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: Feb 21, 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

3.6K

Development of a No-Reference CT Image Quality Assessment Method Using RadImageNet Pre-trained Deep Learning Models.

Kohei Ohashi1,2, Yukihiro Nagatani2, Asumi Yamazaki1,3

  • 1Division of Health Sciences, The University of Osaka Graduate School of Medicine, Suita, Japan.

Journal of Imaging Informatics in Medicine
|May 27, 2025
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

[3. Data Literacy (1): Data Types, Central Values, and Variability].

Nihon Hoshasen Gijutsu Gakkai zasshi·2026
Same author

Comparative Evaluation of Encoder- and Decoder-Based Models for Actionable Findings in CT Reports.

Journal of imaging informatics in medicine·2026
Same author

Enhanced shielding effectiveness for scattered X-rays in diagnostic radiology using origami-inspired 3D tungsten functional paper structures.

European journal of radiology·2026
Same author

Robustness of heart dose against cardiac cycle in breast cancer radiotherapy with deep inspiration breath-hold.

Radiological physics and technology·2026
Same author

Enhancing Explainability in AI-Based Interstitial Lung Disease Detection via Multi-Class Learning Based on Lesion Areas.

Journal of imaging informatics in medicine·2026
Same author

Investigation into the utility of ultra-high-resolution mode on dynamic-ventilation computed tomography using sponge phantoms.

Scientific reports·2025
This summary is machine-generated.

A new deep learning method improves computed tomography (CT) no-reference image quality assessment (NR-IQA) by handling multiple degradations. This approach enhances diagnostic accuracy and optimizes radiation dose, acting as a surrogate for subjective image quality evaluation.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Radiology

Background:

  • Accurate computed tomography (CT) image quality assessment is vital for diagnosis and radiation safety.
  • No-reference image quality assessment (NR-IQA) is crucial when reference images are unavailable.
  • Existing deep learning CT-NR-IQA methods struggle with multiple degradations and real-world variations.

Purpose of the Study:

  • To develop a novel CT-NR-IQA method addressing limitations of current approaches.
  • To enhance the model's ability to handle multiple degradation factors like noise and blur.
  • To improve adaptability to real-world CT image degradations.

Main Methods:

  • Utilized a dataset combining noise and blur to train convolutional neural network (CNN) models.
Keywords:
Computed tomographyDeep learningImage quality assessmentNR-IQAObjective assessmentRadImageNet

More Related Videos

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

43.6K

Related Experiment Videos

Last Updated: Feb 21, 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

3.6K
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

43.6K
  • Leveraged RadImageNet pre-trained models (ResNet50, DenseNet121, InceptionV3, InceptionResNetV2).
  • Evaluated model performance using correlation coefficients between subjective and predicted scores on artificial and real clinical datasets.

    • Main Results:

    • Demonstrated positive correlations between subjective and predicted image quality scores for both datasets.
    • ResNet50 achieved the highest performance with correlation coefficients of 0.910 (artificial) and 0.831 (real clinical).
    • The proposed method showed strong adaptability to real-world degradations without requiring artificially degraded images.

    Conclusions:

    • The novel CT-NR-IQA method effectively handles multiple degradation factors.
    • Pre-trained models like ResNet50 significantly enhance performance and adaptability to real-world CT images.
    • The proposed approach shows potential as a surrogate for subjective image quality assessment in CT scans.