Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Cardiovascular risk factors and carotid plaque components in a multi-ethnic cohort using 3 Tesla MRI: the HELIUS study.

European radiology·2026
Same author

Black-blood dynamic contrast-enhanced MRI of abdominal aortic aneurysms.

Magma (New York, N.Y.)·2026
Same author

Combination of quantitative MRI and laboratory markers for the detection and staging of metabolic dysfunction-associated steatotic liver disease.

European radiology·2026
Same author

Simultaneous Volumetric T1 and T2 Mapping With Blood- and Fat-Suppression in Abdominal Aortic Aneurysms.

Magnetic resonance in medicine·2026
Same author

Real-time magnetic resonance-guided radiofrequency ablation and lesion evaluation in an magnetic resonance-compatible isolated beating pig heart platform.

Heart rhythm O2·2026
Same author

Validation of Quantitative Magnetic Resonance Cholangiopancreatography Metrics in Prediction of Transplant-free Survival in Primary Sclerosing Cholangitis.

Journal of clinical and experimental hepatology·2026

Related Experiment Video

Updated: Sep 7, 2025

Dynamic Contrast Enhanced Magnetic Resonance Imaging of an Orthotopic Pancreatic Cancer Mouse Model
06:24

Dynamic Contrast Enhanced Magnetic Resonance Imaging of an Orthotopic Pancreatic Cancer Mouse Model

Published on: April 18, 2015

15.2K

Deep learning DCE-MRI parameter estimation: Application in pancreatic cancer.

Tim Ottens1, Sebastiano Barbieri2, Matthew R Orton3

  • 1Department of Radiology and Nuclear Medicine, Cancer Center Amsterdam, Amsterdam UMC, University of Amsterdam, HV Amsterdam 1081, the Netherlands.

Medical Image Analysis
|June 16, 2022
PubMed
Summary

Physics-informed deep neural networks, specifically the GRU framework, offer faster and more accurate analysis of dynamic contrast-enhanced MRI (DCE-MRI) data compared to traditional methods. These AI models improve precision and repeatability for tumor classification and treatment monitoring.

Keywords:
Convolutional neural networkDynamic contrast enhanced MRIMagnetic resonance imagingPancreatic cancerRecurrent neural networkUnsupervised training

More Related Videos

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
15:48

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

Published on: December 15, 2014

22.6K
High Resolution 3D Imaging of the Human Pancreas Neuro-insular Network
09:54

High Resolution 3D Imaging of the Human Pancreas Neuro-insular Network

Published on: January 29, 2018

11.1K

Related Experiment Videos

Last Updated: Sep 7, 2025

Dynamic Contrast Enhanced Magnetic Resonance Imaging of an Orthotopic Pancreatic Cancer Mouse Model
06:24

Dynamic Contrast Enhanced Magnetic Resonance Imaging of an Orthotopic Pancreatic Cancer Mouse Model

Published on: April 18, 2015

15.2K
Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
15:48

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

Published on: December 15, 2014

22.6K
High Resolution 3D Imaging of the Human Pancreas Neuro-insular Network
09:54

High Resolution 3D Imaging of the Human Pancreas Neuro-insular Network

Published on: January 29, 2018

11.1K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Biophysics

Background:

  • Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) quantifies perfusion for disease classification.
  • Traditional non-linear least squares (NLLS) methods for DCE-MRI analysis are time-consuming and produce noisy parameter maps.
  • The non-convexity of NLLS cost functions limits accuracy and precision in parameter estimation.

Purpose of the Study:

  • To investigate physics-informed deep neural networks for enhanced physiological parameter estimation from DCE-MRI data.
  • To compare the performance of various temporal and spatio-temporal deep learning frameworks against conventional NLLS methods.
  • To evaluate the clinical utility of deep learning approaches for analyzing DCE-MRI in pancreatic cancer patients.

Main Methods:

  • Evaluated three voxel-wise temporal frameworks (FCN, LSTM, GRU) and two spatio-temporal frameworks (CNN, U-Net) using simulations.
  • Assessed accuracy and precision of parameter estimation, focusing on the ve parameter.
  • Conducted in vivo evaluation of the GRU framework in 28 pancreatic cancer patients, comparing it with spatio-temporal networks and NLLS.

Main Results:

  • All investigated neural networks demonstrated higher precision than NLLS.
  • The GRU framework reduced random error on ve by a factor of 4.8 under specific noise conditions.
  • In vivo studies showed all neural network approaches yielded less noisy parameter maps than NLLS, with GRU exhibiting superior test-retest repeatability.

Conclusions:

  • Physics-informed deep neural networks, particularly the GRU framework, provide a more accurate, precise, and repeatable method for DCE-MRI analysis compared to NLLS.
  • The GRU framework demonstrated clinical potential in identifying treatment response in pancreatic cancer patients.
  • While CNN and U-Net showed strong performance, potential systematic errors warrant caution; GRU is recommended for DCE data analysis.