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

Masking and Demasking Agents

Masking and Demasking Agents

EDTA titrations may necessitate masking and demasking agents to temporarily protect a particular metal ion in a mixture from the EDTA reaction. These agents facilitate the sequential analysis of the metal ions by forming stable complexes with some—but not all—metal ions during certain steps.
There are many masking agents, such as cyanide, fluoride, triethanolamine, thiourea, and 2,3-bis(sulfanyl)propan-1-ol (formerly 2,3-dimercapto-1-propanol), with the masking agent chosen based on...

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...

Electron Microscope Tomography and Single-particle Reconstruction

Electron Microscope Tomography and Single-particle Reconstruction

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...

You might also read

Related Articles

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

Sort by

Same author

Metabolic engineering of Saccharomyces cerevisiae for redox-assisted co-fermentation of l-rhamnose.

Bioresource technology·2026

Same author

A chronic whole cigarette smoke extract model reveals redox-mitochondrial adaptation in human lung epithelial and organoid models.

Experimental & molecular medicine·2026

Same author

Rapid CAR screening and circRNA-driven CAR-NK cells for persistent shed-resistant immunotherapy.

Signal transduction and targeted therapy·2026

Same author

Modulation of Macrophage Inflammatory Responses by UDP-Glucuronosyltransferase-Mediated PGE<sub>2</sub> Glucuronidation.

Journal of personalized medicine·2026

Same author

Dose calculation accuracy with extended CT scales near metal: phantom-patient evaluation using a beam-metal overlap metric.

Radiation oncology (London, England)·2026

Same author

Genetic Burden and <i>APOE</i> Methylation in a Korean Multi-Generational Alzheimer's Disease Family: An Exploratory Multi-Omics Case Study.

Journal of personalized medicine·2026

Search research articles

Related Experiment Video

Updated: Jul 30, 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

A denoising model based on multi-agent reinforcement learning with data transformation for digital tomosynthesis.

Kibok Nam¹, Dahye Lee¹, Seungwan Lee^1,2

¹Department of Medical Science, Konyang University, Daejoen, Republic of Korea.

Physics in Medicine and Biology

|May 16, 2023

Summary

A novel multi-agent reinforcement learning (RL) model significantly enhances denoising in digital tomosynthesis (DT) imaging. This approach improves signal-to-noise ratio (SNR) with less training data, overcoming limitations of traditional supervised learning methods for clearer medical images.

Keywords:

data transformation denoising digital tomosynthesis multi-agent reinforcement learning

More Related Videos

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Related Experiment Videos

Last Updated: Jul 30, 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

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Area of Science:

Medical Imaging
Artificial Intelligence
Machine Learning

Background:

Supervised learning denoising models for medical imaging require extensive training data and struggle with loss minimization.
Clinical availability of denoising models in digital tomosynthesis (DT) is limited by these data and performance constraints.
Reinforcement learning (RL) offers a promising alternative, capable of learning optimal policies with smaller datasets.

Purpose of the Study:

To present a novel denoising model for DT imaging utilizing multi-agent RL.
To enhance the performance of machine learning-based denoising models in DT.
To address the limitations of supervised learning in DT image quality improvement.

Main Methods:

A multi-agent RL network was developed, featuring shared, value, and policy sub-networks.
The value sub-network incorporated a reward map convolution (RMC) technique, while the policy sub-network used a convolutional gated recurrent unit (convGRU).
Wavelet and Anscombe transformations were applied to DT images, with training conducted on phantoms derived from clinical CT images.

Main Results:

The proposed multi-agent RL denoising model improved signal-to-noise ratios (SNRs) by 20.64% compared to supervised learning, while maintaining similar structural similarity (SSIM) and peak signal-to-noise ratio (PSNR).
Utilizing wavelet and Anscombe transformations further boosted output image SNRs by 25.88% and 42.95%, respectively, over supervised learning.
The model demonstrated effective feature extraction, reward calculation, and action execution at the pixel level.

Conclusions:

Multi-agent RL is a viable approach for generating high-quality denoised DT images.
The proposed method significantly improves the performance of machine learning-based denoising in DT imaging.
This technique offers a pathway to overcome data requirements and enhance clinical applicability of denoising in medical imaging.