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

Search research articles

Related Experiment Video

Updated: Jan 9, 2026

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

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

Published on: December 6, 2024

Consistency Conditioned Memory Augmented Dynamic Diagnosis Model for Medical Visual Question Answering.

Ting Yu, Binhui Ge, Shuhui Wang

IEEE Journal of Biomedical and Health Informatics

|December 9, 2025

Summary

We developed CoCoMeD, a novel model for Medical Visual Question Answering (Med-VQA), to improve diagnostic accuracy and consistency. This AI approach mimics human diagnosticians, enhancing clinical decision-making with reliable medical image analysis.

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

On the molecular mechanism of GC content variation among eubacterial genomes.

Biology direct·2012

Same author

Presence of somatic mutations in most early-stage pancreatic intraepithelial neoplasia.

Gastroenterology·2012

Same author

Activation of peroxisome proliferator activated receptor alpha ameliorates ethanol induced steatohepatitis in mice.

Lipids in health and disease·2012

Same author

Pharmacological ascorbate induces cytotoxicity in prostate cancer cells through ATP depletion and induction of autophagy.

Anti-cancer drugs·2011

Same author

A pangenomic study of Bacillus thuringiensis.

Journal of genetics and genomics = Yi chuan xue bao·2011

Same author

[A prevalence investigation of blindness and vision impairment in 2009 in older adults of Dachang Blocks of Baoshan District, Shanghai, China].

[Zhonghua yan ke za zhi] Chinese journal of ophthalmology·2011

Area of Science:

Artificial Intelligence
Medical Imaging
Clinical Decision Support

Background:

Medical Visual Question Answering (Med-VQA) shows potential for clinical decision support but struggles with human-like reasoning and consistent results.
Existing Med-VQA systems lack the ability to dynamically integrate visual information and ensure coherence across related diagnostic questions.

Purpose of the Study:

To introduce the Consistency Conditioned Memory augmented Dynamic diagnosis model (CoCoMeD) for more accurate and reliable Med-VQA.
To enhance Med-VQA by mimicking human diagnostic cognitive processes and ensuring result consistency.

Main Methods:

CoCoMeD utilizes a dynamic memory diagnosis engine to retain and update visual cues from medical images.
A consistency-conditioned enforcer module imposes coherence constraints between related questions and medical facts.

More Related Videos

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Published on: August 9, 2024

Related Experiment Videos

Last Updated: Jan 9, 2026

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

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

Published on: December 6, 2024

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Published on: August 9, 2024

Introduced C-SLAKE, an extended Med-VQA dataset with diverse image types and categorized Q&A pairs for evaluation.

Main Results:

CoCoMeD demonstrated superior performance on the DME and C-SLAKE datasets.
The dynamic memory and consistency enforcer components improved diagnostic reasoning and result credibility.
Experimental results indicate CoCoMeD's potential for advancing trustworthy multi-source medical question answering.

Conclusions:

CoCoMeD effectively addresses limitations in current Med-VQA systems by enhancing dynamic reasoning and diagnostic consistency.
The proposed model shows promise for improving AI-assisted medical diagnosis and clinical decision-making.
The C-SLAKE dataset facilitates more robust and consistent evaluation of Med-VQA systems.