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

Magnetic Resonance Imaging

Magnetic Resonance Imaging

Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...

Search research articles

Home
Generative Adversarial Network-based Synthesis Of Contrast-enhanced Mr Images From Precontrast Images For Predicting Histological Characteristics In Breast Cancer.

Home
Generative Adversarial Network-based Synthesis Of Contrast-enhanced Mr Images From Precontrast Images For Predicting Histological Characteristics In Breast Cancer.

Related Experiment Video

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Generative adversarial network-based synthesis of contrast-enhanced MR images from precontrast images for predicting

Ming Fan¹, Xuan Cao¹, Fuqing Lü¹

¹Institute of Intelligent Biomedicine, Hangzhou Dianzi University,Hangzhou 310018, Zhejiang, People's Republic of China.

Physics in Medicine and Biology

|March 27, 2024

View abstract on PubMed

Summary

This summary is machine-generated.

Keywords:

DCE-MRI breast cancer contrast-enhanced image generation generative adversarial network histological information

More Related Videos

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Published on: December 15, 2014

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

Related Experiment Videos

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Published on: December 15, 2014

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

This study developed a generative adversarial network (GAN) to create contrast-enhanced breast MRI images from precontrast scans. This contrast-free approach improves diagnostic accuracy for breast cancer subtypes and grading.

Area of Science:

Medical Imaging
Artificial Intelligence in Medicine
Oncology

Background:

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is crucial for breast cancer assessment but uses gadolinium contrast agents with potential risks.
Contrast-free MRI is preferred for patients with renal impairment or during pregnancy, necessitating alternative methods for image enhancement.
Accurate prediction of tumor characteristics like Ki-67, histological grade, and luminal A subtype is vital for effective breast cancer management.

Purpose of the Study:

To investigate the feasibility of synthesizing contrast-enhanced (CE) MR images from precontrast images using a generative adversarial network (GAN).
To evaluate the diagnostic performance of these synthetic CE images for breast cancer assessment.
To enable contrast-free breast MRI for improved patient safety and accessibility.

Main Methods:

A retrospective study of 322 invasive breast cancer patients who underwent preoperative DCE-MRI.
Development and application of a GAN-based postcontrast image synthesis (GANPIS) model with perceptual loss.
Evaluation of image quality using Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM).
Assessment of diagnostic performance using a convolutional neural network to predict Ki-67, luminal A, and histological grade via Area Under the Curve (AUC).

Main Results:

The GANPIS model achieved high agreement between synthesized and real postcontrast images (PSNR: 36.210 ± 2.670, SSIM: 0.988 ± 0.006).
Synthetic CE images demonstrated strong diagnostic performance for predicting Ki-67 (AUC: 0.918 ± 0.018), histological grade (AUC: 0.842 ± 0.028), and luminal A subtype (AUC: 0.815 ± 0.019).
Performance with synthetic images significantly outperformed precontrast images alone for all evaluated diagnostic tasks.

Conclusions:

A GAN-based method can effectively synthesize contrast-enhanced MR images from precontrast data for breast cancer.
This contrast-free approach shows significant potential for improving the diagnosis of breast cancer subtypes and grading.
The developed technique offers a safer alternative to traditional DCE-MRI, particularly for at-risk patient populations.