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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Life, death, and 280 characters: a hashtag analysis of #AssistedSuicide on X (2015-2025).

Frontiers in digital health·2026
Same author

Fluorodeoxyglucose PET Scans in the Integrative Medicine Setting.

PET clinics·2026
Same author

Rural cancer research activity across Europe: A bibliometric analysis on patterns, gaps and policy implications.

European journal of oncology nursing : the official journal of European Oncology Nursing Society·2026
Same author

Media representations of rural and coastal cancer inequalities in the UK: A 10-year retrospective place-based analysis.

Health & place·2026
Same author

Coastal cancer care: A blueprint to address the unmet needs through place-based research and policy approaches.

Journal of cancer policy·2026
Same author

"You lose a day for every appointment": A qualitative study of how rural versus urban residence shapes cancer care experiences in Northeast Scotland.

Supportive care in cancer : official journal of the Multinational Association of Supportive Care in Cancer·2026

Related Experiment Video

Updated: Jul 9, 2025

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

2.8K

Label-Free Medical Image Quality Evaluation by Semantics-Aware Contrastive Learning in IoMT.

Dewei Yi, Yining Hua, Peter Murchie

    IEEE Journal of Biomedical and Health Informatics
    |December 7, 2023
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces a novel label-free Medical Image Quality Assessment (MIQA) model using zero-shot learning. The Semantics-Aware Contrastive Learning (SCL) approach effectively assesses diverse medical image types without needing labeled data.

    More Related Videos

    Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
    05:56

    Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

    Published on: April 14, 2023

    2.5K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    406

    Related Experiment Videos

    Last Updated: Jul 9, 2025

    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

    2.8K
    Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
    05:56

    Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

    Published on: April 14, 2023

    2.5K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    406

    Area of Science:

    • Artificial Intelligence
    • Medical Imaging
    • Internet-of-Medical-Things (IoMT)

    Background:

    • Internet-of-Medical-Things (IoMT) offers solutions for medical staff workload, especially in Medical Image Quality Assessment (MIQA).
    • Traditional MIQA models require extensive labeled datasets, posing a significant challenge for training and development.
    • Effective MIQA is crucial for accurate diagnosis and treatment across various medical imaging modalities.

    Purpose of the Study:

    • To develop a label-free MIQA model addressing the limitations of traditional methods requiring large labeled datasets.
    • To introduce a Semantics-Aware Contrastive Learning (SCL) model capable of generalizing quality assessment to diverse medical image types.
    • To demonstrate the efficacy of a zero-shot learning approach for medical image quality evaluation.

    Main Methods:

    • A novel Semantics-Aware Contrastive Learning (SCL) model is proposed, utilizing zero-shot learning via a tailored Contrastive Language-Image Pre-training (CLIP) model.
    • The SCL model integrates features from zero-shot learning, spatial domain (Natural Scene Statistics and patch-based features), and frequency domain (local and global hierarchical features).
    • The model was evaluated on two existing datasets (EyeQ, LiverQ) and a newly created dataset for skin image quality assessment.

    Main Results:

    • The proposed SCL method demonstrated superior performance compared to existing advanced models across three distinct medical image quality datasets.
    • The label-free, zero-shot learning approach proved effective in generalizing quality assessment to various medical image types.
    • Integration of multi-domain features (zero-shot, spatial, frequency) contributed to robust quality scoring.

    Conclusions:

    • The developed label-free SCL model offers a promising solution for Medical Image Quality Assessment, overcoming the need for large labeled datasets.
    • The zero-shot learning approach enables effective generalization of MIQA across different medical imaging modalities.
    • This research advances the application of AI in IoMT for improved medical image analysis and diagnostic support.