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

Magnetic Resonance Imaging01:24

Magnetic Resonance Imaging

6.8K
Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...
6.8K

You might also read

Related Articles

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

Sort by
Same author

LET "Automated iliac artery tortuosity measurement: correlation does not equal agreement".

European journal of radiology·2026
Same author

Ten-year Longitudinal Relationship between Spinal Degenerative Lesions in Axial Spondyloarthritis at MRI and Radiography in the DESIR Cohort.

Radiology·2026
Same author

Combining artificial intelligence analysis with expert mammogram reading: Determining the optimal AI positivity cut-off point for the French population-based breast cancer screening program.

Cancer epidemiology·2026
Same author

Letter to the Editor: Artificial intelligence for prostate MRI screening-methodological considerations regarding reference standards and reader design.

European radiology·2026
Same author

Letter to the Editor: Does semi-supervised learning truly reduce annotation burden in heterogeneous real-world MRI networks?

European radiology·2026
Same author

Alert Burden and Multivendor Interactions: Missing Dimensions in Radiology Artificial Intelligence Predeployment Evaluation.

AJR. American journal of roentgenology·2026
Same journal

Displacement of intraorbital ferromagnetic foreign bodies induced by magnetic resonance imaging: Quantification using an animal model.

Research in diagnostic and interventional imaging·2026
Same journal

Impact of a deep-learning image reconstruction algorithm on image quality and detection of solid lung lesions.

Research in diagnostic and interventional imaging·2025
Same journal

Deep learning reconstruction in biparametric prostate MRI: Impact on qualitative and radiomics analyses.

Research in diagnostic and interventional imaging·2025
Same journal

Hydrodissection in microwave ablation: the effectiveness of 0.9 % NaCl versus 5 % dextrose in an ex vivo experimental set-up.

Research in diagnostic and interventional imaging·2025
Same journal

In vivo percutaneous microwave ablation with ECO system in swine kidney and liver: comparison of ablation-zone size to manufacturer predictions and assessment of new antenna design.

Research in diagnostic and interventional imaging·2025
Same journal

Comparing active teaching to hybrid lecture-based method for learning radiology basics: A single center controlled study.

Research in diagnostic and interventional imaging·2025
See all related articles

Related Experiment Video

Updated: Sep 10, 2025

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

Enhancing knee MRI bone marrow lesion detection with artificial intelligence: An external validation study.

Kevin Maarek1, Philippine Cordelle2, Tom Vesoul2

  • 1Université de Paris, 85, boulevard Saint-Germain, 75006 Paris, France.

Research in Diagnostic and Interventional Imaging
|August 21, 2025
PubMed
Summary
This summary is machine-generated.

Artificial intelligence (AI) significantly improves knee bone marrow edema detection in MRI scans, boosting accuracy and reducing reading time for radiologists. This AI-assisted approach enhances diagnostic capabilities for conditions like osteoarthritis.

Keywords:
Artificial intelligenceBone marrow edemaOsteoarthritisRadiologyRetrospective study

More Related Videos

In Vivo Evaluation of Fracture Callus Development During Bone Healing in Mice Using an MRI-compatible Osteosynthesis Device for the Mouse Femur
07:33

In Vivo Evaluation of Fracture Callus Development During Bone Healing in Mice Using an MRI-compatible Osteosynthesis Device for the Mouse Femur

Published on: November 14, 2017

9.6K
Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

40.3K

Related Experiment Videos

Last Updated: Sep 10, 2025

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
In Vivo Evaluation of Fracture Callus Development During Bone Healing in Mice Using an MRI-compatible Osteosynthesis Device for the Mouse Femur
07:33

In Vivo Evaluation of Fracture Callus Development During Bone Healing in Mice Using an MRI-compatible Osteosynthesis Device for the Mouse Femur

Published on: November 14, 2017

9.6K
Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

40.3K

Area of Science:

  • Radiology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Magnetic resonance imaging (MRI) is crucial for detecting knee bone marrow edema, a key indicator in osteoarthritis and injury.
  • Accurate bone marrow edema detection relies heavily on radiologist expertise and can be time-consuming.
  • Segmentation efficiency for bone marrow edema in knee MRI presents a significant challenge.

Purpose of the Study:

  • To evaluate the impact of artificial intelligence (AI) on improving general radiologists' diagnostic accuracy for knee bone marrow edema.
  • To assess the performance and efficiency of an AI algorithm in segmenting bone marrow edema.
  • To externally validate an AI solution for bone marrow edema detection in knee MRI.

Main Methods:

  • A multicenter, multireader, multicase retrospective study using an external dataset of 198 knee MRI examinations.
  • An AI algorithm (Keros) with three 3D-UNet models was used for bone marrow edema segmentation on specific MRI sequences.
  • Ground truth was established by expert musculoskeletal radiologists; performance was compared with and without AI assistance.

Main Results:

  • AI significantly increased sensitivity for bone marrow edema detection from 79.3% to 85.4% (p=0).
  • Specificity also significantly improved with AI, rising from 88.9% to 93.9% (p=0).
  • AI assistance reduced reading times by 42%, with an average saving of 0.66 minutes per exam (p=3.81e-41).

Conclusions:

  • AI significantly enhances both sensitivity and specificity for bone marrow edema detection by general radiologists.
  • AI-assisted reading substantially shortens the time required for knee MRI interpretation.
  • AI holds promise for improved longitudinal monitoring of knee osteoarthritis patients.