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

Reconstruction of Signal using Interpolation01:10

Reconstruction of Signal using Interpolation

557
Signal processing techniques are essential for accurately converting continuous signals to digital formats and vice versa. When a continuous signal is sampled with a period T, the resulting sampled signal exhibits replicas of the original spectrum in the frequency domain, spaced at intervals equal to the sampling frequency. To handle this sampled signal, a zero-order hold method can be applied, which creates a piecewise constant signal by retaining each sample's value until the next...
557
Electron Microscope Tomography and Single-particle Reconstruction01:07

Electron Microscope Tomography and Single-particle Reconstruction

2.7K
Transmission electron microscopy (TEM) can be used to determine the 3D structure of biological samples with the help of techniques such as electron microscope tomography and single-particle reconstruction. While single-particle reconstruction can examine macromolecules and macromolecular complexes in vitro conditions only, tomography permits the study of cell components or small cells in vivo.
Electron Tomography
Electron tomography can be performed either in TEM or STEM (scanning transmission...
2.7K

You might also read

Related Articles

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

Sort by
Same author

The cutting edge: Promising oncology radiotracers in clinical development.

Diagnostic and interventional imaging·2024
Same author

Investigating the Mechanism of Aluminum Fluoride Chelation.

Inorganic chemistry·2024
Same author

A third generation PSMA-targeted agent [<sup>211</sup>At]YF2: Synthesis and in vivo evaluation.

Nuclear medicine and biology·2024
Same author

An Automated Deep Learning-Based Framework for Uptake Segmentation and Classification on PSMA PET/CT Imaging of Patients with Prostate Cancer.

Journal of imaging informatics in medicine·2024
Same author

Beyond synthetic aperture focusing: deconvolution-based elevation resolution enhancement using simulated point spread function for linear array-based three-dimensional photoacoustic imaging.

Biomedical optics express·2024
Same author

Prognostic Performance of RECIP 1.0 Based on [<sup>18</sup>F]PSMA-1007 PET in Prostate Cancer Patients Treated with [<sup>177</sup>Lu]Lu-PSMA I&T.

Journal of nuclear medicine : official publication, Society of Nuclear Medicine·2024

Related Experiment Video

Updated: Nov 22, 2025

Photorealistic Learned Landscapes for Augmented Reality
06:54

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

474

A Learned Reconstruction Network for SPECT Imaging.

Wenyi Shao1, Martin G Pomper1, Yong Du1

  • 1Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, Baltimore, MD 21287 USA.

IEEE Transactions on Radiation and Plasma Medical Sciences
|January 6, 2021
PubMed
Summary
This summary is machine-generated.

A novel neural network was developed for single-photon emission computed tomography (SPECT) image reconstruction. This AI approach achieves higher resolution and quantitative accuracy than traditional methods, even with noisy or reduced data.

Keywords:
2-D convolutionDeep learningSPECT imagingimage reconstructionneural network

More Related Videos

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
12:27

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Published on: February 15, 2017

7.2K
Anatomically Inspired Three-dimensional Micro-tissue Engineered Neural Networks for Nervous System Reconstruction, Modulation, and Modeling
10:45

Anatomically Inspired Three-dimensional Micro-tissue Engineered Neural Networks for Nervous System Reconstruction, Modulation, and Modeling

Published on: May 31, 2017

13.4K

Related Experiment Videos

Last Updated: Nov 22, 2025

Photorealistic Learned Landscapes for Augmented Reality
06:54

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

474
Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
12:27

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Published on: February 15, 2017

7.2K
Anatomically Inspired Three-dimensional Micro-tissue Engineered Neural Networks for Nervous System Reconstruction, Modulation, and Modeling
10:45

Anatomically Inspired Three-dimensional Micro-tissue Engineered Neural Networks for Nervous System Reconstruction, Modulation, and Modeling

Published on: May 31, 2017

13.4K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Nuclear Medicine

Background:

  • Single-photon emission computed tomography (SPECT) is crucial for functional imaging.
  • Traditional reconstruction algorithms like OS-EM can be limited in resolution and quantitative accuracy.
  • Developing advanced reconstruction methods is essential for improving diagnostic capabilities.

Purpose of the Study:

  • To develop and validate a specialized neural network for direct SPECT image reconstruction.
  • To enhance image resolution, quantitative accuracy, and robustness against noise and data reduction.

Main Methods:

  • A custom neural network architecture was designed, incorporating fully connected and convolutional layers.
  • The network was trained using simulated digital phantom and projection data.
  • Reconstruction performance was evaluated using independent simulated and clinical patient SPECT data.

Main Results:

  • The developed neural network achieved superior image reconstruction compared to OS-EM, demonstrating higher resolution and quantitative accuracy.
  • The network showed robustness when retrained with noisy projection data, effectively filtering noise.
  • Sharp images were maintained even with reduced view projection data after retraining.

Conclusions:

  • The specialized neural network offers a promising advancement for SPECT image reconstruction.
  • This AI-driven method improves image quality and reliability, potentially enhancing clinical diagnostic accuracy.
  • The network's adaptability to noise and data limitations highlights its potential for real-world applications.