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 Concept Videos

You might also read

Related Articles

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

Sort by
Same authorSame journal

Image Quality Assessment of Diffusion-Weighted Imaging (DWI) and Its Impact on Apparent Diffusion Coefficient (ADC) as a Quantitative Imaging Biomarker for Predicting Response to Neoadjuvant Chemotherapy in High-Risk Early Breast Cancer.

Tomography (Ann Arbor, Mich.)·2026
Same author

Bladder cancer segmentation using u-net-based deep-learning.

Scientific reports·2026
Same author

Launching <i>BJR</i>|<i>Artificial intelligence</i>: an editorial.

BJR artificial intelligence·2026
Same author

On-Scanner Correction of Gradient Nonlinearity Bias for Accurate Assessment of Diffusion Heterogeneity Across Bone Sites in Myelofibrosis Patients.

Magnetic resonance in medicine·2026
Same author

Evaluating the reliability of large language models for clinical data extraction in bladder cancer prognosis.

Scientific reports·2025
Same author

Quantitative MRI Assessment of Bone Marrow Disease in Myelofibrosis: A Prospective Study.

Radiology. Imaging cancer·2025

Related Experiment Video

Updated: Aug 5, 2025

Femur Window Chamber Model for In Vivo Cell Tracking in the Murine Bone Marrow
08:41

Femur Window Chamber Model for In Vivo Cell Tracking in the Murine Bone Marrow

Published on: July 28, 2016

8.3K

Improved Repeatability of Mouse Tibia Volume Segmentation in Murine Myelofibrosis Model Using Deep Learning.

Aman Kushwaha1, Rami F Mourad1, Kevin Heist1

  • 1Department of Radiology, University of Michigan, Ann Arbor, MI 48109, USA.

Tomography (Ann Arbor, Mich.)
|March 24, 2023
PubMed
Summary

A deep learning model automates murine tibia segmentation for myelofibrosis research, achieving human-level accuracy and superior repeatability in image-based biomarker analysis.

Keywords:
MRIattention-U-netmouse tibia segmentationmyelofibrosistest–retest pairsvolume wCV

More Related Videos

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.9K
Simplified Intrafemoral Injections Using Live Mice Allow for Continuous Bone Marrow Analysis
06:28

Simplified Intrafemoral Injections Using Live Mice Allow for Continuous Bone Marrow Analysis

Published on: November 10, 2023

2.2K

Related Experiment Videos

Last Updated: Aug 5, 2025

Femur Window Chamber Model for In Vivo Cell Tracking in the Murine Bone Marrow
08:41

Femur Window Chamber Model for In Vivo Cell Tracking in the Murine Bone Marrow

Published on: July 28, 2016

8.3K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.9K
Simplified Intrafemoral Injections Using Live Mice Allow for Continuous Bone Marrow Analysis
06:28

Simplified Intrafemoral Injections Using Live Mice Allow for Continuous Bone Marrow Analysis

Published on: November 10, 2023

2.2K

Area of Science:

  • Biomedical Imaging
  • Machine Learning in Medicine
  • Preclinical Research Models

Background:

  • Myelofibrosis assessment in murine models relies on image-based biomarkers.
  • Accurate segmentation of bone marrow is crucial for quantitative analysis.
  • Manual segmentation is time-consuming and subject to inter-observer variability.

Purpose of the Study:

  • To develop and evaluate an automated segmentation method for murine tibia in a myelofibrosis model.
  • To compare the performance of a deep learning model against manual expert segmentations.
  • To assess the repeatability of automated versus manual segmentation methods.

Main Methods:

  • A murine model of tibia myelofibrosis was utilized.
  • 3D MRI scans from 32 mice were processed.
  • An Attention U-net (A-U-net) deep learning model was trained and validated.
  • Performance was evaluated using Jaccard index, volume intersection ratio, volume error, and Hausdorff distance.
  • Repeatability was assessed using within-subject coefficient of variance (%wCV).

Main Results:

  • A-U-net models achieved high accuracy (AJI 83-84%) comparable to expert annotators.
  • Automated segmentation exceeded one expert annotator's accuracy (AJI 81%).
  • The A-U-net model demonstrated significantly improved repeatability (%wCV 3%) versus experts (EA1: 5%, EA2: 8%).

Conclusions:

  • Deep learning effectively automates murine bone marrow segmentation.
  • The A-U-net model offers accuracy comparable to human experts.
  • Automated segmentation provides substantially improved repeatability for image-based biomarker analysis.