Systems and methods for segmentation aware reconstruction of under-sampled images while minimizing the appearance of artifacts. A semantic segmentation task is added to the reconstruction model as a surrogate task to focus the reconstruction on the segmented areas. The joint training of a reconstruction model and a segmentation model, and the addition of a loss associated with segmentation, enables a pseudo-attention effect for reconstruction.

A method performed by a computing system comprises receiving a fluoroscopic image of a patient anatomy while a portion of a medical instrument is positioned within the patient anatomy. The fluoroscopic image has a fluoroscopic frame of reference. The portion has a sensed position in an anatomic model frame of reference. The method further comprises identifying the portion in the fluoroscopic image and identifying an extracted position of the portion in the fluoroscopic frame of reference using the identified portion in the fluoroscopic image. The method further comprises registering the fluoroscopic frame of reference to the anatomic model frame of reference based on the sensed position of the portion and the extracted position of the portion.

Embodiments of the present application provide a medical image processing method and a medical imaging system. The method comprises: acquiring a plurality of pieces of image data of a subject under examination; performing image registration on the plurality of pieces of image data; and performing at least one of the following processes according to the image registration result: performing image reconstruction, and generating indication information indicating the motion of the subject under examination.

An image processing apparatus includes a CPU. The CPU acquires a two-dimensional image captured by irradiating a breast with radiation; acquires a position of a radiation source that emits the radiation in a case in which the two-dimensional image is captured; acquires a series of a plurality of projection images or a plurality of tomographic images obtained by performing tomosynthesis imaging of the breast; calculates a virtual projection position, which is a position at which the breast is virtually projected during the tomosynthesis imaging, from the position of the radiation source in a case in which the two-dimensional image is captured; and generates a composite two-dimensional image from the plurality of projection images or the plurality of tomographic images based on the virtual projection position.

An image processing apparatus includes a CPU. The CPU acquires a series of a plurality of projection images or a plurality of tomographic images obtained by performing tomosynthesis imaging by irradiating a breast with radiation having a first energy; acquires a plurality of normal two-dimensional images captured by irradiating the breast with radiation having a second energy, which is higher than the first energy, a plurality of times; calculates, for each of the plurality of normal two-dimensional images, a virtual projection position, which is a position at which the breast is virtually projected during the tomosynthesis imaging, from a position of a radiation source in a case in which the normal two-dimensional image is captured; generates a composite two-dimensional image from the plurality of projection images or the plurality of tomographic images based on the virtual projection position calculated for each of the plurality of normal two-dimensional images; and generates a difference image between each of the plurality of normal two-dimensional images and each of the composite two-dimensional images generated for each of the plurality of normal two-dimensional images.

A computer-implemented method for machine-learning a function configured to take as input a plurality of aligned images of a same patient and each of a different modality among a predetermined set of medical-imaging modalities, and to calculate a fused image. The method includes obtaining a dataset including, for each patient of a plurality of patients and for each modality of a respective at least part of the predetermined set, a respective image, the respective images for a patient being aligned; and training the function based on the dataset. This forms an improved solution for medical imaging.

A computer-implemented method comprises: receiving a measurement data set, the measurement data set including energy resolved data based on a computed tomography scan of the patient; reconstructing a morphology preserving image data set based on a first photon-energy band or a first combination of photon-energy bands described by the measurement data set; segmenting a blood pool within a myocardium in the morphology preserving image data set; reconstructing a contrast agent map based on a second photon-energy band or a second combination of photon-energy bands described by the measurement data set; determining a reference value based on at least one pixel or voxel of the contrast agent map within the segmented blood pool; and determining a respective myocardial extracellular volume fraction depending on the reference value and a value given for at least one respective pixel or voxel outside the segmented blood pool by the contrast agent map.

A computer-implemented method for adaptive image reconstruction can include: generating, by a processor, a preliminary reconstruction image using a preliminary reconstruction configuration; automatically adjusting the preliminary reconstruction configuration to an updated reconstruction configuration, by, at least: obtaining, by the processor, preliminary information from the preliminary reconstruction image; accessing, by the processor, a database of reconstruction configurations, the database providing a mapping of characteristics of images and objects in the images to reconstruction configurations; and performing, by the processor, a lookup operation to identify the updated reconstruction configuration based on the preliminary information; and generating, by the processor, a reconstruction image using the updated reconstruction configuration. Intermediate multifrequency images are generated during generating the preliminary reconstruction image and/or the reconstruction image and can be used to obtain preliminary information from the preliminary reconstruction image or reconstruction information from the reconstruction image, respectively.

A system for processing ultrasound images utilizes a trained orientation neural network to provide orientation information for a multiplicity of images captured around a body part, orienting each image with respect to a canonical view. In one aspect, the system includes a set creator and a generative neural network. The set creator generates sets of images and their associated transformations over time. The generative neural network then produces a summary canonical view set from these sets, showing changes during a body part cycle. In another aspect, the system includes a volume reconstructer. The volume reconstructer uses the orientation information to generate a volume representation of the body part from the oriented images using tomographic reconstruction, and to generate a canonical image from that volume representation.

This disclosure introduces an approach that includes techniques for determining an optimal weighted execution sequence of available reconstruction algorithms using a multi-processor unit. The introduced approach includes executing a series of optimal weighted execution sequence candidates on a representative slice of the image data and comparing their results to select one of the candidates as the optimal weighted execution sequence.