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

Super-resolution Fluorescence Microscopy01:37

Super-resolution Fluorescence Microscopy

12.3K
Super-resolution fluorescence microscopy (SRFM) provides a better resolution than conventional fluorescence microscopy by reducing the point spread function (PSF). PSF is the light intensity distribution from a point that causes it to appear blurred. Due to PSF, each fluorescing point appears bigger than its actual size, and it is the PSF interference of nearby fluorophores that causes the blurred image. Various approaches to achieving higher resolution through SRFM have recently been...
12.3K

You might also read

Related Articles

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

Sort by
Same author

Evaluation of anemia in non-enhanced and contrast-enhanced dual-energy CT using electron density imaging.

PloS one·2026
Same author

Hemostatic and antibacterial performance of alginate/tannic acid-coated gauze for advanced wound care.

Biomedical materials (Bristol, England)·2026
Same author

Myeloid miR-155 deficiency exacerbates viral encephalitis by hindering M1 macrophage polarization due to impaired NLRP3 inflammasome activation in extraneural tissues.

Frontiers in immunology·2026
Same author

Harnessing inter-spheroid spacing and structural connectivity to direct collective cell migration and host vessel integration in 3D engineered tissue.

Materials today. Bio·2026
Same author

Development of an osteo-angiogenic scaffold derived from decellularization of spheroid-embedded 3D constructs for vascularized bone regeneration.

Materials horizons·2026
Same author

Transfer learning for Multi-institutional Classification of Intussusception and Splenomegaly in Pediatric Abdominal Radiographs.

Journal of imaging informatics in medicine·2026

Related Experiment Video

Updated: May 4, 2026

A Micro-CT-based Method for Characterizing Lesions and Locating Electrodes in Small Animal Brains
05:12

A Micro-CT-based Method for Characterizing Lesions and Locating Electrodes in Small Animal Brains

Published on: November 8, 2018

9.0K

Enhancing Lesion Detection in Rat CT Images: A Deep Learning-Based Super-Resolution Study.

Sungwon Ham1, Sang Hoon Jeong2, Hong Lee2

  • 1Healthcare Readiness Institute for Unified Korea, Korea University Ansan Hospital, Korea University College of Medicine, 123 Jeokgeum-Ro, Danwon-Gu, Ansan-Si 15355, Gyeonggi, Republic of Korea.

Biomedicines
|October 29, 2025
PubMed
Summary
This summary is machine-generated.

Deep learning super-resolution (SR) enhances rat chest CT image quality. The OmniSR model improved lesion detection and overall interpretability, outperforming traditional metrics like PSNR and SSIM.

Keywords:
computed tomographydeep learninglow-resolution imagingpreclinical imagingsuper-resolution reconstruction

More Related Videos

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

3.3K
Two-Dimensional Super-Resolution Visualization of Rat Brain Microvasculature Using Ultrasound Localization Microscopy
07:26

Two-Dimensional Super-Resolution Visualization of Rat Brain Microvasculature Using Ultrasound Localization Microscopy

Published on: March 28, 2025

1.0K

Related Experiment Videos

Last Updated: May 4, 2026

A Micro-CT-based Method for Characterizing Lesions and Locating Electrodes in Small Animal Brains
05:12

A Micro-CT-based Method for Characterizing Lesions and Locating Electrodes in Small Animal Brains

Published on: November 8, 2018

9.0K
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

3.3K
Two-Dimensional Super-Resolution Visualization of Rat Brain Microvasculature Using Ultrasound Localization Microscopy
07:26

Two-Dimensional Super-Resolution Visualization of Rat Brain Microvasculature Using Ultrasound Localization Microscopy

Published on: March 28, 2025

1.0K

Area of Science:

  • Medical Imaging
  • Radiology
  • Artificial Intelligence in Medicine

Background:

  • Preclinical chest CT imaging in small animals suffers from low resolution, hindering subtle lesion detection.
  • Traditional quantitative metrics (PSNR, SSIM) may not correlate with clinical interpretability of super-resolved images.
  • Need for advanced methods to improve image quality and diagnostic accuracy in small animal CT.

Purpose of the Study:

  • To evaluate deep learning-based super-resolution (SR) models for enhancing rat chest CT image quality.
  • To assess if SR improves lesion detectability and clinical interpretability.
  • To compare quantitative metrics with radiologist assessments for SR model evaluation.

Main Methods:

  • Retrospective analysis of 222 rat chest CT scans from PHMG-p exposure studies.
  • Implementation and comparison of three SR models: SinSR, SinSR3 (segmentation-guided), and OmniSR.
  • Independent blinded evaluation by two thoracic radiologists assessing lesion clarity, nodule detectability, noise, artifacts, and overall quality.

Main Results:

  • SinSR1 and SinSR3 achieved highest PSNR and SSIM, respectively.
  • OmniSR, despite lower PSNR, received the highest radiologist ratings for lesion margin clarity, nodule detectability, and overall image quality.
  • Radiologist assessments showed limited correlation with conventional PSNR and SSIM metrics.

Conclusions:

  • Deep learning-based SR significantly improves visualization of rat chest CT images.
  • OmniSR demonstrated superior clinical interpretability compared to other SR models and traditional metrics.
  • Reader-centered evaluation is crucial for assessing SR techniques in preclinical imaging.