Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jul 5, 2026

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

Biom3d, a modular framework to host and develop 3D segmentation methods.

Guillaume Mougeot1, Sami Safarbati2, Hervé Alégot3

  • 1UCA - Université Clermont Auvergne, CNRS - Centre National de la Recherche Scientifique UMR6293, INSERM - Institut National de la Santé et de la Recherche Médicale U1103, Facultés de Médecine et de Pharmacie, TSA 50400, 28 Place Henri Dunant, 63001 Clermont-Ferrand, France; IP - Institut Pascal, UCA - Université Clermont Auvergne, CNRS - Centre National de la Recherche Scientifique UMR6602, Campus Universitaire des Cézeaux, 4 avenue Blaise Pascal, TSA 60026 / CS 60026, 63178 Aubière Cedex, France; Oxford Brookes University, Department for Biological and Medical Sciences, Headington Campus, Gipsy Lane, Oxford OX3 0BP, Royaume-Uni, UK; Aarhus University, Department of Ecoscience, C.F. Møllers Allé 8, Building 1110, 8000 Aarhus C, Denmark.

Medical Image Analysis
|July 3, 2026
PubMed

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Replication-independent eviction of the histone variant H2B.8 reveals chromatin reprogramming during seed imbibition.

Nature communications·2026
Same author

Built different: ER cisternae formed by the Arabidopsis Lunapark proteins differ in ultrastructure and affect ER-Golgi transport.

The New phytologist·2026
Same author

Sorting Fusarium graminearum core effector candidates shows multiple fungal proteins that target the wheat cell nucleus during Fusarium head blight.

Journal of experimental botany·2026
Same author

Enhanced lysosomal glycogen breakdown is associated with liver tumorigenesis in glycogen storage disease type III.

JHEP reports : innovation in hepatology·2026
Same author

CRESCENT, a comprehensive RNA-Seq expression, splicing, and coding/non-coding element network tool.

BMC bioinformatics·2026
Same author

The mid-SUN-POD1 complex ensures the structural integrity of ER bodies required for herbivore defense in Arabidopsis.

The New phytologist·2025
Same journal

HiVLR: Hierarchical Vision-Language Reasoning for interpretable zero-shot radiography image understanding.

Medical image analysis·2026
Same journal

FAA-Net: Fetal abdominal anomaly diagnosis in prenatal ultrasound via LLM-enhanced multi-instance learning.

Medical image analysis·2026
Same journal

Wavelet-inspired diffusion model with near-field constraint for real-time echocardiography dehazing.

Medical image analysis·2026
Same journal

Co-assistant networks by pathology foundation model and convolutional neural network for gigapixel whole slide image analysis.

Medical image analysis·2026
Same journal

MBAS2024: A large-scale benchmark for multi-class bi-atrial segmentation in multi-center contrast-enhanced MRIs.

Medical image analysis·2026
Same journal

Respiratory motion augmentation for personalized super-resolution (RMApSR) of 3D cine MR images in MRI-guided radiotherapy.

Medical image analysis·2026
See all related articles
Summary
This summary is machine-generated.

Biom3d is a new AI framework for bioimage segmentation, making advanced tools accessible and reproducible for researchers. It ensures interoperability and competes with state-of-the-art methods for 2D and 3D image analysis.

Area of Science:

  • Bioimaging
  • Artificial Intelligence
  • Computational Biology

Background:

  • AI-powered bioimage segmentation tools offer advanced capabilities but suffer from high technical overhead, limiting accessibility for researchers.
  • Bridging the gap between AI developers and the bioimaging community requires user-friendly, reproducible, and interoperable frameworks.

Purpose of the Study:

  • To introduce Biom3d, a modular, PyTorch-based framework designed to simplify the creation of reproducible and interoperable 2D and 3D bioimage segmentation pipelines.
  • To ensure adherence to FAIR data principles within the framework for enhanced data management and reusability.

Main Methods:

  • Developed a modular architecture with seven core module types for fine-grained control over segmentation pipelines.
  • Integrated default configuration (nnCore) for automatic optimization of pipelines based on dataset characteristics.
Keywords:
3d segmentationDeep learning frameworkFAIROMERO

More Related Videos

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells
12:49

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells

Published on: September 28, 2019

Related Experiment Videos

Last Updated: Jul 5, 2026

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells
12:49

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells

Published on: September 28, 2019

  • Ensured interoperability by demonstrating seamless substitution of existing models, such as transformer-based MONAI models.

    • Main Results:

    • Biom3d exhibits high engineering quality, characterized by low module complexity and high modularity.
    • The nnCore configuration autoconfigures optimal pipelines, achieving performance comparable to state-of-the-art 3D segmentation methods.
    • Biom3d outperforms classical tools like NucleusJ/NODeJ and matches the robustness of nnU-Net across various imaging modalities.

    Conclusions:

    • Biom3d provides a sustainable and extensible solution for building, sharing, and reusing advanced bioimage analysis pipelines.
    • The framework's accessibility through multiple interfaces (GUI, Notebook, CLI, Docker, Python library) and OMERO compatibility enhances its utility for the bioimaging community.
    • Biom3d facilitates reproducible computation, including execution on High-Performance Computing (HPC) servers.