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 Videos

A multimodal deep learning framework for precise silicosis detection on radiographic images.

Ramesh N S V S C Sripada1, Pothuri Surendra Varma2, E Laxmi Lydia3

  • 1Department of Computer Science and Engineering, Aditya University, Surampalem, AP, India.

Scientific Reports
|June 22, 2026
PubMed
Summary

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

Cross-attention guided explainable deep transformer model for multi-level classification of rare neurological disorders using MRI images.

Scientific reports·2026
Same author

Advancing biomedical data analytics using explainable neural network-based learning model for progressive neurodegenerative disorder diagnosis.

Scientific reports·2026
Same author

Modelling of hybrid deep ensemble learning based skin lesion detection using FCNN denoising and inception-dilated ResNetV2.

Scientific reports·2026
Same author

Efficacy of Celosia argentea Linn. Seeds in Management of Type 2 Diabetes Mellitus: A Randomized, Double-Blind, Placebo-controlled Clinical Trial.

Alternative therapies in health and medicine·2026
Same author

A multimodal feature fusion with deep representation learning approach for polycystic ovary syndrome diagnosis using ultrasound images.

Scientific reports·2026
Same author

Transformer-assisted convolutional feature extraction with deep representation learning models for lung and colon cancer diagnosis using histopathological images.

Scientific reports·2026

A new multimodal deep learning framework (MDLF-EISD) accurately identifies silicosis from radiological images. This AI tool aids early diagnosis, improving patient outcomes in occupational lung disease screening.

Area of Science:

  • Occupational Medicine and Pulmonology
  • Artificial Intelligence in Medical Imaging
  • Radiology and Diagnostic Imaging

Background:

  • Pneumoconiosis, including silicosis, is a significant occupational lung disease caused by dust inhalation, leading to lung scarring and inflammation.
  • Current silicosis diagnosis relies on routine monitoring, including physical exams, medical history, and imaging, with chest radiography being a common screening method.
  • Deep learning (DL) shows promise in medical image classification, with convolutional neural networks effectively analyzing radiographic images for disease detection.

Purpose of the Study:

  • To introduce a novel Multimodal Deep Learning Framework for Early Identification of Silicosis Diagnosis (MDLF-EISD) using radiological images.
  • To enable timely clinical intervention and improve patient outcomes through enhanced early silicosis diagnosis.
  • To develop a computer-aided screening tool for early silicosis detection, especially in resource-limited settings.
Keywords:
Artificial intelligenceDeep learningFeature fusionPrecision diagnosticsRadiological image analysisSilicosis diagnosis

Related Experiment Videos

Main Methods:

  • The MDLF-EISD framework employs feature fusion integrating EfficientNet-B3, a capsule network, and ConvNext V2 to capture complementary radiographic representations.
  • A convolutional bidirectional attention model is utilized for effective classification of silicosis into distinct categories.
  • Extensive simulation studies were conducted on the Silicodata dataset to evaluate the framework's performance.

Main Results:

  • The MDLF-EISD method achieved a superior accuracy of 98.73% compared to other evaluated models.
  • Feature fusion demonstrated improved discriminative capabilities for identifying silicosis-related radiographic findings.
  • The proposed framework effectively captures disease-specific patterns across different silicosis severity levels.

Conclusions:

  • The MDLF-EISD framework shows significant potential as a computer-aided screening tool for early silicosis diagnosis.
  • The study highlights the effectiveness of multimodal deep learning and feature fusion in enhancing diagnostic accuracy for occupational lung diseases.
  • This AI-driven approach can support clinical decision-making and improve patient management in occupational health settings.