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

Search research articles

Related Experiment Videos

A Novel Medical Image Denoising Method Based on Conditional Generative Adversarial Network.

Yuqin Li¹, Ke Zhang^1,2, Weili Shi^1,2

¹School of Computer Science and Technology, Changchun University of Science and Technology, Changchun 130022, China.

Computational and Mathematical Methods in Medicine

|October 8, 2021

Summary

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...

You might also read

Related Articles

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

Sort by

Same author

MCPD-YOLOv3: A Novel Lightweight Detection Model for Surgical Instruments in Laparoscopic Images.

The international journal of medical robotics + computer assisted surgery : MRCAS·2025

Same author

Automatic pterygopalatine fossa segmentation and localisation based on DenseASPP.

The international journal of medical robotics + computer assisted surgery : MRCAS·2024

Same author

Dual contrastive learning for synthesizing unpaired fundus fluorescein angiography from retinal fundus images.

Quantitative imaging in medicine and surgery·2024

Same author

Transformer-based 2D/3D medical image registration for X-ray to CT via anatomical features.

The international journal of medical robotics + computer assisted surgery : MRCAS·2024

Same author

A Novel Method for COVID-19 Detection Based on DCNNs and Hierarchical Structure.

Computational and mathematical methods in medicine·2022

Same author

DAFLNet: Dual Asymmetric Feature Learning Network for COVID-19 Disease Diagnosis in X-Rays.

Computational and mathematical methods in medicine·2022

This study introduces a new deep learning method for medical image denoising that effectively handles unknown, spatially varying noise. The advanced conditional generative adversarial network (CGAN) preserves image details and structures, improving diagnostic accuracy.

Area of Science:

Medical Imaging
Artificial Intelligence
Image Processing

Background:

Medical image quality is crucial for accurate diagnosis and treatment.
Deep learning methods show promise for automatic feature extraction in image denoising.
Existing denoising methods struggle with spatially varying noise and can cause detail loss.

Purpose of the Study:

To develop a novel medical image denoising method capable of handling various unknown noises.
To address limitations of existing methods regarding spatially varying noise and structural preservation.
To enhance image context perception and structural integrity in denoised medical images.

Main Methods:

A conditional generative adversarial network (CGAN) architecture is proposed for medical image denoising.

Related Experiment Videos

Noise images and gradient images are merged as conditional information to enhance signal-noise contrast.

A generator with residual dense blocks and a combined reconstruction and WGAN loss function are utilized.

Main Results:

The proposed method achieved high performance on JSRT and LIDC datasets with PSNR values of 33.2642 and 35.1086, respectively.
Structural Similarity Index (SSIM) scores of 0.9206 (JSRT) and 0.9328 (LIDC) were obtained.
The method demonstrated superior performance compared to state-of-the-art denoising techniques.

Conclusions:

The developed CGAN-based method effectively denoises medical images with various unknown noises.
The approach successfully preserves image details and structures, outperforming existing methods.
This technique offers a significant advancement in medical image denoising for improved clinical applications.