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

Inductive Reasoning00:59

Inductive Reasoning

Inductive reasoning is a form of logical thinking that uses related observations to arrive at a general conclusion. It is uncertain and operates in degrees to which the conclusions are credible. As such, inductive arguments can be weak or strong, rather than valid or invalid, and conclusions can be used to formulate testable, falsifiable hypotheses.Inductive reasoning is common in descriptive science. A life scientist makes observations and records them. This data can be qualitative or...
Reasoning01:30

Reasoning

Reasoning is the action of thinking about something in a logical, sensible way. It is integral to problem-solving, decision-making, and critical thinking. Reasoning can be inductive or deductive. Reasoning involves transforming information into conclusions, which is essential for problem-solving, decision-making, and critical thinking.
Inductive reasoning involves deriving generalizations from specific observations. This type of reasoning helps form beliefs about the world. For example,...
Radiological Investigation II: MRI and Ventilation Perfusion Scan01:30

Radiological Investigation II: MRI and Ventilation Perfusion Scan

Description
Magnetic Resonance Imaging (MRI) and Ventilation Perfusion Scans are two radiological investigations that offer detailed diagnostic images of the body, particularly lung structures.
MRI
MRI uses magnetic fields and radiofrequency signals to distinguish between normal and abnormal tissues. This technology provides a more detailed diagnostic image than CT scans, enabling it to characterize pulmonary nodules, stage bronchogenic carcinoma, and evaluate inflammatory activity in...
Magnetic Resonance Imaging01:24

Magnetic Resonance Imaging

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...

You might also read

Related Articles

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

Sort by
Same author

Population Pharmacokinetics of Intravenous Infusion of Hydromorphone in Critically Ill Patients Supported by Extracorporeal Membrane Oxygenation.

Clinical and translational science·2026
Same author

Clinical efficacy and safety of icodextrin dialysate for overnight dwell in continuous ambulatory peritoneal dialysis: A prospective self-controlled study.

The Journal of international medical research·2026
Same author

The impact of acupuncturists' experience level on the efficacy of acupuncture for functional dyspepsia: an exploratory secondary analysis of a randomized clinical trial.

Frontiers in medicine·2026
Same author

Dysregulation of the HSF1-Mediated UPR<sup>mt</sup> Pathway in Colonic Smooth Muscle Cells Drives Motility Dysfunction in Functional Constipation.

Biomolecules·2026
Same author

Spatial Tail Design in Ionizable Lipids Enhances the Safety and Efficacy of mRNA Delivery.

Small methods·2026
Same author

Multiscale structural connectome eigenmodes constrain human brain functional dynamics.

Communications biology·2026

Related Experiment Videos

Interpretable agentic AI system with localized reasoning for radiology.

Wenting Chen1,2, Yi Dong3, Zhaojun Ding4

  • 1Department of Electrical Engineering, City University of Hong Kong, Hong Kong, SAR, China.

NPJ Digital Medicine
|July 15, 2026
PubMed
Summary

RadFabric, an AI system, unifies multiple chest X-ray models for improved, explainable diagnoses. It enhances detection of common and rare findings, boosting clinical applicability.

Related Experiment Videos

Area of Science:

  • Artificial Intelligence in Medical Imaging
  • Radiology AI
  • Clinical Decision Support Systems

Background:

  • Existing medical AI models for chest X-rays (CXRs) have limited generalizability and face integration challenges due to isolated tasks and restricted datasets.
  • Large language models (LLMs) offer a new approach to integrate heterogeneous AI models within agentic frameworks for unified natural language interpretation.

Purpose of the Study:

  • To develop RadFabric, an agentic AI system that orchestrates multiple specialized CXR analytics models and vision-language models (VLMs).
  • To enable transparent, step-by-step diagnoses by synthesizing model outputs with VLM-generated reports, even with conflicting data.
  • To enhance explainability, robustness, and clinical applicability of AI-driven radiological diagnoses.

Main Methods:

  • An agentic AI system, RadFabric, was created, orchestrating fourteen open-source CXR analytics models and two VLMs via a modular protocol.
  • An Anatomical Interpretation Agent was developed to contextualize visual findings within anatomical structures.
  • A trainable reasoning agent synthesizes anatomically-enriched outputs and VLM reports for diagnosis generation.

Main Results:

  • RadFabric demonstrated robust diagnostic capabilities across common and rare pathologies.
  • The system achieved an AUC of 85.18% on the MIMIC-CXR dataset for detecting various lesion types, outperforming state-of-the-art CXR models.
  • The reasoning agent significantly improved the detection of uncommon findings, highlighting enhanced interpretability and generalizability.

Conclusions:

  • RadFabric provides an extensible architecture for explainable and robust AI-driven radiological diagnoses.
  • The system's ability to unify heterogeneous model outputs enhances clinical applicability and diagnostic accuracy, particularly for rare conditions.
  • The developed agentic framework shows promise for advancing the integration and performance of medical AI in clinical practice.