Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Deconvolution

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...

You might also read

Related Articles

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

Sort by

Same author

GPDM: generation-prior diffusion model for accelerated direct attenuation and scatter correction of whole-body18F-FDG PET.

Physics in medicine and biology·2026

Same author

First-in-Human Imaging Results of PHAROS: A Versatile High-Resolution TOF/DOI PET Scanner for Brain, Breast, and Extremity Imaging.

Journal of nuclear medicine : official publication, Society of Nuclear Medicine·2026

Same author

Influence of scintillation light confinement on depth-of-interaction measurement performance in a single-ended readout PET detector.

Physics in medicine and biology·2026

Same author

Photoacoustic computed tomography monitors cerebrospinal fluid dynamics and glymphatic function.

Nature communications·2026

Same author

Investigating the timing behavior of compton scattering in BGO for time-of-flight PET.

Physics in medicine and biology·2026

Same author

Voxel-based dosimetry for predicting treatment response to transarterial radioembolization in hepatocellular carcinoma: significance of intratumoral dose distribution.

EJNMMI physics·2025

Same journal

Current Status of PSMA-Targeted Agents Based on Small Molecules for Prostate Cancer in Preclinical Studies.

Nuclear medicine and molecular imaging·2026

Same journal

Fibroblast Activation Protein-Targeted SPECT Imaging Using <sup>99m</sup>Tc: A Comprehensive Review.

Nuclear medicine and molecular imaging·2026

Same journal

The 2026 Special Issue on Radiopharmaceuticals: from Molecular Design to Clinical Translation.

Nuclear medicine and molecular imaging·2026

Same journal

Feasibility of [<sup>99m</sup>Tc]Tc-Mannosylated Human Serum Albumin for Lymphoscintigraphy: A Phase 1/2 Clinical Trial.

Nuclear medicine and molecular imaging·2026

Same journal

Automated Synthesis of Radiopharmaceuticals: Technology, Applications, and Regulatory Perspectives.

Nuclear medicine and molecular imaging·2026

Same journal

Development of Antibody and Antibody Fragment-Based Radiopharmaceuticals for Cancer Imaging and Therapy.

Nuclear medicine and molecular imaging·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Nov 27, 2025

Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging

Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging

Published on: July 11, 2025

Self-supervised PET Denoising.

Si Young Yie^1,2, Seung Kwan Kang^1,3, Donghwi Hwang^1,3

¹Department of Nuclear Medicine, Seoul National University College of Medicine, 103 Daehak-ro, Jongno-gu, Seoul, 03080 South Korea.

Nuclear Medicine and Molecular Imaging

|December 7, 2020

Summary

This summary is machine-generated.

Self-supervised deep learning methods, noise2noise (N2N) and noiser2noise (Nr2N), show promise for positron emission tomography (PET) image denoising. These methods offer comparable or superior results to noise2clean (N2C), potentially reducing scan time or radiation dose.

Keywords:

Artificial neural network Deep learning Denoising filter Positron emission tomography (PET)

More Related Videos

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

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

Published on: April 21, 2023

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

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

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Nov 27, 2025

Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging

Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging

Published on: July 11, 2025

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

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

Published on: April 21, 2023

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

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

Published on: December 15, 2023

Area of Science:

Medical Imaging
Artificial Intelligence
Radiology

Background:

Deep learning-based image denoising is crucial for medical imaging.
Conventional methods often require clean training data (noise2clean).
Self-supervised learning offers an alternative approach.

Purpose of the Study:

To evaluate self-supervised denoising methods (noise2noise, noiser2noise) for PET imaging.
To compare their performance against a supervised method (noise2clean).
To assess feasibility using real PET data.

Main Methods:

Retrospective analysis of 14 patients' 18F-FDG brain PET/CT scans.
Generation of noisy PET data from list-mode data at various durations (10s, 40s, 300s).
U-Net architecture used for training and testing denoising models.

Main Results:

All tested methods (N2C, N2N, Nr2N) effectively denoised PET images.
N2N achieved peak signal-to-noise ratio (PSNR) comparable to N2C.
Nr2N demonstrated higher structural similarity index measure (SSIM) than N2N.
N2N produced denoised images with better contrast and similarity to filtered reference images.

Conclusions:

Self-supervised denoising methods are effective for PET imaging.
These techniques can potentially reduce PET scan duration or radiation exposure.
N2N and Nr2N present viable alternatives to supervised denoising in PET.