Authors
Alex Abbey, Yasmine Meroz
Published in
Journal of experimental botany. Sep 25, 2026. Epub Sep 25, 2026.
Abstract
Quantitative studies of plant growth and environmental responses increasingly rely on time-series imaging, yet automated segmentation remains challenging due to continuous growth, large non-rigid morphological change, and frequent self-occlusion. Traditional image-processing pipelines and task-specific deep learning models often require extensive annotated datasets and retraining, limiting portability across species, developmental stages, and imaging conditions. Here we present SAP (Segment Any Plant), a plant-focused framework that leverages the pretrained Segment Anything Model 2 (SAM2) to enable few-shot, training-free segmentation of plant time-series imagery. SAP integrates interactive prompting, automated temporal mask propagation, and centerline extraction within a web-based interface, allowing users to move from raw images to quantitative descriptors of organ shape, growth, and dynamics without programming expertise. Across multiple systems, including Arabidopsis thaliana rosette development, root growth, sunflower gravitropism, and confocal root microscopy, SAP achieves high segmentation accuracy on macroscopic organs (mean IoU 0.89-0.93) and pixel-level centerline precision from single-frame prompting, with lower but promising accuracy at the cellular scale (confocal, mean IoU 0.75) that we report as a proof of concept. By reducing the need for task-specific retraining, SAP provides a transferable framework for reproducible time-series phenotyping across diverse experimental contexts.
PMID:
42788609
Bibliographic data and abstract were imported from PubMed on 25 Sep 2026.
Read full publication at:
Please sign in
to see all details.
Advertisement
Stats
- Recommendations n/a n/a positive of 0 vote(s)
- Views 16
- Comments 0