Systems and methods for tissue discrimination are disclosed. The systems and the methods utilize coded x-ray beams. Transmission signals and scatter signals are utilized to determine tissue properties.

At least one standard image representing a standard object having different thicknesses, the at least one standard image being obtained by imaging the standard object by radiation in a state in which an object is interposed between the standard object and a radiation detector is acquired, a relationship between the thickness of the standard object and a radiation attenuation coefficient of the standard object, which corresponds to an energy characteristic of the radiation, the relationship reflecting an influence of beam hardening by the standard object and the object, is derived, a primary ray component corresponding to the thickness of the standard object included in the standard image is derived based on the relationship between the thickness of the standard object and the radiation attenuation coefficient of the standard object, a scattered ray component corresponding to the thickness of the standard object included in the standard image is derived based on a difference between the standard image and the primary ray component, and a scattered ray model representing a relationship between the thickness of the standard object and a ratio of the scattered ray component to the primary ray component is derived.

An estimation device includes at least one processor, in which the processor functions as a learned neural network that derives a result of estimation of at least one emphasis image in which a specific composition of a subject including a plurality of compositions is emphasized from a simple two-dimensional image acquired by simply imaging the subject. The learned neural network is learned by using, as teacher data, a composite two-dimensional image representing the subject, which is derived by combining a three-dimensional CT image of the subject, and an emphasis image for learning in which the specific composition of the subject is emphasized, which is derived from the CT image.

An estimation device includes at least one processor, in which the processor functions as a learned neural network that derives a result of estimation relating to a bone density of a bone part from a simple radiation image acquired by simply imaging a subject including the bone part. The learned neural network is learned by using, as teacher data, (i) two radiation images acquired by imaging the subject including the bone part with radiation having different energy distributions, (ii) the radiation image of the subject and a bone part image representing the bone part of the subject, or (iii) the radiation image of the subject and a bone density image representing the bone density of the bone part of the subject, and information relating to the bone density of the bone part of the subject.

An estimation device includes at least one processor, in which the processor functions as a learned neural network that derives a result of estimation of at least one emphasis image in which a specific composition of a subject including a plurality of compositions is emphasized from a simple two-dimensional image acquired by simply imaging the subject. The learned neural network is learned by using, as teacher data, two radiation images acquired by imaging the subject with radiation having different energy distributions and an emphasis image for learning in which the specific composition of the subject is emphasized, which is derived from the two radiation images.

A method is for producing a scattered beam collimator starting from a lower side and extending in a build-up direction as far as an upper side, and having a large number of X-ray absorbing partitions, and in which pass-through channels for unscattered X-ray radiation are embodied between the partitions. A lithographic process is used, by which the partitions of the scattered beam collimator are formed from a photoresist into which an X-ray absorbing material is mixed.

An estimation device includes at least one processor, in which the processor functions as a learned neural network that derives a result of estimation relating to a bone density of a bone part from a simple radiation image acquired by simply imaging a subject including the bone part or a DXA scanning image acquired by imaging the subject by a DXA method. The learned neural network is learned by using, as teacher data, a composite two-dimensional image representing the subject, which is derived by combining a three-dimensional CT image of the subject, and information relating to the bone density of the subject.

Systems and methods monitoring progress of a medical procedure by radiation exposure are provided. Locations of radiation producing and scattering items of medical equipment are received at a controller. Locations of individuals assisting with the medical procedure are received at the controller by way of tracking devices worn by the individuals during the medical procedure. The controller receives indication of when the radiation producing item(s) are activated and develops a radiation scatter intensity field. An analytical subsystem determines an estimated exposure level for each individual based on their position within the radiation scatter intensity field at each instance the radiation producing device is activated, which are compared to a benchmark. Where the estimated exposure level exceeds the benchmark, an intervention subsystem provides an intervention.

An imaging system (102) includes a radiation source (112) configured to emit X-ray radiation, a detector array (114) configured to detect X-ray radiation and generate a signal indicative thereof, an a reconstructor (116) configured to reconstruct the signal and generate non-spectral image data. The imaging system further includes a processor (124) configured to process the non-spectral image data using a deep learning regression algorithm to estimate spectral data from a group consisting of spectral basis components and a spectral image.

A computed tomography (CT) system and method is provided. The CT system is used to carry out an image improvement method in which a prior or previously-acquired patient image can be used to supplement or otherwise improve an acquired CT image, wherein the acquired projection data representative of the acquired CT image might be truncated or otherwise incomplete/insufficient to accurately and stably recover the scanned object/patient.