Artificial Neural Networks approach to pharmacokinetic model selection in DCE-MRI studies

Highlights • Artificial Neural Networks are proposed for solving the model selection problem in pharmacokinetic studies. • Neural networks show to be faster and superior in performance in comparison with the F-test. • The proposed method removes the need for curve fitting and hypothesis testing in m...

Full description

Saved in:
Bibliographic Details
Published in:Physica medica 2016-12, Vol.32 (12), p.1543-1550
Main Authors: Mohammadian-Behbahani, Mohammad-Reza, Kamali-Asl, Ali-Reza
Format: Article
Language:English
Subjects:
Algorithms
Artificial Neural Networks
Brain Neoplasms - diagnostic imaging
Contrast Media - pharmacokinetics
Dynamic Contrast Enhanced magnetic resonance imaging
Extended Tofts model
Female
Fisher’s test
Glioblastoma - diagnostic imaging
Humans
Image Processing, Computer-Assisted
Magnetic Resonance Imaging
Male
Middle Aged
Model selection
Neural Networks (Computer)
Radiology
Reproducibility of Results
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Highlights • Artificial Neural Networks are proposed for solving the model selection problem in pharmacokinetic studies. • Neural networks show to be faster and superior in performance in comparison with the F-test. • The proposed method removes the need for curve fitting and hypothesis testing in model selection procedure.
ISSN:1120-1797
1724-191X
DOI:10.1016/j.ejmp.2016.11.011