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

ARTEMIS: An Explainable AI Framework for Multi-Class COVID-19 Diagnosis with a Newly Curated Dataset.

Muhammet Emin Sahin1,2, Hasan Ulutas3, Mustafa Fatih Erkoc4

  • 1Department of Computer Engineering, Izmir Bakırçay University, Izmir 35665, Türkiye.

Bioengineering (Basel, Switzerland)
|May 27, 2026
PubMed
Summary

Related Concept Videos

Classification of Illness01:17

Classification of Illness

The meaning of illness is individualized to each person who experiences an alteration in health. In contrast, disease is a medical term indicating a pathological change in the structure and function of the body or mind. It is a condition that has specific symptoms and boundaries.
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe and...

You might also read

Related Articles

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

Sort by
Same author

Explainable Ensemble Learning for Robust Severity Stratification of Carpal Tunnel Syndrome from Clinical Data.

Diagnostics (Basel, Switzerland)·2026
Same author

Evaluation of the Relationship Between Trace Element Levels and Cellular Adhesion Molecules (ICAM-1, VCAM-1) in Hemodialysis Patients.

Journal of clinical medicine·2026
Same author

A novel hybrid medical image encryption scheme based on memristive chaos and DNA-ARX-3DES with Real-Time implementation.

Scientific reports·2026
Same author

Optimized YOLO architectures for efficient Kiwi detection in precision agriculture on embedded systems.

Scientific reports·2025
Same author

Assessment of Microplastic Exposure in Diabetic Patients Using Insulin.

Toxics·2025
Same author

Efficient Cerebral Infarction Segmentation Using U-Net and U-Net3 + Models.

Journal of imaging informatics in medicine·2025

ARTEMIS, a deep learning model, accurately classifies Chest X-ray (CXR) and Computed Tomography (CT) images for COVID-19, pneumonia, and normal cases. Its adaptive preprocessing and hybrid network ensure clinically meaningful, interpretable results.

Area of Science:

  • Artificial Intelligence
  • Medical Imaging Analysis
  • Deep Learning

Background:

  • Accurate classification of thoracic imaging is crucial for diagnosing respiratory diseases like COVID-19 and Community-Acquired Pneumonia (CAP).
  • Existing deep learning models often rely on static preprocessing, limiting their adaptability to diverse image characteristics.

Purpose of the Study:

  • To introduce ARTEMIS, a novel, interpretable deep learning pipeline for classifying Chest X-ray (CXR) and Computed Tomography (CT) images.
  • To enable automatic differentiation between COVID-19 infection, CAP, and normal cases using medical imaging.

Main Methods:

  • ARTEMIS utilizes a learnable preprocessing component for dynamic image contrast and sharpness adaptation.
  • A hybrid network architecture combines EfficientNet-B0 with SE attention and an optional Transformer encoder for local and global feature learning.
Keywords:
COVID-19CTExplainable AI (Grad-CAM++)X-raydeep learning

Related Experiment Videos

  • The model was evaluated on five datasets (four public, one novel CT) including both X-ray and CT modalities.

    • Main Results:

    • ARTEMIS achieved macro F1-scores over 96% on public datasets and 99.39% accuracy on a new CT dataset.
    • Class-discriminative saliency maps generated by Grad-CAM++ were validated by a radiologist, confirming clinical relevance.
    • The model demonstrated strong robustness and generalization across different datasets and imaging modalities.

    Conclusions:

    • ARTEMIS provides a robust, interpretable, and highly accurate method for classifying thoracic pathologies from CXR and CT images.
    • The learnable preprocessing and hybrid network design contribute to improved diagnostic performance.
    • Model decisions are grounded in clinically meaningful radiological findings, enhancing trust and clinical utility.