Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Imaging Studies IV: Magnetic Resonance Imaging

Imaging Studies IV: Magnetic Resonance Imaging

Introduction:Magnetic Resonance Imaging, or MRI, can include a specialized imaging technique of the urinary system known as Magnetic Resonance Urography (MRU). This radiation-free technique uses strong magnetic fields and radio waves to produce detailed images with the help of a computer. MRU is particularly effective for visualizing fluid-filled structures like the kidneys, ureters, and bladder.Applications of MRI in the Genitourinary SystemKidneys and Ureters: MRI detects tumors, cysts,...

You might also read

Related Articles

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

Sort by

Same author

Strategy for Simultaneous Multiomic Survey of N-Glycomic and Extracellular Matrix Proteome by Mass Spectrometry Imaging.

Journal of the American Society for Mass Spectrometry·2026

Same author

Correction: ISSLS Prize in Clinical Science 2026: Data-driven classification of lumbar spine degeneration trajectories in chronic low back pain.

European spine journal : official publication of the European Spine Society, the European Spinal Deformity Society, and the European Section of the Cervical Spine Research Society·2026

Same author

Celebrating ISSLS Science, Leadership, Legacy, and Partnership with the European Spine Journal.

European spine journal : official publication of the European Spine Society, the European Spinal Deformity Society, and the European Section of the Cervical Spine Research Society·2026

Same author

Quantitative Disk and Metabolic Bone PET-MRI for Understanding Disk-Endplate Crosstalk in Degeneration of the Lumbar Spine.

JOR spine·2026

Same author

Vertebral endplate bone marrow lesion composition: relation to Modic change classification and associations with chronic low back pain.

The spine journal : official journal of the North American Spine Society·2026

Same author

A longitudinal imaging study of the effects of type 2 diabetes and microvascular disease on diabetic bone disease.

Bone·2026

Search research articles

Related Experiment Video

Updated: Jun 11, 2026

Scanning Skeletal Remains for Bone Mineral Density in Forensic Contexts

Scanning Skeletal Remains for Bone Mineral Density in Forensic Contexts

Published on: January 29, 2018

Information Extraction from Lumbar Spine MRI Radiology Reports Using GPT4: Accuracy and Benchmarking Against

Katharina Ziegeler¹, Virginie Kreutzinger¹, Michelle W Tong^1,2,3

¹Department of Radiology and Biomedical Imaging, University of California San Francisco, San Francisco, CA 94143, USA.

Diagnostics (Basel, Switzerland)

|April 12, 2025

Summary

This summary is machine-generated.

Large language models (LLMs) can accurately extract detailed lumbar spine pathology data from radiology reports. While performance is excellent, moderate agreement with expert scoring highlights the need for improved, less subjective machine-based data extraction methods.

Keywords:

large language models magnetic resonance imaging spinal imaging

More Related Videos

Quantitative [18F]-Naf-PET-MRI Analysis for the Evaluation of Dynamic Bone Turnover in a Patient with Facetogenic Low Back Pain

Quantitative [18F]-Naf-PET-MRI Analysis for the Evaluation of Dynamic Bone Turnover in a Patient with Facetogenic Low Back Pain

Published on: August 8, 2019

Evaluation of Patients' Posture and Gait Profile After Lumbar Fusion Surgery by Video Rasterstereography and Treadmill Gait Analysis

Published on: March 23, 2019

Related Experiment Videos

Last Updated: Jun 11, 2026

Scanning Skeletal Remains for Bone Mineral Density in Forensic Contexts

Scanning Skeletal Remains for Bone Mineral Density in Forensic Contexts

Published on: January 29, 2018

Quantitative [18F]-Naf-PET-MRI Analysis for the Evaluation of Dynamic Bone Turnover in a Patient with Facetogenic Low Back Pain

Quantitative [18F]-Naf-PET-MRI Analysis for the Evaluation of Dynamic Bone Turnover in a Patient with Facetogenic Low Back Pain

Published on: August 8, 2019

Evaluation of Patients' Posture and Gait Profile After Lumbar Fusion Surgery by Video Rasterstereography and Treadmill Gait Analysis

Published on: March 23, 2019

Area of Science:

Medical Imaging Analysis
Natural Language Processing in Healthcare
Radiology Informatics

Background:

Standardized data extraction from lumbar spine MRI reports is crucial for research.
Current methods can be subjective and time-consuming.
Large language models (LLMs) offer a potential solution for automated data extraction.

Purpose of the Study:

To develop and evaluate an LLM-based pipeline for standardized data extraction from lumbar spine MRI reports.
To assess the agreement between LLM-extracted data and research-grade semi-quantitative scoring.
To identify areas for improvement in LLM-based data extraction for spinal pathologies.

Main Methods:

Utilized a secure API deployment of OpenAI's GPT-4 for pathology extraction from clinical radiology reports.
Employed unsupervised UMAP and agglomerative clustering for prompt optimization.
Benchmarked LLM extraction against human extraction using F1 scores, FPR, and FNR.
Calculated agreement between LLM-extracted data and expert radiologist scores using Cohen's kappa.

Main Results:

Included data from 230 chronic low back pain patients.
Achieved excellent overall LLM performance with a mean F1 score of 0.96 for pathology extraction.
Observed moderate agreement (kappa 0.424) between LLM-extracted data and expert scores.
Noted underreporting of lateral recess stenosis (FNR 63.6%) and overreporting of disc pathology (FPR 42.7%).

Conclusions:

LLMs demonstrate high accuracy in extracting detailed lumbar spine imaging pathology information from radiology reports.
Moderate agreement with expert scoring indicates a need for further refinement of LLM extraction methods.
Machine-based data extraction holds promise for reducing subjectivity in imaging analysis.