Abstract: A mechanism for generating denoised basis images for a computed tomography scanner. An input dataset, comprising first and second basis image data, is processed using a machine-learning algorithm process to produce the denoised basis images. The first and second basis image data each comprise at least one basis image, wherein the type of image differs between the first and second basis image data.

Abstract: A method is provided for processing images comprising retrieving measured data for a first image. The method then generates partially filtered data by applying a first filter to the measured data. The first filter is a generic filter. The method then reconstructs the partially filtered data to generate a partially filtered image. The method then generates a partially processed image by applying a first processing routine to the partially filtered image. The method then generates a filtered image by applying a second filter to the partially processed image, where the second filter is a filter selected from a plurality of potential secondary filters. The method then outputs the filtered image. Systems are provided for implementing the claimed method and training methods for neural networks used in the method are provided as well.

Abstract: The present invention relates to a spectral X-ray CT imaging system (10), comprising: a spectral X-ray CT imaging unit (20); a processing unit (30); and an output unit (40). The spectral X-ray CT imaging unit comprises an X-ray tube (22) and a dual layer X-ray detector (24), and wherein a body portion of a subject to be examiner can be located between the X-ray tube and the dual layer X-ray detector. The spectral X-ray CT imaging unit is configured to acquire an overall scan of the body portion comprising a plurality of acquisitions at different projections angles. The processing unit is configured to utilize information on the body portion for each projection of the different projections angles. The processing unit is configured to determine a voltage for the X-ray tube for each acquisition of the plurality of acquisitions, wherein the determination for each acquisition comprises utilization of the corresponding information on the body portion for the projection associated with that acquisition.

Abstract: A mechanism for generating denoised basis projection data. Low-energy projection data and high-energy projection data is processed using a neural network that is trained to perform the dual task of decomposition and denoising. The neural network thereby directly outputs basis projection data, taking the place of existing decomposition and denoising techniques.

Abstract: A mechanism for processing projection data generated by a computed tomography scanner. The projection data is processed by a machine-learning algorithm trained to perform an up-sampling or super-resolution technique on input data in order to generate higher resolution projection data.

Abstract: A non-transitory computer readable medium (26s) stores instructions executable by at least one electronic processor (14s) to perform a method (100) to coordinate radiologist review of a medical imaging procedure performed using a medical imaging device (2). The method includes acquiring a video (17) of the medical imaging device, the acquired video including at least one of video acquired by a camera (16) arranged to image the medical imaging device and/or video comprising screen-scraped image frames of an imaging device controller (10) of the medical imaging device: determining a review time for the medical imaging procedure based on the video: providing a notification to a remote electronic processing device (12) operable by a radiologist of the determined review time; and at the review time, extracting at least one review image (38) from the video and making the at least one review image available at the remote electronic processing device.

Abstract: Described herein is a medical system (100, 300) comprising a memory (110) storing machine executable instructions (120) and an upsampling neural network (122). The upsampling neural network is configured to output an upsampled magnetic resonance image (130) with a second resolution in response to receiving a preliminary magnetic resonance image (126) with a first resolution which is lower than the second resolution. The execution of the machine executable instructions causes a computational system (104) to: receive (200) preliminary k-space data (124); reconstruct (202) the preliminary magnetic resonance image from the preliminary k-space data; receive (204) clinical k-space data (204); receive (206) the upsampled magnetic resonance image in response to inputting the preliminary magnetic resonance image into the upsampling neural network; and provide (208) a motion corrected magnetic resonance image (132) using the upsampled magnetic resonance image and the clinical k-space data.

Abstract: An approach for denoising a medical image. A noise map, which defines an estimate of one or more statistical parameters for each pixel of the medical image, is used to modify or normalize the medical image. The modified medical image is then processed, using a machine-learning method, to produce a denoised medical image.

Abstract: A system (CDD) and related method for facilitating an iterative reconstruction operation. In iterative reconstruction, imagery in image domain is reconstructed in plural steps from measured projection data in projection domain. The system and methods use a trained machine learning module (MLM). The system receives input correction data generated in the iterative reconstruction operation. The system predicts, based on the input correction data, output correction data. The output correction data is provided for facilitating correcting a current image, as reconstructed in a given step, into a new image.

Abstract: A mechanism for generating a partially denoised image. A residual noise image, obtained by processing an image using a convolutional neural network, is weighted. The blending or combination of the weighted residual noise image and the (original) image generates the partially denoised image.

Abstract: A method is provided for processing medical images, the method including receiving a first image and a second image different from the first image, where the second image is of the same subject matter as the first image. The method further includes identifying a plurality of anatomical structures in the first image and defining a plurality of image segments in the second image based N on locations of the anatomical structures identified in the first image. The method then applies a processing routine associated with a first anatomical structure to the first image segment in the second image and a processing routine associated with a second anatomical structure to the second image segment in the second image. Also provided is an imaging system for implementing the described method and a non-transitory computer readable medium storing a program for processing medical images.

Abstract: One embodiment of the present disclosure may provide a method for training and tuning a neural network model, including: adding simulated noise to an initial image of an object to generate a noisy image (601, 603), the simulated noise taking the same form as natural noise in the initial image; training a neural network model on the noisy image using the initial image as ground truth (605), wherein in the neural network model is trained on the noisy work model a tuning variable is extracted or generated, the tuning variable defining an amount of noise removed during use (607); identifying a first value for the tuning variable that minimizes a training cost function for the tuning variable is identified or for the initial image; and assigning a second value for the tuning variable (611), the second value different than the first value, wherein the neural network model identifies more noise in the noisy image when using the second value than when using the first value.

Abstract: Disclosed herein is a medical system (100, 300, 400) comprising a memory (110) storing a trainable machine learning module (122) trained using training data descriptive of a training data distribution (600) to output a reconstructed medical image (136) in response to receiving measured medical image data (128) as input. The medical system comprises a computational system (104). The execution of machine executable instructions (120) causes the computational system to: receive (200) the measured medical image data and determine (202) the out-of-distribution score and the in-distribution accuracy score consecutively in an order determined a sequence, detect (204) a rejection of the measured medical image data using the out-of-distribution score and/or the in-distribution accuracy score during execution of the sequence, provide (206) a warning signal (134) if the rejection of the measured medical image data is detected.

Abstract: An image processing system (IPS) and related method for supporting tomographic imaging. The system comprises an input interface (IN) for receiving, for a given projection direction (pi), a plurality of input projection images at different phase steps acquired by a tomographic X-ray imaging apparatus configured for dark-field and/or phase-contrast imaging. A machine learning component (MLC) processes the said plurality into output projection imagery that includes a dark-field projection image and/or a phase contrast projection image for the said given projection direction.

Abstract: System and related methods for de-noising 3D imagery. The system (IPS) comprises a pre-trained discriminative neural network (NN). The network includes a sequence of 3D convolutional operators (CV) for processing a received 3D image volume into a 3D output image. The 3D output image has a lower noise level than the 3D input image.