Samplify
                    : a versatile tool for image‐based segmentation and annotation of seed abortion phenotypes

Heinrich Bente; Ronja Lea Jennifer Müller; Andreas Donath; Dirk Walther; Claudia Köhler

doi:10.1111/nph.70979

journal article Open Access Feb 15, 2026

Samplify : a versatile tool for image‐based segmentation and annotation of seed abortion phenotypes

Heinrich Bente

Ronja Lea Jennifer Müller Andreas Donath Dirk Walther

Claudia Köhler

New Phytologist Vol. 250 No. 3 pp. 1964-1978 · Wiley

View at Publisher Save 10.1111/nph.70979

Abstract

Summary

Automated seed phenotyping has wide applications in research and agriculture and relies on easy‐to‐use platforms and pipelines. Seed phenotyping in the model species
Arabidopsis thaliana
poses a significant challenge due to the large number of tiny seeds produced by individual plants, which are difficult to manually separate and count. Manual counting methods are time‐consuming and prone to user bias, particularly for subtle phenotypic changes.

To address these limitations, we developed
Samplify
, a scalable, automated pipeline for seed segmentation and classification by integrating classical image processing techniques with Meta's Segment Anything Model.

Samplify
effectively segments
Arabidopsis
seeds, even in dense clusters where conventional methods fail. To demonstrate its versatility, we quantified the seed abortion occurring in interploidy crossings in Arabidopsis, often referred to as ‘triploid block’.
Samplify
includes a random forest classifier trained on a set of computed seed shape features that enable the categorization of seeds into normal, partially collapsed, and fully collapsed seeds, automating the manual classification process.

The tool, designed as a command‐line application, significantly reduces manual annotation workload. Our validation across multiple datasets demonstrates high segmentation and classification reliability, making
Samplify
a valuable resource for the plant research community.

Topics

No keywords indexed for this article. Browse by subject →

References

57

[1]

10.1073/pnas.96.8.4710

[2]

The MADS-box transcription factor PHERES1 controls imprinting in the endosperm by binding to domesticated transposons

Rita A Batista, Jordi Moreno-Romero, Yichun Qiu et al.

eLife 10.7554/elife.50541

[3]

10.1016/j.anres.2017.12.002

[4]

10.1093/plphys/kiae050

[5]

10.1105/tpc.13.3.495

[6]

Bradski G (2008)

[7]

A Computational Approach to Edge Detection

John Canny

IEEE Transactions on Pattern Analysis and Machine... 10.1109/tpami.1986.4767851

[8]

10.1002/ajb2.16135

[9]

10.1371/journal.pbio.1000124

[10]

10.1371/journal.pbio.0060308

[11]

10.1016/j.cub.2015.12.032

[12]

GravesS PiephoH‐P SelzerL Dorai‐RajS.2019.multcompView: visualizations of paired comparisons. R package version 0.2.

[13]

10.1242/dev.077057

[14]

10.1186/1746-4811-7-3

[15]

10.1105/tpc.111.091793

[16]

Simultaneous Inference in General Parametric Models

Torsten Hothorn, Frank Bretz, Peter Westfall

Biometrical Journal 10.1002/bimj.200810425

[17]

10.3390/s24186117

[18]

10.1104/pp.16.01122

[19]

10.1016/j.compag.2022.107583

[20]

10.1016/j.media.2025.103547

[21]

10.1016/j.compag.2023.107740

[22]

Panoptic Segmentation

Alexander Kirillov, Kaiming He, Ross Girshick et al.

2019 IEEE/CVF Conference on Computer Vision and Pa... 10.1109/cvpr.2019.00963

[23]

10.1109/iccv51070.2023.00371

[24]

10.3389/fpls.2025.1539424

[25]

10.1016/j.tig.2009.12.006

[26]

10.1016/j.devcel.2013.08.006

[27]

10.1016/j.xplc.2023.100732

[28]

10.1007/s11694-020-00707-7

[29]

10.1073/pnas.1615123114

[30]

10.1016/j.media.2024.103370

[31]

Least-Squares Means: TheRPackagelsmeans

Russell V. Lenth

Journal of Statistical Software 10.18637/jss.v069.i01

[32]

10.1002/mp.17481

[33]

Segment anything in medical images

Jun Ma, Yuting He, Feifei Li et al.

Nature Communications 10.1038/s41467-024-44824-z

[34]

THE ORIGIN AND SIGNIFICANCE OF INTRASPECIFIC POLYPLOIDY: EXPERIMENTAL EVIDENCE FROM SOLANUM CHACOENSE

G. E. Marks

Evolution 10.1111/j.1558-5646.1966.tb03385.x

[35]

10.1038/s41588-017-0033-4

[36]

10.1038/s41598-020-79115-2

[37]

10.1186/s13007-020-00572-x

[38]

Scalable Parallel Programming with CUDA

John Nickolls, Ian Buck, Michael Garland et al.

Queue 10.1145/1365490.1365500

[39]

A Threshold Selection Method from Gray-Level Histograms

Nobuyuki Otsu

IEEE Transactions on Systems, Man, and Cybernetics 10.1109/tsmc.1979.4310076

[40]

Paszke A "Pytorch: An imperative style, high‐performance deep learning library" Advances in Neural Information Processing Systems (2019)

[41]

Pedregosa F "Scikit‐learn: Machine learning in Python" The Journal of Machine Learning Research (2011)

[42]

10.1007/s00066-024-02313-8

[43]

R Core Team (2020)

[44]

10.1111/nph.15642

[45]

10.1105/tpc.19.00047

[46]

Fiji: an open-source platform for biological-image analysis

Johannes Schindelin, Ignacio Arganda-Carreras, Erwin Frise et al.

Nature Methods 10.1038/nmeth.2019

[47]

10.1242/dev.125.17.3329

[48]

10.1104/pp.112.205120

[49]

10.1186/s13007-024-01268-2

[50]

Venables WN (2013)

Showing 50 of 57 references

Metrics

0

Citations

57

References

Details

Published: Feb 15, 2026
Vol/Issue: 250(3)
Pages: 1964-1978
License: View

Authors

H

Heinrich Bente