Skip to content
DraconiticResearch
Search Sources API
186,086 studies31 sourcesUpdated 39 min ago
Peer-reviewedCC BYNature Communications

SAMJ: fast image annotation on ImageJ/Fiji via segment anything model

  • Carlos García-López-de-Haro1,2
  • Caterina Fuster-Barceló3,4
  • Curtis Rueden5
  • Jónathan Heras6
  • Vladimír Ulman7,8
  • Daniel Franco-Barranco9,10,11
  • Adrián Inés6
  • Kevin W. Eliceiri5
  • Jean‐Christophe Olivo‐Marín1,12,13
  • Jean-Yves Tinévez14
  • Daniel Sage15
  • Arrate Muñoz‐Barrutia16,17
17 affiliations
  1. 1Bioimage Analysis Unit, Institut Pasteur, Université Paris Cité, Paris, France
  2. 2Neuroscience and Life Sciences Department, Universidad Carlos III de Madrid, Getafe, Spain
  3. 3BioVisionCenter, University of Zurich, Zurich, Switzerland
  4. 4Bioengineering Department, Universidad Carlos III de Madrid, Leganes, Spain
  5. 5Center for Quantitative Cell Imaging, University of Wisconsin, Madison, USA
  6. 6Department of Mathematics and Computer Science, University of La Rioja, Logroño, Spain
  7. 7Central European Institute of Technology (CEITEC), Masaryk University, Brno, Czech Republic
  8. 8Centre for Biomedical Image Analysis, Masaryk University, Brno, Czech Republic
  9. 9Department of Physiology, Development and Neuroscience, University of Cambridge, Cambridge, UK
  10. 10Donostia International Physics Center (DIPC), San Sebastian, Spain
  11. 11MRC Laboratory of Molecular Biology, Cambridge, UK
  12. 12CNRS UMR 3691, Institut Pasteur, Paris, France
  13. 13Faculty of Health Sciences, Universidad Carlos III de Madrid, Getafe, Spain
  14. 14Image Analysis Hub, Institut Pasteur, Université Paris Cité, Paris, France
  15. 15Biomedical Imaging Group and Center for Imaging, Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland. [email protected]
  16. 16Bioengineering Division, Instituto de Investigación Sanitaria Gregorio Marañón, Madrid, Spain. [email protected]
  17. 17Neuroscience and Life Sciences Department, Universidad Carlos III de Madrid, Getafe, Spain. [email protected]
Open at sourcePDFDOICite

Abstract

Accurate image annotation is essential for training artificial intelligence (AI) systems in biomedical image analysis, enabling tasks such as cell detection, tissue quantification, and disease characterization. However, creating pixel-level annotations is a time-consuming and labor-intensive process that requires expert input, limiting the development and adoption of AI methods. Recent advances in foundation models, such as the Segment Anything Model (SAM), enable interactive object segmentation from simple user prompts, but their integration into widely used bioimage analysis platforms remains limited and often requires technical expertise. Here we show that SAMJ, a user-friendly plugin for ImageJ/Fiji, enables fast, interactive, and accurate image annotation on standard computers without requiring programming skills or specialized hardware. SAMJ integrates efficient SAM variants into a familiar graphical interface, allowing users to delineate objects in large scientific images in real time using simple clicks or bounding boxes. This approach significantly reduces annotation effort, accelerates dataset creation, and broadens access to advanced AI-assisted annotation tools for the biomedical research community.

Related

  1. Examining the Atypical Structure Adopted by the 37-51 Segment of α-synuclein in the Early Stage of Aggregation
    A. Guzzo, P. Delarue, K. Kachlishvili +3
    bioRxivPreprintAll rights reservedFull textBiophysicsbioRxiv
  2. Efficient evidence-based genome annotation with EviAnn
    Aleksey V. Zimin, Daniela Puiu, Mihaela Pertea +2
    Nature MethodsPeer-reviewedLicence not statedFull text23 citedMolecular biology & gene regulationOpenAlex
  3. scBOA: Bayesian optimization of single-cell analysis pipelines for robust annotation and discovery
    Qiang Su, Yi Long, Fuyu Duan +1
    Nature CommunicationsPeer-reviewedCC BY-NC-ND 4.0Full textMolecular biology & gene regulationCrossref
  4. Identification and bioinformatic functional annotation of circRNAs mediating phenotypic differences in hair follicle cycling of Jinlan cashmere goats
    Li Zhang, Liqi Guo, Qishan Wang +5
    BMC GenomicsPeer-reviewedCC BY-NC-ND 4.0Molecular biology & gene regulationCrossref
  5. LLM-based cell type annotation harmonization across single-cell studies using GCTHarmony.
    Xingyuan Zhang, Zhicheng Ji
    Genome biologyPeer-reviewedCC BYFull textMolecular biology & gene regulationEurope PMCPMC

Cite

BibTeXRIS
BibTeX
@article{garcialopezdeharo2026samj,
  title = {{SAMJ: fast image annotation on ImageJ/Fiji via segment anything model}},
  author = {Carlos García-López-de-Haro and Caterina Fuster-Barceló and Curtis Rueden and Jónathan Heras and Vladimír Ulman and Daniel Franco-Barranco and Adrián Inés and Kevin W. Eliceiri and Jean‐Christophe Olivo‐Marín and Jean-Yves Tinévez and Daniel Sage and Arrate Muñoz‐Barrutia},
  journal = {Nature Communications},
  year = {2026},
  month = jun,
  doi = {10.1038/s41467-026-71752-x},
  url = {https://doi.org/10.1038/s41467-026-71752-x},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - SAMJ: fast image annotation on ImageJ/Fiji via segment anything model
AU  - Carlos García-López-de-Haro
AU  - Caterina Fuster-Barceló
AU  - Curtis Rueden
AU  - Jónathan Heras
AU  - Vladimír Ulman
AU  - Daniel Franco-Barranco
AU  - Adrián Inés
AU  - Kevin W. Eliceiri
AU  - Jean‐Christophe Olivo‐Marín
AU  - Jean-Yves Tinévez
AU  - Daniel Sage
AU  - Arrate Muñoz‐Barrutia
PY  - 2026
DA  - 2026/06/18
JO  - Nature Communications
DO  - 10.1038/s41467-026-71752-x
UR  - https://doi.org/10.1038/s41467-026-71752-x
AB  - Accurate image annotation is essential for training artificial intelligence (AI) systems in biomedical image analysis, enabling tasks such as cell detection, tissue quantification, and disease characterization. However, creating pixel-level annotations is a time-consuming and labor-intensive process that requires expert input, limiting the development and adoption of AI methods. Recent advances in foundation models, such as the Segment Anything Model (SAM), enable interactive object segmentation from simple user prompts, but their integration into widely used bioimage analysis platforms remains limited and often requires technical expertise. Here we show that SAMJ, a user-friendly plugin for ImageJ/Fiji, enables fast, interactive, and accurate image annotation on standard computers without requiring programming skills or specialized hardware. SAMJ integrates efficient SAM variants into a familiar graphical interface, allowing users to delineate objects in large scientific images in real time using simple clicks or bounding boxes. This approach significantly reduces annotation effort, accelerates dataset creation, and broadens access to advanced AI-assisted annotation tools for the biomedical research community.
SN  - 2041-1723
ER  -