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

4.9K
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...
4.9K

You might also read

Related Articles

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

Sort by
Same author

Jurassic avialan reveals stepwise evolution of bony tail in birds.

Science advances·2026
Same author

Assessment of water ecosystem service value in the Jianghuai watershed area: a case study of Chuzhou.

Scientific reports·2026
Same author

Porphyromonas gingivalis promotes the malignant phenotype of oral squamous cell carcinoma through the recruitment of Treg cells.

Communications biology·2026
Same author

Integrative multi-omics analysis identifies GNAZ and SLC5A4 as critical regulators of gestation length in Large White pigs.

Genetics, selection, evolution : GSE·2026
Same author

The Impact of Adjuvant Radiotherapy Combined With Targeted or Immunotherapy on the Heart in Breast Cancer.

Thoracic cancer·2026
Same author

Characterizing immune heterogeneity in gastric cancer by high-throughput T-cell receptor sequencing: predictive clonotypes and functional signatures.

Translational cancer research·2026

Related Experiment Video

Updated: Jun 4, 2025

Deep Vascular Imaging in the Eye with Flow-Enhanced Ultrasound
07:29

Deep Vascular Imaging in the Eye with Flow-Enhanced Ultrasound

Published on: October 4, 2021

2.3K

Dual-modality visual feature flow for medical report generation.

Quan Tang1, Liming Xu2, Yongheng Wang3

  • 1School of Computer Science, China West Normal University, Nanchong, 637009, Sichuan, China.

Medical Image Analysis
|December 18, 2024
PubMed
Summary
This summary is machine-generated.

This study introduces Dual-Modality Visual Feature Flow (DMVF) for medical report generation, improving lesion identification and cross-modal alignment for more accurate clinical descriptions from medical images.

Keywords:
Feature fusionMedical report generationMulti-modal learningRegion feature

More Related Videos

In vitro Assessment of Aortic Regurgitation Using Four-Dimensional Flow Magnetic Resonance Imaging
11:16

In vitro Assessment of Aortic Regurgitation Using Four-Dimensional Flow Magnetic Resonance Imaging

Published on: February 25, 2022

3.2K
Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis
05:41

Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis

Published on: February 9, 2024

529

Related Experiment Videos

Last Updated: Jun 4, 2025

Deep Vascular Imaging in the Eye with Flow-Enhanced Ultrasound
07:29

Deep Vascular Imaging in the Eye with Flow-Enhanced Ultrasound

Published on: October 4, 2021

2.3K
In vitro Assessment of Aortic Regurgitation Using Four-Dimensional Flow Magnetic Resonance Imaging
11:16

In vitro Assessment of Aortic Regurgitation Using Four-Dimensional Flow Magnetic Resonance Imaging

Published on: February 25, 2022

3.2K
Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis
05:41

Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis

Published on: February 9, 2024

529

Area of Science:

  • Artificial Intelligence
  • Medical Informatics
  • Computer Vision

Background:

  • Medical report generation is a cross-modal task translating medical images into clinical text.
  • Current methods struggle with lesion focus, internal edge details, and cross-modal data alignment.

Purpose of the Study:

  • To enhance medical report generation by addressing limitations in existing approaches.
  • To improve the accuracy and clinical relevance of generated medical reports.

Main Methods:

  • Proposed Dual-Modality Visual Feature Flow (DMVF) for medical report generation.
  • Introduced region-level features alongside grid-level features for enhanced lesion identification.
  • Implemented attribute-based enhancement of feature flows to preserve key information.
  • Utilized a feature fusion module for aligning visual features with textual embeddings for cross-modal learning.

Main Results:

  • DMVF demonstrated superior performance over state-of-the-art methods.
  • Improvements were observed in both natural language generation and clinical efficacy metrics.
  • Experiments were validated on four benchmark datasets.

Conclusions:

  • The proposed DMVF method significantly advances medical report generation.
  • DMVF effectively enhances lesion identification, information retention, and cross-modal learning.
  • This approach offers a more robust solution for generating professional medical descriptions from images.