Abstract: A conversion device (20) is operable to perform a learning-based method of generating a synthetic electron density image (sCT) of an anatomical portion based on one or more magnetic resonance, MR, images. The method is processing-efficient and capable of producing highly accurate sCT images irrespective of misalignment in the underlying training set. The conversion device (20) receives and installs a machine-learning model (22) trained to predict coefficients of an image transfer function (24). The conversion device (20) then receives a current set of MR images (MRI) of the anatomical portion, computes current coefficients ([C]) of the image transfer function (24) by operating the machine-learning model (22) on the current set of MR images (MRI), and computes a current sCT image of the anatomical portion by operating the current coefficients ([C]), in accordance with the image transfer function (24), on the current set of MR images (MRI).

Abstract: A conversion device (20) is operable to perform a learning-based method of generating a synthetic electron density image (sCT) of an anatomical portion based on one or more magnetic resonance, MR, images. The method is processing-efficient and capable of producing highly accurate sCT images irrespective of misalignment in the underlying training set. The conversion device (20) receives and installs a machine-learning model (22) trained to predict coefficients of an image transfer function (24). The conversion device (20) then receives a current set of MR images (MRI) of the anatomical portion, computes current coefficients ([C]) of the image transfer function (24) by operating the machine-learning model (22) on the current set of MR images (MRI), and computes a current sCT image of the anatomical portion by operating the current coefficients ([C]), in accordance with the image transfer function (24), on the current set of MR images (MRI).

Abstract: A method for generating synthetic electron density information based on an acquired magnetic resonance, MR, image stack is disclosed.

Abstract: A method for generating synthetic electron density information based on an acquired magnetic resonance, MR, image stack is disclosed.

Abstract: The invention relates to a method and a device for separating particles using ultrasonic standing waves which are switched between two different frequencies. A second order harmonic standing wave is used together with the fundamental standing wave. If the particles are exposed to the fundamental standing wave, the forces act to collect particles at the center. If the particles are exposed to the second order harmonic standing wave, the forces act to collect particles at the two pressure nodes at the sides. By switching the frequency between the second order harmonic standing wave and the fundamental standing wave, particles with different properties will be exposed to different accelerations and are separated into two streams.

Abstract: The invention relates to a method and a device for separating particles using ultrasonic standing waves which are switched between two different frequencies. A second order harmonic standing wave is used together with the fundamental standing wave. If the particles are exposed to the fundamental standing wave, the forces act to collect particles at the centre. If the particles are exposed to the second order harmonic standing wave, the forces act to collect particles at the two pressure nodes at the sides. By switching the frequency between the second order harmonic standing wave and the fundamental standing wave, particles with different properties will be exposed to different accelerations and are separated into two streams.