Disclosed herein is a medical image reconstruction apparatus for reconstructing a medical image to assist the reading of a medical image. The medical image reconstruction apparatus includes a computing system, which includes: a receiver interface configured to receive a first medical image to which a first reconstruction parameter adapted to diagnose or analyze a first type of lesion is applied; and at least one processor configured to generate a second reconstruction parameter to be applied to the first medical image in response to a diagnosis order for the diagnosis or analysis of a second type of lesion. The at least one processor provides the second reconfiguration parameter to a user via a user interface, or generates a second medical image for the diagnose or analysis of the second type of lesion by executing the second reconstruction parameter on the first medical image and provides the second medical image to the user.

A method of statistical image restoration for a low-dose CT image using a deep learning, the method includes increasing a number of channels of the low-dose CT image, which is an input image, and decreasing a size of an activation map of the low-dose CT image using an encoder, passing the activation map generated by the encoder to a plurality of residual blocks, and increasing the size of the activation map passed through the residual blocks and generating a denoised result image using a decoder.

Computer-implemented method for determining nuclear medical image data sets in dynamic nuclear medical imaging. The method includes using a trained function to determine at least one further nuclear medical image data set for at least one frame if a basis raw data set is taken from one single frame, wherein input data of the trained function includes at least one of the nuclear medical raw data set of the respective frame or a preliminary reconstructed image reconstructed therefrom, and an already determined nuclear medical image data set.

For reconstruction in medical imaging, such as reconstruction in MR imaging, an iterative, hierarchal network for regularization may decrease computational complexity. The machine-learned network of the regularizer is unrolled or made iterative. For each iteration, nested U-blocks form a hierarchy so that some of the down-sampling and up-sampling of some U-blocks begin and end with lower resolution data or features, reducing computational complexity.

A system for generating a 4D representation of a scene in motion given a sinogram collected from the scene while in motion. The system generates, based on scene parameters, an initial 3D representation of the scene indicating linear attenuation coefficients (LACs) of voxels of the scene. The system generates, based on motion parameters, a 4D motion field indicating motion of the scene. The system generates, based on the initial 3D representation and the 4D motion field, a 4D representation of the scene that is a sequence of 3D representations having LACs. The system generates a synthesized sinogram of the scene from the generated 4D representation. The system adjusts the scene parameters and the motion parameters based on differences between the collected sinogram and the synthesized sinogram. The processing is repeated until the differences satisfy a termination criterion.

Devices, systems, and methods for generating a medical image obtain scan data that were generated by scanning a scanned region, wherein the scan data include groups of scan data that were captured at respective angles; generate partial reconstructions of at least a part of the scanned region, wherein each partial reconstruction of the partial reconstructions is generated based on a respective one or more groups of the groups of scan data, and wherein a collective scanning range of the respective one or more groups is less than the angular scanning range; input the partial reconstructions into a machine-learning model, which generates one or more motion-compensated reconstructions of the at least part of the scanned region based on the partial reconstructions; calculate a respective edge entropy of each of the one or more motion-compensated reconstructions of the at least part of the scanned region; and adjust the machine-learning model based on the respective edge entropies.

During catheter-based angiography, the bone and soft tissues degrade visualization of the vasculature, which is of primary interest in such medical imaging procedures. The present disclosure includes systems and methods utilizing a trained neural network to remove the bone and soft tissue densities from post-contrast images, revealing isolated vascular densities, without the need for a standard pre-injection digital mask and in the setting of patient motion. The final angiographic images may be created in real-time. Systems and methods for the training and optimization of the disclosed neural network are also described.

A system and method include training of an artificial neural network to generate a simulated attenuation-corrected reconstructed volume from an input non-attenuation-corrected reconstructed volume, the training based on a plurality of non-attenuation-corrected volumes generated from respective ones of a plurality of sets of two-dimensional emission data and on a plurality of attenuation-corrected reconstructed volumes generated from respective ones of the plurality of sets of two-dimensional emission data.

An image reconstruction system generates a motion estimation using images that have been reconstructed using AI processing. The system receives listmode data collected by an imaging system and produces two or more histo-images based on the listmode data. The system provides the two or more histo-images to an AI system and receives two or more AI reconstructed images back from the AI system based on the two or more histo-images. The system generates a motion estimation based on the two or more AI reconstructed images.

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.