Disclosed herein is a system, comprising: a radiation source configured to cause emission of characteristic X-rays of a chemical element in a portion of a human body by generating and directing radiation to the portion; a first image sensor configured to capture a set of images of the portion using the characteristic X-rays; and a second image sensor configured to capture a set of tomograms using the radiation that has transmitted through the portion.

Disclosed herein is an apparatus comprising: an X-ray source configured to direct X-rays through a human tissue; an X-ray detector configured to capture an image of the human tissue with the X-rays; wherein the apparatus is configured to identify an image of a blood vessel from the image of the human tissue and configured to determine a blood sugar level based on the image of the blood vessel.

In described examples, a charge sensitive amplifier (CSA) generates an integrated signal in response to a current signal. A high pass filter is coupled to the CSA and receives the integrated signal and an inverse of an event signal, the high pass filter generates a coarse signal. An active comparator is coupled to the high pass filter and receives the coarse signal and a primary reference voltage signal, the active comparator generates the event signal.

One or more example embodiments of the present invention relates to a system for detection of x-ray radiation. The system comprises photon-counting x-ray CT scanners and associated edge devices. Each edge device determines a quality indicator indicative of a quality of the sensor data based on scanner data. Further, each edge device generates a parameterized machine learning model by optimizing the quality indicator. A server device receives the generated parameterized machine learning models from the edge devices, aggregates the parameterized machine learning models into an aggregated parameterized machine learning model, and sends at least part of the aggregated parameterized machine learning model back to the edge devices.

In an embodiment of a motion correction method, a first virtual non-contrast X-ray image of a region under examination is determined based upon first spectral raw X-ray data associated with a first contrast distribution, via material decomposition. In addition, a second virtual non-contrast X-ray image of the region under examination is determined based upon second spectral raw X-ray data associated with a second contrast distribution, differing from the first contrast distribution, via material decomposition. Then the first virtual non-contrast X-ray image is registered with the second virtual non-contrast X-ray image to determine a transformation field between the two virtual non-contrast X-ray images. Finally, based upon the determined transformation field, first X-ray image data based on the first raw X-ray data is registered with second X-ray image data based on the second raw X-ray data. An X-ray imaging method, a motion correction device and an X-ray imaging system are also discussed.

A neural network based corrector for photon counting detectors is described. A method for photon count correction includes receiving, by a trained artificial neural network (ANN), a detected photon count from a photon counting detector. The detected photon count corresponds to an attenuated energy spectrum. The attenuated energy spectrum is related to characteristics of an imaging object and is based, at least in part, on an incident energy spectrum. The method further includes correcting, by the trained ANN, the detected photon count to produce a corrected photon count. The method may include reconstructing, by image reconstruction circuitry, an image based, at least in part, on the corrected photon count.

A fat mass derivation device includes at least one processor, in which the processor derives a fat mass distribution of a subject from a first radiation image and a second radiation image acquired by imaging the subject with radiation having different energy distributions, and derives a visceral fat mass distribution of the subject based on a shape of the fat mass distribution in a cross section orthogonal to a body axis of the subject.

A computed tomography (CT) image processing apparatus and a CT image processing method are provided. The CT image processing apparatus may generate a virtual monochromatic image (VMI) by applying a weight to each of first, second, and third images corresponding to three different energy ranges. The CT image processing apparatus may set a region of interest (ROI) on a CT image, determine a VMI at an energy level at which a CNR of the ROI is at a maximum among a plurality of VMIs, and display the determined VMI.

A multi-spectral tomography imaging system includes one or more source devices configured to direct beams of radiation in multiple spectra to a region of interest (ROI), and one or more detectors configured to receive the beams of radiation. The system includes a processor configured to cause movement in at least one of the components such that a first beam of radiation with a first spectrum is directed to the ROI for less than 360 degrees of movement of the ROI. The processor is also configured to process data detected by the one or more detectors, where the data results at least in part from the first beam of radiation with the first spectrum that is directed to the ROI for less than the 360 degrees of movement of the ROI. The processor is further configured to generate an image of the ROI based on the processed data.

A method and apparatus for diagnosing and/or calibrating underperforming pixels in detectors in a small pixelated photon counting CT system utilizes a series of tests on image data acquired in-situ as part of a series of calibration scans in the CT system. Tests are performed on the acquired data to determine the existence of underperforming pixels within the detectors such that the information acquired by those pixels can be replaced by alternate data from surrounding pixels (e.g. by interpolation). The underperforming pixels are stored in “bad” pixel tables and may be specific to a type of image (e.g., spectral or counting) and a specific protocol.