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

MPU-rPPG: A Comprehensive and High-Fidelity Dataset for Remote Photoplethysmography Across Diverse Conditions and Demographics.

Scientific data·2026
Same author

Differences in amyloid PET positivity based on ethnoracial group and social determinants of health: The new IDEAS study.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2026
Same author

UniEmo: Unifying Emotional Understanding and Generation With Learnable Expert Queries.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

Surface engineering of extracellular vesicles: trends, strategies, and applications in diagnosis and therapy.

Journal of nanobiotechnology·2026
Same author

Multi-Granularity Facial Emotional Representation With Unlabeled Data and Textual Supervision.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

Pediatric thyroid cancer lung metastases and RAI: long-term results.

Journal of pediatric endocrinology & metabolism : JPEM·2026

Related Experiment Video

Updated: Jul 10, 2025

Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph
05:32

Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph

Published on: February 21, 2025

295

A task-specific deep-learning-based denoising approach for myocardial perfusion SPECT.

Md Ashequr Rahman1, Zitong Yu1, Barry A Siegel2

  • 1Department of Biomedical Engineering, Washington University in St. Louis, St. Louis, MO, USA.

Proceedings of Spie--The International Society for Optical Engineering
|November 22, 2023
PubMed
Summary
This summary is machine-generated.

Deep learning (DL) denoising improves low-dose myocardial perfusion SPECT imaging by preserving task-specific information for better defect detection. This approach enhances observer performance in clinical settings.

Keywords:
Objective task-based evaluationSPECTdeep learningimage denoisingmyocardial perfusion imagingsignal detection

More Related Videos

Intra-cardiac Side-Firing Light Catheter for Monitoring Cellular Metabolism using Transmural Absorbance Spectroscopy of Perfused Mammalian Hearts
08:51

Intra-cardiac Side-Firing Light Catheter for Monitoring Cellular Metabolism using Transmural Absorbance Spectroscopy of Perfused Mammalian Hearts

Published on: May 12, 2019

6.8K
Oxygenation-sensitive Cardiac MRI with Vasoactive Breathing Maneuvers for the Non-invasive Assessment of Coronary Microvascular Dysfunction
08:35

Oxygenation-sensitive Cardiac MRI with Vasoactive Breathing Maneuvers for the Non-invasive Assessment of Coronary Microvascular Dysfunction

Published on: August 17, 2022

2.4K

Related Experiment Videos

Last Updated: Jul 10, 2025

Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph
05:32

Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph

Published on: February 21, 2025

295
Intra-cardiac Side-Firing Light Catheter for Monitoring Cellular Metabolism using Transmural Absorbance Spectroscopy of Perfused Mammalian Hearts
08:51

Intra-cardiac Side-Firing Light Catheter for Monitoring Cellular Metabolism using Transmural Absorbance Spectroscopy of Perfused Mammalian Hearts

Published on: May 12, 2019

6.8K
Oxygenation-sensitive Cardiac MRI with Vasoactive Breathing Maneuvers for the Non-invasive Assessment of Coronary Microvascular Dysfunction
08:35

Oxygenation-sensitive Cardiac MRI with Vasoactive Breathing Maneuvers for the Non-invasive Assessment of Coronary Microvascular Dysfunction

Published on: August 17, 2022

2.4K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Nuclear Cardiology

Background:

  • Deep learning (DL) shows promise for denoising low-dose myocardial perfusion SPECT images.
  • Current DL methods focus on image fidelity, but may not improve clinical task performance.
  • Evaluating DL denoising on clinical tasks is essential for real-world application.

Purpose of the Study:

  • To develop and evaluate a DL-based denoising method for myocardial perfusion SPECT.
  • To preserve observer-related information crucial for clinical detection tasks.
  • To improve the performance of detecting perfusion defects in low-dose SPECT images.

Main Methods:

  • Proposed a DL denoising approach incorporating model observer concepts and human visual system understanding.
  • Focused on preserving observer-related information for detection tasks.
  • Objectively evaluated the method on a retrospective clinical dataset for perfusion defect detection.

Main Results:

  • The proposed DL denoising method significantly improved performance on the myocardial perfusion defect detection task.
  • Performance with the proposed method surpassed that of using standard low-dose images.
  • Task-specific information preservation in DL denoising enhanced observer performance.

Conclusions:

  • DL-based denoising can be optimized to preserve task-specific information for improved clinical utility.
  • This approach offers a mechanism to enhance observer performance in low-dose myocardial perfusion SPECT.
  • Preserving observer-related information is key for effective DL application in medical imaging tasks.