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

Radiological Investigation III: Pulmonary Angiogram and PET Scan01:13

Radiological Investigation III: Pulmonary Angiogram and PET Scan

511
Radiological investigations are paramount in the diagnosis and management of various pulmonary diseases. Two essential investigations are the Pulmonary Angiogram and the Positron Emission Tomography (PET) Scan.
Pulmonary Angiogram
A Pulmonary Angiogram is an invasive procedure involving injecting a contrast medium through a catheter threaded into the pulmonary artery or the right side of the heart to visualize the pulmonary vasculature. Computed Tomography (CT) scans have mainly replaced this...
511
Radiological Investigation II: MRI and Ventilation Perfusion Scan01:30

Radiological Investigation II: MRI and Ventilation Perfusion Scan

699
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...
699

You might also read

Related Articles

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

Sort by
Same author

Maternal Complications Associated with Primiparous Adolescent Pregnancies.

Journal of clinical medicine·2026
Same author

Excess Mortality as the Primary Mediator of COVID-19's Impact on Life Expectancy in Europe: A Multilevel Longitudinal Analysis of Regional Disparities.

Medicina (Kaunas, Lithuania)·2026
Same author

The Role of Microbiota in Type 1 Diabetes: Insights into Dysbiosis and Immune Interactions.

Nutrients·2026
Same author

Breathing Out the Truth: What Fractional Exhaled Nitric Oxide Really Tells Us About Pediatric Asthma.

Diagnostics (Basel, Switzerland)·2026
Same author

Sirolimus Treatment for Complex Fetal and Neonatal Vascular Anomalies: Emerging Evidence and Safety Considerations.

Journal of clinical medicine·2026
Same author

Early Gut Microbiota and Neurodevelopmental Trajectories: Implications for Pediatric Neuropsychiatric Vulnerability-A Narrative Review.

Nutrients·2026

Related Experiment Video

Updated: Feb 22, 2026

Unilateral Lung Volume Analysis Using Micro-CT for Enhanced Assessment of Pulmonary Fibrosis in Preclinical Models
03:38

Unilateral Lung Volume Analysis Using Micro-CT for Enhanced Assessment of Pulmonary Fibrosis in Preclinical Models

Published on: June 20, 2025

1.0K

Multimodal Autoencoder-Based Anomaly Detection Reveals Clinical-Radiologic Heterogeneity in Pulmonary Fibrosis.

Constantin Ghimuș1, Călin Gheorghe Buzea2,3, Alin Horațiu Nedelcu1,4

  • 1Grigore T. Popa University of Medicine and Pharmacy, 700115 Iasi, Romania.

Medical Sciences (Basel, Switzerland)
|February 20, 2026
PubMed
Summary
This summary is machine-generated.

Artificial intelligence (AI) can identify atypical clinical-radiologic profiles in pulmonary fibrosis (PF) by integrating imaging and clinical data. This AI approach reveals disease heterogeneity beyond standard severity measures, aiding in personalized patient phenotyping.

Keywords:
CT imaginganomaly detectionautoencoderdeep learningmultimodal AIpost-infectious fibrosispulmonary fibrosisvariational autoencoder

More Related Videos

Multifractal Spectrum Analysis for Assessing Pulmonary Nodule Malignancy
05:24

Multifractal Spectrum Analysis for Assessing Pulmonary Nodule Malignancy

Published on: January 10, 2025

942
Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
07:53

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Published on: October 13, 2023

2.2K

Related Experiment Videos

Last Updated: Feb 22, 2026

Unilateral Lung Volume Analysis Using Micro-CT for Enhanced Assessment of Pulmonary Fibrosis in Preclinical Models
03:38

Unilateral Lung Volume Analysis Using Micro-CT for Enhanced Assessment of Pulmonary Fibrosis in Preclinical Models

Published on: June 20, 2025

1.0K
Multifractal Spectrum Analysis for Assessing Pulmonary Nodule Malignancy
05:24

Multifractal Spectrum Analysis for Assessing Pulmonary Nodule Malignancy

Published on: January 10, 2025

942
Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
07:53

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Published on: October 13, 2023

2.2K

Area of Science:

  • Radiology
  • Artificial Intelligence
  • Pulmonary Medicine

Background:

  • Pulmonary fibrosis (PF) exhibits significant heterogeneity in imaging patterns, physiological impairment, and clinical presentation.
  • Conventional methods struggle to capture complex, non-linear relationships between imaging findings and functional limitations in PF.
  • Artificial intelligence (AI) offers a potential solution for comprehensive disease characterization by integrating diverse data types.

Purpose of the Study:

  • To develop and evaluate a multimodal AI framework for identifying atypical clinical-radiologic profiles in PF patients.
  • Utilize unsupervised anomaly detection to analyze heterogeneity in fibrotic lung disease.
  • Combine imaging-derived features with structured clinical data for enhanced patient phenotyping.

Main Methods:

  • Retrospective analysis of 41 patients with confirmed pulmonary fibrosis or post-infectious fibrotic lung disease.
  • Extracted deep imaging embeddings from thoracic CT scans using a pretrained convolutional neural network.
  • Integrated imaging embeddings with clinical and functional variables into a multimodal variational autoencoder (VAE) for unsupervised anomaly detection.

Main Results:

  • Anomaly scores, derived from VAE reconstruction error and KL divergence, quantified patient-specific deviations.
  • A significant portion of patients (17.1%) showed high anomaly scores, irrespective of clinician-assigned severity.
  • High anomaly scores correlated weakly with conventional markers (e.g., DLCO, FEV1), indicating detection of multimodal deviations rather than severity alone.
  • Identified patients with discordant profiles, such as preserved function despite significant imaging abnormalities.

Conclusions:

  • Multimodal AI anomaly detection effectively quantifies clinical-radiologic heterogeneity in PF beyond traditional severity metrics.
  • Unsupervised anomaly detection provides a valuable tool for identifying atypical patient profiles and generating hypotheses in fibrotic lung disease.
  • This proof-of-concept study highlights the potential for AI in individualized phenotyping and understanding disease complexity.