A Machine Learning Approach to Perfusion Imaging With Dynamic Susceptibility Contrast MR
Open Access
- 4 September 2018
- journal article
- research article
- Published by Frontiers Media SA in Frontiers in Neurology
- Vol. 9, 717
Abstract
Background: Dynamic susceptibility contrast (DSC) MR perfusion is a frequently-used technique for neurovascular imaging. The progress of a bolus of contrast agent through the tissue of the brain is imaged via a series of T2*-weighted MRI scans. Clinically relevant parameters such as blood flow and Tmax can be calculated by deconvolving the contrast-time curves with the bolus shape (arterial input function). In acute stroke, for instance, these parameters may help distinguish between the likely salvageable tissue and irreversibly damaged infarct core. Deconvolution typically relies on singular value decomposition (SVD): however, studies have shown that these algorithms are very sensitive to noise and artifacts present in the image and therefore may introduce distortions that influence the estimated output parameters. Methods: In this work, we present a machine learning approach to the estimation of perfusion parameters in DSC-MRI. Various machine learning models using as input the raw MR source data were trained to reproduce the output of an FDA approved commercial implementation of the SVD deconvolution algorithm. Experiments were conducted to determine the effect of training set size, optimal patch size, and the effect of using different machine-learning models for regression. Results: Model performance increased with training set size, but after 5,000 samples (voxels) this effect was minimal. Models inferring perfusion maps from a 5 by 5 voxel patch outperformed models able to use the information in a single voxel, but larger patches led to worse performance. Random Forest models produced had the lowest root mean squared error, with neural networks performing second best: however, a phantom study revealed that the random forest was highly susceptible to noise levels, while the neural network was more robust. Conclusion: The machine learning-based approach produces estimates of the perfusion parameters invariant to the noise and artifacts that commonly occur as part of MR acquisition. As a result, better robustness to noise is obtained, when evaluated against the FDA approved software on acute stroke patients and simulated phantom data.Keywords
Funding Information
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung (320030L 170060, 32003B 160107)
- Schweizerische Herzstiftung
This publication has 26 references indexed in Scilit:
- The Case for Using the Repeatability Coefficient When Calculating Test–Retest ReliabilityPLOS ONE, 2013
- Perfusion MRI: The Five Most Frequently Asked Technical QuestionsAmerican Journal of Roentgenology, 2013
- Regional Prediction of Tissue Fate in Acute Ischemic StrokeAnnals of Biomedical Engineering, 2012
- Use of Magnetic Resonance Imaging to Predict Outcome after Stroke: A Review of Experimental and Clinical EvidenceJournal of Cerebral Blood Flow & Metabolism, 2010
- Geography, Structure, and Evolution of Diffusion and Perfusion Lesions in Diffusion and Perfusion Imaging Evaluation For Understanding Stroke Evolution (DEFUSE)Stroke, 2009
- Bayesian estimation of cerebral perfusion using a physiological model of microvasculatureNeuroImage, 2006
- Diagnostic performance of spectroscopic and perfusion MRI for distinction of brain tumoursCancer Imaging, 2006
- Perfusion MRI Abnormalities in Speech or Motor Transient Ischemic Attack PatientsStroke, 2005
- Quantification of bolus‐tracking MRI: Improved characterization of the tissue residue function using Tikhonov regularizationMagnetic Resonance in Medicine, 2003
- Influential Observations, High Leverage Points, and Outliers in Linear RegressionStatistical Science, 1986