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

9.1K
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...
9.1K
Imaging Studies I: CT and MRI01:14

Imaging Studies I: CT and MRI

802
Introduction: MRI and CT scans are crucial advancements in medical imaging techniques, playing a vital role in diagnosing conditions related to the gastrointestinal (GI) system. Each scan serves distinct purposes, targets specific areas, and requires unique nursing duties.
Description of the Procedures
Computed Tomography (CT) scan:
Computed Tomography (CT) scans use X-ray technology to generate detailed images of bones, organs, and tissues. During the scan, the patient lies on a moving table...
802

You might also read

Related Articles

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

Sort by
Same author

Externally Tested AI for Lung Nodule Classification: A Realistic Benchmark for an Emerging Screening Era.

Radiology. Artificial intelligence·2026
Same author

Erratum for: Associations of MRI-derived Paraspinal IMAT and LMM with Cardiometabolic Risk Factors: Results from a German Cohort.

Radiology·2026
Same author

Supporting Radiology Resident Education and Clinical Decision-Making With Large Language Models: Comparative Study of Reasoning Models DeepSeek-R1 and ChatGPT-o1.

JMIR AI·2026
Same author

Beyond the LUMIR challenge: The pathway to foundational registration models.

Medical image analysis·2026
Same author

Organ masks applied in feature space improve weakly supervised scan-level CT classification.

Scientific reports·2026
Same author

An automated quantitative report for multiple sclerosis using only 3D T2-fluid-attenuated inversion recovery MRI.

Neuroradiology·2026

Related Experiment Video

Updated: Jan 17, 2026

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

43.4K

MRI annotation using an inversion-based preprocessing for CT model adaptation.

Hartmut Häntze1,2, Lina Xu1, Maximilian Nikolas Rattunde1

  • 1Department of Radiology, Charité-Universitätsmedizin Berlin corporate member of Freie Universität Berlin and Humboldt Universität zu Berlin, Berlin, Germany.

European Radiology Experimental
|September 20, 2025
PubMed
Summary

Computed tomography (CT) segmentation models can generate accurate magnetic resonance imaging (MRI) presegmentations. Image inversion preprocessing enhances CT model performance on T1-weighted MRI, improving segmentation accuracy for structures and renal tumors.

Keywords:
Artificial IntelligenceCarcinoma (renal cell)Image processing (computer-assisted)Magnetic resonance imagingTomography (x-ray computed)

More Related Videos

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

49.3K
High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain
10:06

High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain

Published on: May 10, 2012

13.4K

Related Experiment Videos

Last Updated: Jan 17, 2026

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

43.4K
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

49.3K
High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain
10:06

High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain

Published on: May 10, 2012

13.4K

Area of Science:

  • Medical imaging analysis
  • Artificial intelligence in radiology
  • Cross-modality image segmentation

Background:

  • Manual annotation of new classes in MRI is time-consuming.
  • CT segmentation models can support MRI analysis, but direct translation is challenging.
  • CT-trained models can create accurate MRI presegmentations with or without image inversion.

Purpose of the Study:

  • To evaluate the performance of CT-trained segmentation models on MRI data.
  • To assess the impact of image inversion preprocessing on segmentation accuracy.
  • To determine the generalizability of CT models to MRI for various anatomical structures and renal tumors.

Main Methods:

  • Retrospective analysis of 100 T1-weighted and 100 T2-weighted fat-saturated MRI sequences from 100 patients.
  • Application of a general multiclass CT model (TotalSegmentator) and a specialized renal tumor model.
  • Evaluation of segmentation quality using Dice Similarity Coefficients (DSC) on raw and intensity-inverted sequences.

Main Results:

  • Segmentation accuracy varied by MRI sequence and anatomical structure.
  • CT models accurately segmented kidneys in T2wfs sequences (DSC 0.60) but struggled with blood vessels and muscles.
  • Intensity inversion significantly improved TotalSegmentator performance on T1w sequences (mean DSC 0.04 to 0.56, p < 0.001).
  • Inversion improved renal tumor segmentation DSC in T1w sequences from 0.04 to 0.42 (p < 0.001).

Conclusions:

  • CT-trained models can generalize to MRI with appropriate preprocessing, such as image inversion.
  • Inversion preprocessing enabled segmentation of renal cell carcinoma in T1w MRI using CT models.
  • CT models show potential for transferability to MRI, accelerating AI development for MRI analysis.