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 Experiment Video

Updated: May 28, 2026

A Silicosis Mouse Model Established by Repeated Inhalation of Crystalline Silica Dust
10:45

A Silicosis Mouse Model Established by Repeated Inhalation of Crystalline Silica Dust

Published on: January 6, 2023

SiCLIP: An explainable multimodal framework for silicosis diagnosis.

Duy Le1, Tien Nguyen2, Huyen Nguyen1

  • 1Posts and Telecommunications Institute of Technology, Hanoi, Viet Nam.

Artificial Intelligence in Medicine
|May 26, 2026
PubMed
Summary
This summary is machine-generated.

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

VeloRM: disentangling pre- and post-splicing RNA modification dynamics at single-cell resolution.

Nucleic acids research·2026
Same author

Perceptual quality assessment in digital pathology: Modeling diagnostic usability from expert opinions.

Computer methods and programs in biomedicine·2026
Same author

Explosive nucleation and growth of Pb islands on Ge(111) below room temperature via collective diffusion.

Journal of physics. Condensed matter : an Institute of Physics journal·2026
Same author

TRIM21 facilitates inflammasome assembly and contributes to autoinflammatory disease.

Nature communications·2026
Same author

Self-administration of oral voluntary assisted dying medication in Victoria, Australia: the first 6 years.

BMJ supportive & palliative care·2026
Same author

Objective quantification of motion-induced dizziness using a proof-of-concept multimodal wearable platform.

Scientific reports·2026
Same journal

Real-time EEG-based epileptic seizure prediction using artificial intelligence: A systematic review.

Artificial intelligence in medicine·2026
Same journal

R-peak detection and ECG data compression scheme based on empirical mode decomposition and wavelet transform.

Artificial intelligence in medicine·2026
Same journal

CastNet: A three-channel EEG-based deep learning model for cross-subject depression detection.

Artificial intelligence in medicine·2026
Same journal

State-of-the-art TinyML approaches for colorectal cancer detection: Current advances, challenges, and future directions.

Artificial intelligence in medicine·2026
Same journal

JRadiEvo: A Japanese radiology report generation model enhanced by evolutionary optimization of model merging.

Artificial intelligence in medicine·2026
Same journal

Causally-informed deep learning towards explainable and generalizable outcome prediction in critical care.

Artificial intelligence in medicine·2026
See all related articles

Early detection of silicosis, an occupational lung disease, is challenging. A new multimodal AI framework (SiCLIP) using X-rays and patient data shows promise for improved screening in at-risk workers.

Area of Science:

  • Occupational Medicine
  • Artificial Intelligence
  • Medical Imaging

Background:

  • Silicosis is a severe occupational lung disease caused by crystalline silica dust exposure.
  • Early detection of silicosis in at-risk populations remains a significant clinical challenge.
  • Existing diagnostic methods often lack early sensitivity, necessitating advanced screening tools.

Purpose of the Study:

  • To introduce the Silicosis Diagnosis Dataset (SDD), a multimodal dataset combining chest X-rays and patient profiles.
  • To propose and evaluate SiCLIP, a novel multimodal retrieval framework for silicosis screening and classification.
  • To enhance early detection capabilities for silicosis in occupationally exposed individuals.

Main Methods:

  • Development of the Silicosis Diagnosis Dataset (SDD) with chest X-rays and structured patient data.
Keywords:
Explainable frameworkSilicosis detectionVision-language models

More Related Videos

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

Establishing a Silicosis Rat Model via Exposure of Whole-Body to Respirable Silica
05:03

Establishing a Silicosis Rat Model via Exposure of Whole-Body to Respirable Silica

Published on: October 28, 2022

Related Experiment Videos

Last Updated: May 28, 2026

A Silicosis Mouse Model Established by Repeated Inhalation of Crystalline Silica Dust
10:45

A Silicosis Mouse Model Established by Repeated Inhalation of Crystalline Silica Dust

Published on: January 6, 2023

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

Establishing a Silicosis Rat Model via Exposure of Whole-Body to Respirable Silica
05:03

Establishing a Silicosis Rat Model via Exposure of Whole-Body to Respirable Silica

Published on: October 28, 2022

  • Implementation of SiCLIP, a multimodal framework utilizing CLIP-ViT for learning a shared embedding space.
  • Application of retrieval-based aggregation for prediction and binary classification of silicosis.
  • Generation of saliency visualizations for case-based interpretability.

    • Main Results:

    • SiCLIP achieved superior accuracy and F1-score compared to image-only baselines on the SDD benchmark.
    • The proposed framework outperformed a comparative multimodal Vision-Language Model (VLM) baseline.
    • SiCLIP demonstrated case-based interpretability through retrieval of similar cases and saliency maps.

    Conclusions:

    • Multimodal retrieval using SiCLIP is a promising approach for supporting silicosis screening in exposed populations.
    • The integration of imaging and clinical data enhances diagnostic performance.
    • External validation is required prior to widespread clinical deployment of the SiCLIP framework.