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: Dec 1, 2025

Hybrid µCT-FMT imaging and image analysis
13:45

Hybrid µCT-FMT imaging and image analysis

Published on: June 4, 2015

13.5K

Deep learning-enabled multi-organ segmentation in whole-body mouse scans.

Oliver Schoppe1,2,3, Chenchen Pan4,5, Javier Coronel6,7

  • 1Department of Informatics, Technical University of Munich, Munich, Germany. oliver.schoppe@tum.de.

Nature Communications
|November 7, 2020
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

Ratio of Left Atrial and Ventricular Volume as New Marker of Atrial Cardiopathy and Stroke Risk.

Stroke·2026
Same author

A deep-learning framework reveals whole-body perturbations at cell level.

Nature·2026
Same author

Brain tumor segmentation in Sub-Saharan Africa patient population: The BraTS-Africa challenge.

Neuro-oncology advances·2026
Same author

Whole-mouse immunolabeling at cellular resolution for comprehensive 3D atlases.

Nature protocols·2026
Same author

The Ischemic Stroke Lesion Segmentation Challenge (ISLES)'24 Dataset: A Multimodal Stroke Imaging Dataset with Hyperacute CT, Acute Postinterventional MRI, and 3-month Clinical Outcomes.

Radiology. Artificial intelligence·2026
Same author

Pathogenic role of serpin B3-positive neutrophils in reinforcing thrombus stiffening during ischemic stroke.

Blood·2026
Summary

A new deep learning tool, AIMOS, automates organ segmentation in mouse imaging, significantly reducing time and improving accuracy. This open-source solution enhances research reproducibility and quantifies human bias in annotations.

Area of Science:

  • Biomedical imaging
  • Computational biology
  • Medical image analysis

Background:

  • Manual organ segmentation in mouse whole-body imaging is time-consuming and prone to errors.
  • Accurate organ segmentation is crucial for quantitative analysis in preclinical research.
  • Existing automated methods lack the speed and accuracy of advanced deep learning approaches.

Purpose of the Study:

  • To develop and validate AIMOS, a deep learning tool for rapid and accurate automatic organ and skeleton segmentation in mouse whole-body imaging.
  • To compare AIMOS performance against state-of-the-art methods and human experts.
  • To investigate and quantify human bias in expert annotations for segmentation tasks.

Main Methods:

  • Development of a deep learning model (AIMOS) for segmenting major organs (brain, lungs, heart, liver, kidneys, spleen, bladder, stomach, intestine) and skeleton.

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

666
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

10.2K

Related Experiment Videos

Last Updated: Dec 1, 2025

Hybrid µCT-FMT imaging and image analysis
13:45

Hybrid µCT-FMT imaging and image analysis

Published on: June 4, 2015

13.5K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

666
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

10.2K
  • Evaluation of segmentation speed, achieving results in under a second.
  • Comparison of AIMOS segmentation accuracy against existing algorithms and human expert annotations.
  • Analysis of inter-annotator agreement to identify and quantify human bias.

    • Main Results:

    • AIMOS achieves automated segmentation of major organs and skeleton in less than a second.
    • The tool's segmentation quality matches or surpasses state-of-the-art methods and human experts.
    • Demonstrated applicability in localizing cancer metastases in biomedical research.
    • Quantified human error and bias in expert annotations, highlighting the need for multiple annotations.
    • AIMOS identifies and quantifies regions of human disagreement, aiding downstream analysis.

    Conclusions:

    • AIMOS is a powerful, open-source tool for accelerating organ segmentation in mouse imaging.
    • The tool enhances scalability, reduces bias, and improves reproducibility in biomedical research.
    • AIMOS provides a reliable method for quantifying uncertainty in annotations, leading to more robust analyses.