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: Jul 2, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Deep reinforcement learning-based reversible medical image encryption framework for secure IoMT environments.

K Mahalakshmi1, Sivakumar Nagarajan2

  • 1Department of Mathematics, School of Advanced Sciences, Vellore Institute of Technology, Vellore, Tamil Nadu, India.

Frontiers in Artificial Intelligence
|July 1, 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

A hybrid machine learning and explainable AI framework for optimizing risk-based authentication.

PloS one·2026
Same author

Photocatalytic and Antibacterial Activity of CoFe<sub>2</sub>O<sub>4</sub> Nanoparticles from <i>Hibiscus rosa-sinensis</i> Plant Extract.

Nanomaterials (Basel, Switzerland)·2022
Same author

Influential role of 7-Ketocholesterol in the progression of Alzheimer's disease.

Prostaglandins & other lipid mediators·2021
Same author

Unveiling the Impacted Canine - Eyelet Chain Guide: Concepts and Clinical Application.

Contemporary clinical dentistry·2021
Same author

Vehicular Cloud for Smart Driving Using Internet of Things.

Journal of medical systems·2018
Same author

A novel and less invasive technique to assess cytokine profile of vitreous in patients of diabetic macular oedema.

Eye (London, England)·2018

This study introduces a secure, reversible encryption framework for medical images in the Internet of Medical Things (IoMT). It uses deep reinforcement learning and adaptive encryption to protect sensitive data against cyber threats.

Area of Science:

  • Cybersecurity
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Internet of Medical Things (IoMT) environments face significant challenges in securely transmitting and storing medical images due to limited resources and increasing cybersecurity threats.
  • Existing encryption methods may not adequately address the unique demands of IoMT, such as dynamic adaptation and resource constraints.

Purpose of the Study:

  • To propose a novel, reversible RGB medical image encryption framework for IoMT environments.
  • To enhance the security and integrity of medical image transmission and storage.
  • To leverage deep reinforcement learning for adaptive encryption strategies.

Main Methods:

  • A deep reinforcement learning approach using a Deep Q-Network (DQN) for adaptive encryption action selection.
Keywords:
Internet of Medical Things (IoMT)chaotic cryptographydeep reinforcement learningdeterministic encryptiondifferential attack resistancemedical image encryptionreversible encryption

Related Experiment Videos

Last Updated: Jul 2, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

  • A multi-layer reversible encryption technique combining SHA-512 keystream masking, Arnold scrambling, and chaotic diffusion.
  • Statistical feature extraction from intermediate encrypted image states for dynamic policy learning.

    • Main Results:

    • The framework demonstrated high entropy (approaching 7.999), optimal NPCR (>99.9%), and UACI (up to 40%).
    • Achieved minimal pixel correlation and near-zero SSIM, indicating robust protection against statistical and differential attacks.
    • Showed resilience against noise, data loss, occlusion, chosen plaintext, and determinism leaking attacks.

    Conclusions:

    • The proposed framework offers a robust and scalable solution for secure medical image encryption in IoMT.
    • The integration of deep reinforcement learning provides adaptive security, outperforming fixed encryption systems.
    • The framework ensures high security, precise image recovery, and efficient computational complexity for high-resolution medical images.