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

Difference from Background: Limit of Detection01:05

Difference from Background: Limit of Detection

7.4K
The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...
7.4K
Super-resolution Fluorescence Microscopy01:37

Super-resolution Fluorescence Microscopy

9.6K
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...
9.6K

You might also read

Related Articles

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

Sort by
Same author

Label-free segmentation of mitochondria for simultaneous morphological and metabolic studies.

Communications biology·2026
Same author

Application of learned ideal observers for estimating task-based performance bounds for computed imaging systems.

Journal of medical imaging (Bellingham, Wash.)·2026
Same author

Enhancing deep learning interpretability for hand-crafted feature-guided histologic image classification via weak-to-strong generalization.

Journal of medical imaging (Bellingham, Wash.)·2026
Same author

Approximating the ideal observer for joint signal detection and estimation tasks by the use of Markov-Chain Monte Carlo with generative adversarial networks.

Journal of medical imaging (Bellingham, Wash.)·2025
Same author

Semi-supervised semantic segmentation of cell nuclei with diffusion model and collaborative learning.

Journal of medical imaging (Bellingham, Wash.)·2025
Same author

Optimizing quantitative photoacoustic imaging systems: the Bayesian Cramér-Rao bound approach.

Inverse problems·2024

Related Experiment Video

Updated: Oct 12, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

682

Impact of deep learning-based image super-resolution on binary signal detection.

Xiaohui Zhang1, Varun A Kelkar2, Jason Granstedt3

  • 1University of Illinois at Urbana-Champaign, Department of Bioengineering, Urbana, Illinois, United States.

Journal of Medical Imaging (Bellingham, Wash.)
|November 19, 2021
PubMed
Summary

Deep learning-based image super-resolution (DL-SR) improves traditional image quality but often fails to enhance medical imaging task performance. DL-SR can benefit suboptimal observers in specific scenarios, highlighting the need for objective assessment.

Keywords:
Rayleigh detection taskdeep learning-based image super-resolutionnumerical observersobjective image quality assessment

More Related Videos

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

960
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

3.0K

Related Experiment Videos

Last Updated: Oct 12, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

682
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

960
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

3.0K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computer Vision

Background:

  • Deep learning-based image super-resolution (DL-SR) shows potential in medical imaging.
  • Current DL-SR assessments primarily use computer vision image quality (IQ) metrics.
  • The impact of DL-SR on medical imaging task-specific IQ remains under-explored.

Purpose of the Study:

  • To investigate the effect of DL-SR methods on binary signal detection performance in medical imaging.
  • To evaluate if DL-SR enhances objective IQ measures relevant to clinical tasks.
  • To determine the influence of DL-SR network complexity and its utility for suboptimal observers.

Main Methods:

  • Trained two popular DL-SR methods (Super-Resolution Convolutional Neural Network, Super-Resolution Generative Adversarial Network) on simulated medical data.
  • Formulated binary signal detection tasks (e.g., signal-known-exactly/background-known-statistically).
  • Employed numerical observers (ideal and linear) to assess DL-SR impact on task performance and observer efficacy.

Main Results:

  • DL-SR improved traditional IQ measures as anticipated.
  • DL-SR provided minimal to no improvement in task performance for many scenarios, sometimes causing degradation.
  • DL-SR demonstrated potential to enhance the task performance of suboptimal observers under certain conditions.

Conclusions:

  • Objective assessment of DL-SR methods is crucial for medical imaging applications.
  • Current DL-SR approaches may not translate to improved diagnostic performance.
  • Further research is needed to optimize DL-SR for enhanced efficacy in medical tasks.