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

Imaging Studies VII: Vascular Imaging

Imaging Studies VII: Vascular Imaging

DefinitionRenal angiography, also known as renal arteriography, is an imaging technique used to obtain a comprehensive view of blood flow and the vascular structure of blood vessels in the kidneys and surrounding areas.PurposeRenal angiography detects blood vessel abnormalities in the kidneys, such as aneurysms, stenosis, thrombosis, vascular tumors, and renal artery stenosis. It evaluates kidney function and guides interventional treatments like angioplasty or stent placement.Pre-Procedure...

You might also read

Related Articles

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

Sort by

Same author

2025 Update of the Taiwan Expert Consensus on Hormone Receptor-Positive Metastatic Breast Cancer Management.

Journal of breast cancer·2026

Same author

A bongkrekic acid incident in Taiwan, and a proposed nomogram for determining clinical severity.

Clinical toxicology (Philadelphia, Pa.)·2026

Same author

Population Pharmacokinetics and Cerebrospinal Fluid Penetration of Intravenous Vancomycin in Intracranial Hemorrhage Patients with External Ventricular Drains: Implications for Dosing and Therapeutic Drug Monitoring.

Drug design, development and therapy·2026

Same author

Enhancing Hydroxyl Metabolite Analysis through In Situ Derivatization-Enabled Desorption Electrospray Ionization-Mass Spectrometry.

Analytical chemistry·2025

Same author

Development and validation of a five-channel multiplex LC-ESI-MS/MS method for the quantification of carboxylic acids in urine.

Analytica chimica acta·2025

Same author

The utility of a dermoscopic 'bud-like appearance' combined with disease duration in differentiating keratoacanthoma from well-differentiated cSCC: A preliminary study.

Medicine·2025

Search research articles

Related Experiment Video

Updated: May 8, 2026

Heterogeneity Mapping of Protein Expression in Tumors using Quantitative Immunofluorescence

Heterogeneity Mapping of Protein Expression in Tumors using Quantitative Immunofluorescence

Published on: October 25, 2011

Characterizing Breast Tumor Heterogeneity Through IVIM-DWI Parameters and Signal Decay Analysis.

Si-Wa Chan^1,2,3, Chun-An Lin⁴, Yen-Chieh Ouyang⁴

¹Department of Medical Imaging, Taichung Veterans General Hospital, Taichung 407219, Taiwan.

Diagnostics (Basel, Switzerland)

|June 26, 2025

Summary

This summary is machine-generated.

This study introduces a novel method combining intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI) and deep learning for safer breast tumor characterization. The deep neural network (DNN) approach outperformed traditional methods in accurately segmenting tumors without contrast agents.

Keywords:

apparent diffusion coefficient (ADC)breast cancer deep neural networks (DNNs)diffusion-weighted imaging (DWI)dynamic contrast-enhanced MRI (DCE-MRI)intravoxel incoherent motion (IVIM)

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

Author Spotlight: Integrating High-Resolution Intravital Imaging and MRI to Enhance Stereotactic Body Radiation Therapy Planning

Author Spotlight: Integrating High-Resolution Intravital Imaging and MRI to Enhance Stereotactic Body Radiation Therapy Planning

Published on: April 12, 2024

Related Experiment Videos

Last Updated: May 8, 2026

Heterogeneity Mapping of Protein Expression in Tumors using Quantitative Immunofluorescence

Heterogeneity Mapping of Protein Expression in Tumors using Quantitative Immunofluorescence

Published on: October 25, 2011

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

Author Spotlight: Integrating High-Resolution Intravital Imaging and MRI to Enhance Stereotactic Body Radiation Therapy Planning

Author Spotlight: Integrating High-Resolution Intravital Imaging and MRI to Enhance Stereotactic Body Radiation Therapy Planning

Published on: April 12, 2024

Area of Science:

Medical Imaging
Oncology
Machine Learning

Background:

Dynamic contrast-enhanced MRI (DCE-MRI) is standard for breast tumor diagnosis but uses contrast agents with potential risks.
Intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI) offers a non-invasive alternative by analyzing diffusion (D) and microcirculation (D*).
This study explores IVIM-DWI data treated as hyperspectral images for advanced breast tumor characterization.

Purpose of the Study:

To evaluate deep learning and hyperspectral imaging techniques for breast tumor characterization using IVIM-DWI.
To compare the performance of deep neural networks (DNNs) against kernel-based methods (KCEM, I-KCEM) for tumor segmentation.
To assess the capability of the methods in detailed tumor characterization beyond binary diagnosis.

Main Methods:

Acquisition of multi-b-value IVIM-DWI data from 22 breast cancer patients using a 3T MRI system.
Pre-processing of images and treatment of IVIM-DWI data as hyperspectral image stacks.
Evaluation of tumor detection using DNNs, KCEM, and I-KCEM, with segmentation accuracy measured by Dice and Jaccard indices against physician-confirmed DCE-MRI.

Main Results:

Deep neural networks (DNNs) demonstrated superior performance, achieving a Dice similarity coefficient of 86.56% and Jaccard index of 76.30%.
DNNs effectively identified tumor heterogeneity, differentiating between high- and low-cellularity regions based on diffusion parameters (ADC, D, D*, PF).
3D-ROC analysis confirmed DNN as the best detector, highlighting its accuracy and overall effectiveness.

Conclusions:

Combining IVIM-DWI, hyperspectral imaging, and deep learning provides a robust, non-invasive method for breast cancer diagnosis.
This approach offers a safer alternative to contrast-enhanced MRI, delivering detailed insights into tissue microstructure and heterogeneity.
The DNN model shows significant potential for improving breast tumor characterization and understanding tissue microenvironment.