Simulated perfusion MRI data to boost training of convolutional neural networks for lesion fate prediction in acute stroke. (January 2020)

• Record Type: Journal Article
• Authors: Debs, Noëlie; Rasti, Pejman; Victor, Léon; Cho, Tae-Hee; Frindel, Carole; Rousseau, David
• Is Part Of: Computers in biology and medicine. Volume 116(2020)
• Publication Date: 2020-01
• Subjects: Stroke -- Lesion prediction -- Perfusion magnetic resonance imaging -- Arterial input function -- Simulation -- Convolutional neural network; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2019.103579
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: The problem of final tissue outcome prediction of acute ischemic stroke is assessed from physically realistic simulated perfusion magnetic resonance images. Different types of simulations with a focus on the arterial input function are discussed. These simulated perfusion magnetic resonance images are fed to convolutional neural network to predict real patients. Performances close to the state-of-the-art performances are obtained with a patient specific approach. This approach consists in training a model only from simulated images tuned to the arterial input function of a tested real patient. This demonstrates the added value of physically realistic simulated images to predict the final infarct from perfusion. Highlights: Simulated perfusion MRI is used to train prediction of stroke lesion. Neural networks trained on simulated perfusion are used for stroke lesion prediction. Importance of realism of simulated arterial input function is discussed.