Exploring linearity of deep neural network trained QSM: QSMnet<sup>.</sup>
Woojin Jung, Jaeyeon Yoon, Sooyeon Ji, Joon Yul Choi, Jae Myung Kim, Yoonho Nam, Eung Yeop Kim, Jongho Lee
Abstract
. This study demonstrates the importance of the trained data range in deep neural network-powered parametric mapping and suggests the data augmentation approach for generalization of network. The new network can be applicable for a wide range of susceptibility quantification.
Topics & Concepts
Quantitative susceptibility mappingLinearityArtificial neural networkLinear regressionParametric statisticsRange (aeronautics)Artificial intelligenceRegressionDeep neural networksComputer scienceMathematicsBiomedical engineeringStatisticsMedicineMaterials scienceRadiologyEngineeringMagnetic resonance imagingElectronic engineeringComposite materialAdvanced MRI Techniques and ApplicationsAtomic and Subatomic Physics ResearchCharacterization and Applications of Magnetic Nanoparticles