Abstract: The invention relates to a method of MR imaging of an object (10) placed in an examination volume of a MR device (1). It is an object of the invention to enable MR signal acquisition in a single scan providing the necessary information for electric properties imaging (EPT), namely a phase map as well as tissue boundaries. The method of the invention comprises the following steps: —subjecting the object (10) to a multi echo steady state imaging sequence or a fast spectroscopic imaging sequence comprising RF pulses and switched magnetic field gradients, wherein two or more echo signals are generated after each RF excitation; —acquiring the echo signals; —deriving a magnitude image and a phase map from the acquired echo signals, which phase map represents the spatial RF field distribution induced by the RF pulses in the object (10); and —reconstructing an electric conductivity map from the magnitude image and from the phase map, wherein tissue boundaries are derived from at least the magnitude image.

Abstract: The present disclosure relates to a method for determining electrical properties, EP, of a target volume (708) in an imaged subject (718). The method comprises: a) training (201) a deep neural network, DNN, using a training dataset, the training dataset comprising training B1 field maps and corresponding EP maps, the training comprising using a monte carlo, MC, dropout of the DNN during the training, resulting in a trained DNN configured for generating EP maps from B1 field maps; b) receiving (203) an input B1 field map of the target volume, and repeatedly generate by the trained DNN from the input B1 field map an EP map, resulting in a set of EP maps, wherein the generating comprises using in each repetition the MC dropout during inference of the DNN; c) combining (205) the set of EP maps for determining an EP map and associated uncertainty map of the input B1 field map.

Abstract: The present disclosure relates to a method for determining electrical properties, EP, of a target volume (708) in an imaged subject (718). The method comprises: performing a first training (201) of a deep neural network, DNN, using a first training dataset, the first training dataset comprising training B1 field maps and corresponding first EP maps, the first training resulting in a pre-trained DNN configured for generating EP maps from B1 field maps; performing a second training (203) of the pre-trained DNN using conditional generative adversarial networks, GAN, and a second training dataset, wherein the pre-trained DNN is a generator of the conditional GAN, the second training dataset comprising measured B1 maps and second EP maps, the second training resulting in a trained DNN; receiving (205) an input B1 field map of the target volume and generating an EP map of the input B1 field map using the trained DNN.

Abstract: The present disclosure relates to a computer implemented medical analysis method for predicting metastases (300) in a test tissue sample, the method comprising: providing a first machine learning model (154) having an input and an output, receiving a description (401) of a tumor (304) and first image data (148) of a test tissue sample of an anatomy region (306), the test tissue sample being free of metastases (300), providing the first image data (148) and the tumor description (401) to the input of the first machine learning model (154), in response to the providing, receiving from the output of the first machine learning model (154) a prediction of occurrence of metastases (300) originating from the tumor (304) in the test tissue sample, and providing the prediction.

Abstract: The invention relates to a magnetic resonance imaging system (100) for determining an approximation (150) of an electric conductivity distribution within a three-dimensional anatomical structure of interest. The determining comprises acquiring a first set of (3-n)-dimensional magnetic resonance data (144), reconstructing a (3-n)-dimensional phase distribution (146) using the (3-n)-dimensional magnetic resonance data (144), calculating a (3-n)-dimensional electric conductivity distribution (148) using spatial derivatives within the (3-n) dimensions and applying to the (3-n)-dimensional electric conductivity distribution (148) a scaling factor compensating for the relative reduction of dimensions by n.

Abstract: An iterative reconstruction is performed of multiple gradient echo MR imaging data to generate a reconstructed MR image (36). The iterative reconstruction uses a model (30) that links the MR imaging data and the reconstructed MR image. The model includes a parameterized magnetic field fluctuation component (32). During the performing of the iterative reconstruction, parameters of the parameterized magnetic field fluctuation component of the model are updated to optimize a cost function (40) dependent on partial derivatives of the reconstructed MR image with respect to the parameters of the parameterized magnetic field fluctuation component of the model. The image may be further processed to generate an R2* map (50), an SWI image (52), or a QSM map (54).

Abstract: The invention provides for a medical imaging system (100, 300) comprising: a memory (110) for storing machine executable instructions (120); and a processor (104) for controlling the medical imaging system. Execution of the machine executable instructions causes the processor to: receive (200) a resting group of B1 phase maps (122) of a region (309) of interest of a subject (318); receive (202) an active group of B1 phase maps (124) of the region of interest of the subject, calculate (204) a resting group of conductivity maps (126) for the region of interest using the resting group of B1 phase maps according to an electrical properties tomography algorithm; calculate (206) an active group of conductivity maps (128) for the region of interest using the active group of B1 phase maps according to the electrical properties tomography algorithm, and calculate (208) a conductivity change mapping (130) for the region of interest using the resting group of conductivity maps and the active group of conductivity maps.

Abstract: The invention provides for a medical system (100, 300, 400, 500) comprising: a memory (110) for storing machine executable instructions (150) and a processor (104) for controlling the medical system.

Abstract: It is an object of the invention to improve tissue classification in MRI images. In particular it is an object of the invention to improve the classification of bone and air in MRI images. This object is achieved by a method for tissue classification in a region of interest in a magnetic resonance (MR) image comprising a first region and a second region, wherein the first region represents air and the second region represents bone.

Abstract: The invention relates to a magnetic resonance imaging system (100) for determining an approximation (150) of an electric conductivity distribution within a three-dimensional anatomical structure of interest. The determining comprises acquiring a first set of (3-n)-dimensional magnetic resonance data (144), reconstructing a (3-n)-dimensional phase distribution (146) using the (3-n)-dimensional magnetic resonance data (144), calculating a (3-n)-dimensional electric conductivity distribution (148) using spatial derivatives within the (3-n) dimensions and applying to the (3-n)-dimensional electric conductivity distribution (148) a scaling factor compensating for the relative reduction of dimensions by n.

Abstract: The present disclosure relates to a computer implemented medical analysis method for predicting metastases (300) in a test tissue sample, the method comprising: providing a first machine learning model (154) having an input and an output, receiving a description (401) of a tumor (304) and first image data (148) of a test tissue sample of an anatomy region (306), the test tissue sample being free of metastases (300), providing the first image data (148) and the tumor description (401) to the input of the first machine learning model (154), in response to the providing, receiving from the output of the first machine learning model (154) a prediction of occurrence of metastases (300) originating from the tumor (304) in the test tissue sample, and providing the prediction.

Abstract: The invention relates to a magnetic resonance imaging system (10), the system comprising a magnetic resonance imaging device (12) for acquiring data from a moving subject (14), especially a fetus or a part of said fetus; and an image generator (30) for generating an image of said moving subject (14), wherein the magnetic resonance imaging device (12) is configured to acquire the data from the subject (14) at different positions of said subject (14) with respect to a magnetization direction B0, utilizing the movement of the subject (14); and wherein the image generator (30) is configured to —determine the position and/or orientation of said subject (14) during the respective data acquisition; —reconstruct phase images from the acquired data; and —generate a susceptibility map based on the reconstructed phase images. The invention further relates to a corresponding method for generating an image of the subject (14).

Abstract: A computerized system for monitoring cancer therapy and a related method. The system comprises an input port (IN) for receiving two or more input images acquired of a subject, the two or more input images capable of recording metabolic activity and extracellular pH level. An evaluator (EVAL) of the system is configured to assess, based on the input images, i) a change over time in metabolic activity and ii) a change over time in extracellular pH level. The evaluator (EVAL) is further configured to establish, based on the assessment, an indication on whether or not there is a response to a cancer therapy in relation to a lesion of the subject or on whether the assessment is inconclusive. The indication is output through an output interface (OUT).

Abstract: The invention provides for a medical imaging system (100, 400) comprising: a memory (112) for storing machine executable instructions and a processor (106) for controlling the medical imaging system.

Abstract: An iterative reconstruction is performed of multiple gradient echo MR imaging data to generate a reconstructed MR image (36). The iterative reconstruction uses a model (30) that links the MR imaging data and the reconstructed MR image. The model includes a parameterized magnetic field fluctuation component (32). During the performing of the iterative reconstruction, parameters of the parameterized magnetic field fluctuation component of the model are updated to optimize a cost function (40) dependent on partial derivatives of the reconstructed MR image with respect to the parameters of the parameterized magnetic field fluctuation component of the model. The image may be further processed to generate an R2* map (50), an SWI image (52), or a QSM map (54).

Abstract: The invention provides for a magnetic resonance imaging system (100, 300, 100) for acquiring magnetic resonance data (110, 1104) from a subject (118) within an imaging zone (108). The magnetic resonance imaging system comprises a memory (136) for storing machine executable instructions (160, 162, 164, 166, 316) and pulse sequence data (140, 1102). The pulse sequence data comprises instructions for controlling the magnetic resonance imaging system to acquire magnetic resonance data according to a magnetic resonance imaging method. The magnetic resonance imaging system further comprises a processor (130) for controlling the magnetic resonance imaging system.

Abstract: The invention relates to a magnetic resonance imaging system (10), the system comprising a magnetic resonance imaging device (12) for acquiring data from a moving subject (14), especially a fetus or a part of said fetus; and an image generator (30) for generating an image of said moving subject (14), wherein the magnetic resonance imaging device (12) is configured to acquire the data from the subject (14) at different positions of said subject (14) with respect to a magnetization direction B0, utilizing the movement of the subject (14); and wherein the image generator (30) is configured to —determine the position and/or orientation of said subject (14) during the respective data acquisition; —reconstruct phase images from the acquired data; and —generate a susceptibility map based on the reconstructed phase images. The invention further relates to a corresponding method for generating an image of the subject (14).

Abstract: An electric properties tomography method for reconstructing a spatial distribution of electric conductivity (?) from magnetic resonance image data representative of a magnetic resonance image of at least a portion of a subject of interest (20), the spatial distribution covering at least a portion of the area of the magnetic resonance image, and the method comprising following steps:—segmenting the magnetic resonance image,—extrapolating acquired phase values, —replacing acquired phase values by the extrapolated phase values,—transforming into the frequency domain,—multiplying a frequency domain-transformed numerical second derivative by the acquired phase values and the frequency domain-transformed numerical second derivative by the extrapolated phase values, respectively, and—transforming the result of the multiplying into the spatial domain. Also covered are a corresponding MRI system and a software module.

Abstract: The invention provides for a medical imaging system (100, 400) comprising: a memory (112) for storing machine executable instructions and a processor (106) for controlling the medical imaging system.

Abstract: It is an object of the invention to improve tissue classification in MRI images. In particular it is an object of the invention to improve the classification of bone and air in MRI images. This object is achieved by a method for tissue classification in a region of interest in a magnetic resonance (MR) image comprising a first region and a second region, wherein the first region represents air and the second region represents bone.