Magnetic Resonance in Medicine · 2019 · 26 citations · 35 references
MedicineBiomedical EngineeringRadiologyDiagnostic ImagingDiagnostic RadiologyMedical PhysicsAbdominal UltrasonographyBiomedical Signal ModelingMagnetic Resonance ImagingMagnetic Resonance Pulse SequencesMedical ImagingMedical InstrumentationMagnetic Resonance Imaging AcquisitionParallel TransmissionPhysiological Signal CalibrationPulse Processing AlgorithmsPulse Sequence DesignPulse SequencesRadiofrequency Pulse DesignSubjects
Purpose A calibration‐free pulse design method is introduced to alleviate artifacts in clinical routine with parallel transmission at high field, dealing with significant inter‐subject variability, found for instance in the abdomen. Theory and Methods From a dual‐transmit 3T scanner, a database of and off‐resonance abdominal maps from 50 subjects was first divided into 3 clusters based on mutual affinity between their respective tailored k T ‐points pulses. For each cluster, a k T ‐points pulse was computed, minimizing normalized root‐mean‐square flip angle deviations simultaneously for all subjects comprised in it. Using 30 additional subjects' field distributions, a machine learning classifier was trained on this 80‐labeled‐subject database to recognize the best pulse from the 3 ones available, relying only on patient features accessible from the preliminary localizer sequence present in all protocols. This so‐called SmartPulse process was experimentally tested on an additional 53‐subject set and compared with other pulse types: vendor's hard calibration‐free dual excitation, tailored static radiofrequency shimming, universal and tailored k T ‐points pulses. Results S martPulse outperformed both calibration‐free approaches. Tailored static radiofrequency shimming yielded similar flip angle homogeneity for most patients but broke down for some while SmartPulse remained robust. Although flip angle homogeneity was systematically better with tailored k T ‐points, the difference was barely noticeable on in vivo images. Conclusion The proposed method paves the way toward an efficient trade‐off between tailored and universal pulse design approaches for large inter‐subject variability. With no need for on‐line field mapping or pulse design, it can fit seamlessly into a clinical protocol.
35
Scikit-learn: Machine Learning in Python
Fabián Pedregosa, Gaël Varoquaux, Alexandre Gramfort et al. · arXiv (Cornell University) · 2012 · 63.7K citations · Full text
Corinna Cortes, Vladimir Vapnik · Machine Learning · 1995 · 40.5K citations · Full text
Pierre Geurts, Damien Ernst, Louis Wehenkel · Machine Learning · 2006 · 8.7K citations · Full text
A few useful things to know about machine learning
Pedro Domingos · Communications of the ACM · 2012 · 3.2K citations