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: Jan 9, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.3K

Explainable AI for Multi-Label Chest X-ray Diagnosis: Layer-wise Grad-CAM with Hierarchical Feature Extraction.

Kyungjin Kim, Youna Choi, Jongmo Seo

    Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
    |December 3, 2025
    PubMed
    Summary

    This study introduces an explainable AI framework using U-Net and Grad-CAM for chest X-ray analysis. It enhances diagnostic transparency and clinician trust in artificial intelligence for medical imaging.

    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

    A chip integration method for implantable devices based on structural embedding using cyclic olefin copolymer.

    IEEE transactions on bio-medical engineering·2026
    Same author

    Thermally Conductive and Compliant PIB-hBN Nanocomposite Encapsulation for Soft Neural Interfaces.

    ACS applied bio materials·2026
    Same author

    Untargeted plasma metabolomics in canine cognitive dysfunction: the naturally occurring Alzheimer's disease analog in dogs.

    Frontiers in neuroscience·2026
    Same author

    Synthesis of triazolopyrimidinone- and imidazotriazinone-based tankyrase inhibitors: Identification of Basroparib (STP1002) as a clinical candidate.

    Bioorganic & medicinal chemistry letters·2026
    Same author

    Optimization of Pressing Parameters for 3D Perfluoroalkoxy (PFA) Electrode Fabrication.

    Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
    Same author

    Bridging Ensemble Performance and Transparency: Knowledge Distillation for Obesity Classification on KNHANES Dataset.

    Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025

    Area of Science:

    • Medical Imaging
    • Artificial Intelligence
    • Radiology

    Background:

    • Artificial intelligence (AI) models like CNNs and Transformers excel in medical image analysis.
    • Lack of interpretability in AI hinders clinical adoption, as understanding disease features is crucial for trust.

    Purpose of the Study:

    • To develop an explainability framework for multi-label disease classification in chest X-ray (CXR) diagnosis.
    • To enhance the interpretability of AI models in radiology using a U-Net architecture and Grad-CAM.

    Main Methods:

    • Utilized a U-Net encoder-decoder architecture to capture hierarchical features for classifying 14 observations in the MIMIC-CXR dataset.
    • Applied gradient-weighted class activation mapping (Grad-CAM) across multiple layers to visualize disease-specific regions.

    More Related Videos

    Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
    04:09

    Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

    Published on: October 10, 2018

    8.6K

    Related Experiment Videos

    Last Updated: Jan 9, 2026

    Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
    07:15

    Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

    Published on: August 16, 2020

    7.3K
    Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
    04:09

    Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

    Published on: October 10, 2018

    8.6K
  • Integrated U-Net with an explainable AI (XAI) framework to improve transparency.

    • Main Results:

    • The proposed framework effectively captures hierarchical features for multi-label CXR classification.
    • Grad-CAM visualizations provided detailed insights into feature refinement and disease-specific region emphasis.
    • Enhanced transparency in the AI diagnostic process was achieved.

    Conclusions:

    • The study highlights the critical role of interpretability in AI-based radiology.
    • The framework fosters greater trust in AI tools by providing clear visualizations for clinical validation.
    • This approach supports AI as a robust, clinician-friendly decision support system in routine radiological workflows.