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

A stereo dataset of annotated budgerigar flight trajectories for multi-agent collision avoidance studies.

Data in brief·2026
Same author

Explainable AI in kidney stone detection and segmentation: a mini review.

Frontiers in digital health·2026
Same author

CBAM-Xception: An Attention-Guided Framework for Skin Cancer Classification.

Journal of imaging informatics in medicine·2026
Same author

Multi-modal federated learning with differential privacy for privacy-preserving healthcare AI.

Scientific reports·2026
Same author

Explainable deep learning for early diagnosis of chronic kidney disease from CT images in Bangladeshi patients.

Scientific reports·2026
Same author

Early detection of chronic kidney disease using deep learning: a Mini review.

Frontiers in digital health·2026

Related Experiment Video

Updated: Jun 30, 2026

A Gaze-Contingent Display Framework for Perceptual Learning Research with Simulated Central Vision Loss
07:12

A Gaze-Contingent Display Framework for Perceptual Learning Research with Simulated Central Vision Loss

Published on: April 11, 2025

Medical visual question answering with multimodal: a systematic mini review (2023-2026).

Maimuna Biswas Noshin1,2, Monoronjon Dutta2,3, Md Nadim Kaysar4

  • 1Department of Electrical and Electronics Engineering, Islamic University of Technology, Gazipur, Bangladesh.

Frontiers in Digital Health
|June 29, 2026
PubMed
Summary
This summary is machine-generated.

Recent advancements in medical visual question answering (Med-VQA) leverage large language models (LLMs) and vision-language models (VLMs) for multimodal image explanation and clinical question answering.

Keywords:
generative AI in healthcarelarge vision-language modelsmedical visual question answeringmultimodal reasoningsystematic review

More Related Videos

Assessing Binocular Central Visual Field and Binocular Eye Movements in a Dichoptic Viewing Condition
07:45

Assessing Binocular Central Visual Field and Binocular Eye Movements in a Dichoptic Viewing Condition

Published on: July 21, 2020

Quantification of Oculomotor Responses and Accommodation Through Instrumentation and Analysis Toolboxes
08:27

Quantification of Oculomotor Responses and Accommodation Through Instrumentation and Analysis Toolboxes

Published on: March 3, 2023

Related Experiment Videos

Last Updated: Jun 30, 2026

A Gaze-Contingent Display Framework for Perceptual Learning Research with Simulated Central Vision Loss
07:12

A Gaze-Contingent Display Framework for Perceptual Learning Research with Simulated Central Vision Loss

Published on: April 11, 2025

Assessing Binocular Central Visual Field and Binocular Eye Movements in a Dichoptic Viewing Condition
07:45

Assessing Binocular Central Visual Field and Binocular Eye Movements in a Dichoptic Viewing Condition

Published on: July 21, 2020

Quantification of Oculomotor Responses and Accommodation Through Instrumentation and Analysis Toolboxes
08:27

Quantification of Oculomotor Responses and Accommodation Through Instrumentation and Analysis Toolboxes

Published on: March 3, 2023

Area of Science:

  • Artificial Intelligence in Medicine
  • Medical Imaging Analysis
  • Clinical Decision Support

Background:

  • Medical visual question answering (Med-VQA) has rapidly evolved from text-heavy systems to sophisticated AI frameworks.
  • Large language models (LLMs) and vision-language models (VLMs) are revolutionizing medical question answering (QA).

Purpose of the Study:

  • To systematically review and analyze recent developments in Med-VQA.
  • To identify key trends, methodologies, and challenges in Med-VQA systems.

Main Methods:

  • A systematic review following PRISMA guidelines.
  • Analysis of 27 representative studies on Med-VQA.
  • Inclusion and exclusion criteria applied to studies from various databases.

Main Results:

  • A significant shift towards generative models, retrieval mechanisms, and structured reasoning (e.g., Chain-of-Thought, multi-agent frameworks).
  • Generative models with retrieval-augmented generation (RAG) offer improved consistency and free-form QA over traditional methods.
  • Frameworks like multi-agent and hierarchical CoT enhance interpretability and reduce hallucinations but face challenges.

Conclusions:

  • Med-VQA systems show great promise for clinical decision support and answer generation.
  • Future research should address computational efficiency, fairness, standardized evaluation, and interpretable reasoning for real-world clinical application.