transferable tool for automated root anatomical phenotyping under heterogeneous experimental conditions. Transformer-based segmentation enables consistent and high-throughput quantification of lacunae, facilitating integration of these anatomical traits into breeding, physiological studies, and climate-smart crop improvement programs.
SN - 1746-4811
ER -