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 author

The Association Between Sitting Delivery During the Second Stage of Labor and Pelvic Floor Function in Primiparas: A Prospective Cohort Study.

Healthcare (Basel, Switzerland)·2026
Same author

Sludge Retention Time Governs Ectoine Synthesis and Pollutant Removal in Halophilic Activated Sludge Treating High-Salinity Wastewater.

Toxics·2026
Same author

Construction of chitosan-coated TiO<sub>2</sub>/In<sub>2</sub>S<sub>3</sub> heterojunction on titanium surfaces for NIR triggered photothermal/photodynamic synergistic enhanced antibacterial.

Colloids and surfaces. B, Biointerfaces·2026
Same author

The LncRNA GAS5/miR-205 ceRNA axis regulates fibroblast activation and may contribute to hypertrophic scarring.

Molecular biology reports·2026
Same author

Adjuvant Chemoradiotherapy or Chemotherapy After D2 Gastrectomy in Gastric Cancer: A Randomized Clinical Trial.

JAMA network open·2026
Same author

A Two-Stage Penalized Least Squares Method for Constructing Large Systems of Structural Equations.

Journal of machine learning research : JMLR·2026
Same journal

Low-Intensity Focused Ultrasound Enhances Hippocampal Neurogenesis via BDNF Pathways: Toward a Regenerative Modality for CNS Recovery.

Ultrasound in medicine & biology·2026
Same journal

Effects of Ultrasound-Mediated Treatments on Dental Biofilm Attachment and Viability.

Ultrasound in medicine & biology·2026
Same journal

Diagnosis of Small Focal Liver Lesions (≤2 cm): A Deep Learning Approach Based on B-Mode Ultrasound and Contrast-Enhanced Ultrasound.

Ultrasound in medicine & biology·2026
Same journal

Point-of-Care Ultrasound-based Characterization of the Patellar Tendon in Children with Cerebral Palsy.

Ultrasound in medicine & biology·2026
Same journal

Beyond a Single Particle Size Distribution: Does Microbubble Size Distribution Influence the Applicability of Reported Safety Conclusions?

Ultrasound in medicine & biology·2026
Same journal

Beyond a Single Particle Size Distribution: Does Microbubble Size Distribution Influence the Applicability of Reported Safety Conclusions?

Ultrasound in medicine & biology·2026
See all related articles
  1. Home
  3. Automated O-rads Risk Stratification Using A Large Language Model Analysis Of Narrative Ultrasound Reports.
  1. Home
  3. Automated O-rads Risk Stratification Using A Large Language Model Analysis Of Narrative Ultrasound Reports.

Related Experiment Video

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

1.3K

Automated O-RADS Risk Stratification Using a Large Language Model Analysis of Narrative Ultrasound Reports.

Yanhui Guo1, Jingjing Gong2, Ruquan Jiang3

  • 1Department of Computer Science, University of Illinois Springfield, Springfield, IL, USA.

Ultrasound in Medicine & Biology
|April 12, 2026

View abstract on PubMed

Summary
This summary is machine-generated.

This study developed an automated method using large language models (LLMs) to score ovarian lesions (O-RADS), improving accuracy and efficiency in risk stratification.

Keywords:
Large language model (LLM)Machine learning (ML)Natural language processing (NLP)Ovarian cancerOvarian-Adnexal Reporting and Data System (O-RADS)Risk stratificationUltrasound radiology

More Related Videos

A Modified Sonographic Algorithm for Image Acquisition in Life-Threatening Emergencies in the Critically Ill Newborn
11:27

A Modified Sonographic Algorithm for Image Acquisition in Life-Threatening Emergencies in the Critically Ill Newborn

Published on: April 7, 2023

7.8K
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
07:31

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

8.3K

Related Experiment Videos

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

1.3K
A Modified Sonographic Algorithm for Image Acquisition in Life-Threatening Emergencies in the Critically Ill Newborn
11:27

A Modified Sonographic Algorithm for Image Acquisition in Life-Threatening Emergencies in the Critically Ill Newborn

Published on: April 7, 2023

7.8K
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
07:31

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

8.3K

Area of Science:

  • Artificial Intelligence in Medical Imaging
  • Machine Learning for Diagnostic Support
  • Natural Language Processing in Radiology

Background:

  • Ovarian-Adnexal Reporting and Data System (O-RADS) standardizes ovarian lesion risk stratification.
  • Manual O-RADS scoring is time-consuming and subject to inter-observer variability.
  • Automated O-RADS scoring using large language models (LLMs) is investigated.

Purpose of the Study:

  • To develop and evaluate an automated method for O-RADS scoring.
  • To leverage LLMs for feature extraction from ultrasound reports.
  • To improve the efficiency and consistency of ovarian cancer risk assessment.

Main Methods:

  • A two-stage pipeline using the Lingshu LLM for feature extraction from narrative ultrasound reports.
  • Identification of key diagnostic features by the LLM.
  • Training and evaluation of machine learning algorithms (logistic regression, SVM, random forests) for O-RADS score prediction (1-5).

    • Main Results:

    • The Lingshu LLM with logistic regression achieved an accuracy of 0.803 and AUROC of 0.948.
    • This automated method outperformed the MedGemma model pipeline.
    • The system demonstrated high performance in classifying ovarian lesions across a dataset of 513 cases.

    Conclusions:

    • A novel approach for automated O-RADS scoring using LLMs and machine learning was introduced.
    • The method accurately stratifies ovarian cancer risk, enhancing clinical workflow efficiency.
    • This automated system has the potential to reduce diagnostic variability and support radiologists' assessments.