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

Deconvolution01:20

Deconvolution

Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
Downsampling01:20

Downsampling

When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
Upsampling01:22

Upsampling

Managing signal sampling rates is essential in digital signal processing to maintain signal integrity. A decimated signal, characterized by a reduced frequency range due to its lower sampling rate, can be upsampled by inserting zeros between each sample. This upsampling process expands the original spectrum and introduces repeated spectral replicas at intervals dictated by the new Nyquist frequency. To refine this zero-inserted sequence, it is passed through a lowpass filter with a cutoff...

You might also read

Related Articles

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

Sort by
Same author

AI-Powered MRI Radiomics and Deep Learning for Preoperative Prediction of Cavernous Sinus Invasion in Pituitary Adenomas: A Clinically Oriented Review of Current Evidence.

Neuroimage. Reports·2026
Same author

Supervised Volumetric Segmentation of White and Gray Matter from Brain Positron Emission Tomography Images Using Magnetic Resonance Labels.

Journal of medical signals and sensors·2026
Same author

Diagnostic utility of FAPI PET/CT in radioiodine-refractory thyroid cancer and TENIS syndrome: a systematic review.

Oncology reviews·2026
Same author

Swin UNETR-based prediction of [<sup>68</sup>Ga]Ga-FAPI-46 PET/CT dose rate maps in cancer patients: quantitative comparison with [<sup>18</sup>F]FDG PET/CT.

BMC medical imaging·2026
Same author

Revisiting multi-nodal radiomics with advanced feature learning for lymphoma classification: a multi-center study.

Physics in medicine and biology·2026
Same author

Clinically reliable and stable automated segmentation of DLBCL lesions on PET/CT using self-configuring nnU-Net for robust TMTV quantification.

Applied radiation and isotopes : including data, instrumentation and methods for use in agriculture, industry and medicine·2026
Same journal

Kolmogorov-Arnold Guided Local-Global Attention for Medical Image Classification.

Journal of imaging informatics in medicine·2026
Same journal

Artificial Intelligence-Assisted Inner Ear Computed Tomography Analysis: Radiomics-Based Comparison of Affected and Unaffected Ears in Idiopathic Sudden Sensorineural Hearing Loss.

Journal of imaging informatics in medicine·2026
Same journal

High Adoption, Higher Expectations: A Cross-Sectional Survey of Radiologist Engagement with Artificial Intelligence in the United Arab Emirates.

Journal of imaging informatics in medicine·2026
Same journal

Complex-valued Multi-scale Hybrid Attention Network for Fast MRI via Sparsified Data Learning.

Journal of imaging informatics in medicine·2026
Same journal

Automatic Phase and Sequence Identification in Gd-EOB-DTPA-Enhanced Liver MRI Using Deep Convolutional and Sequential Learning.

Journal of imaging informatics in medicine·2026
Same journal

Ultrasound-Based AI in Predicting Hormone Receptor Status in Breast Cancer: Is "Digital Biopsy" Possible.

Journal of imaging informatics in medicine·2026
See all related articles

Related Experiment Video

Updated: May 10, 2026

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.4K

SwinPix: A Swin Transformer-based Pix2Pix Framework for Low-Dose PET Denoising Using Multi-level Inputs Toward

Mohammad Saber Azimi1,2, Vahid Felfelian3, Habibollah Dadgar4

  • 1Doctoral School of Applied Informatics and Applied Mathematics, Óbuda University, Budapest, Hungary.

Journal of Imaging Informatics in Medicine
|March 10, 2026
PubMed
Summary
This summary is machine-generated.

SwinPix, a novel network, effectively uses multi-level low-dose PET images to improve standard-dose PET image prediction. The multi-input SwinPix model significantly enhances image quality and lesion quantification for accurate PET imaging.

Keywords:
Deep learningLow-dose PETMulti-input reconstructionPET denoisingStandard-dose PETSwin Transformer

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

852
Whole-cell Super-Resolution Imaging via DNA-PAINT on a Spinning Disk Confocal with Optical Photon Reassignment
07:12

Whole-cell Super-Resolution Imaging via DNA-PAINT on a Spinning Disk Confocal with Optical Photon Reassignment

Published on: January 6, 2026

547

Related Experiment Videos

Last Updated: May 10, 2026

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.4K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

852
Whole-cell Super-Resolution Imaging via DNA-PAINT on a Spinning Disk Confocal with Optical Photon Reassignment
07:12

Whole-cell Super-Resolution Imaging via DNA-PAINT on a Spinning Disk Confocal with Optical Photon Reassignment

Published on: January 6, 2026

547

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Healthcare
  • Radiological Physics

Background:

  • Low-dose (LD) Positron Emission Tomography (PET) imaging offers reduced radiation exposure but often suffers from poor image quality.
  • Reconstructing standard-dose (SD) PET images from LD inputs is crucial for improving diagnostic accuracy and patient safety.
  • Existing methods may not fully leverage the information contained within multi-level LD PET data.

Purpose of the Study:

  • To introduce and evaluate SwinPix, a novel network architecture for PET image prediction using multi-level LD PET inputs.
  • To compare the performance of single-input versus multi-input SwinPix models across various LD levels (4%, 6%, 10%).
  • To assess the efficacy of SwinPix against established models like Pix2Pix and Swin Transformer for PET reconstruction.

Main Methods:

  • Developed SwinPix, a hybrid transformer-based Generative Adversarial Network (GAN) architecture.
  • Trained and evaluated six models: single-input (4%, 6%, 10% LD) and multi-input (combining three LD levels) SwinPix.
  • Quantitatively assessed performance using SSIM, PSNR, SUVmean bias, SUVmax bias, and RMSE in head regions and malignant lesions.

Main Results:

  • The multi-input SwinPix model consistently outperformed single-input models across all LD levels.
  • At 4% LD, SwinPix demonstrated significant improvements: 13% PSNR increase, 82-86% RMSE reduction, and substantial decreases in SUV biases.
  • SwinPix achieved superior reconstruction quality compared to Pix2Pix and Swin Transformer, with statistically significant improvements (p < 0.01).

Conclusions:

  • Multi-level LD PET inputs significantly enhance SD PET image prediction accuracy and quality when utilized by the SwinPix architecture.
  • SwinPix offers a robust and computationally efficient solution for LD PET reconstruction, improving lesion quantification.
  • The findings support the clinical potential of SwinPix for accurate and safer PET imaging.