Machine learning improves classification of preclinical models of pancreatic cancer with chemical exchange saturation transfer MRI.
Journal:
Magnetic resonance in medicine
PMID:
30277270
Abstract
PURPOSE: We sought to assess whether machine learning-based classification approaches can improve the classification of pancreatic tumor models relative to more simplistic analysis methods, using T relaxation, CEST, and DCE MRI.
Authors
Keywords
Algorithms
Animals
Area Under Curve
Cell Line, Tumor
Female
Humans
Hypoxia
Image Enhancement
Image Interpretation, Computer-Assisted
Image Processing, Computer-Assisted
Machine Learning
Magnetic Resonance Imaging
Mice
Mice, SCID
Normal Distribution
Pancreatic Neoplasms
Principal Component Analysis
Reproducibility of Results
Sensitivity and Specificity