A radiographic imaging system includes a radiographic detector having a scanning device to obtain patient identifying information. The detector is programmed to display the patient identifying information in human readable form and to access additional information about the patient stored in networked databases.

An image acquisition unit acquires a plurality of projection images corresponding to a plurality of radiation source positions at the time of tomosynthesis imaging, the plurality of projection images being generated by causing an imaging apparatus to perform tomosynthesis imaging. A positional shift amount derivation unit derives a positional shift amount between the plurality of projection images based on body movement of the subject with a reference projection image generated at a radiation source position where an optical axis of the radiation emitted from the radiation source is perpendicular to a detection surface of the detection unit, among the plurality of projection images, as a reference. A reconstruction unit generates a tomographic image of at least one tomographic plane of the subject by reconstructing the plurality of projection images while correcting the positional shift amount.

A method is for generating an X-ray image dataset via an X-ray detector having a converter element and a multiplicity of pixel elements. In an embodiment, the method includes first counting of at least one quantity of count signals dependent upon the incident X-ray radiation in each pixel element of the multiplicity of pixel elements; second counting of at least one quantity of coincidence count signals in each pixel element of the subset of pixel elements with at least one further pixel element of the multiplicity of pixel elements; and generating an X-ray image dataset based upon the at least one quantity of count signals counted in each pixel element of the multiplicity of pixel elements and upon the at least one quantity of coincidence count signals counted in each pixel element of the subset of pixel elements.

An X-ray image processing method, including obtaining a first X-ray image of an object including a plurality of materials including a first material and a second material; obtaining a first partial image generated by imaging the first material and a second partial image generated by imaging the first material overlapping the second material from the first X-ray image; obtaining first information related to a stereoscopic structure of the first material, based on the first partial image included in the first X-ray image; and obtaining second information about the second material based on the first information and the second partial image.

A method, performed by a mobile X-ray detector, of processing an X-ray image, including generating the X-ray image of an object by detecting an X-ray transmitted through the object and converting the detected X-ray into an electrical signal; detecting a power supply stoppage which prevents transmission of the generated X-ray image from the mobile X-ray detector to a workstation; based on the detecting of the power supply stoppage, storing the X-ray image in a nonvolatile memory inside the mobile X-ray detector; and after storing the X-ray image, deactivating the mobile X-ray detector.

A method for estimating motion of an X-ray focal spot is provided. The acts of the method include acquiring image data by causing X-rays to be emitted from the X-ray focal spot of an X-ray source toward a radiation detector comprising multiple channels, wherein a subset of the channels each have a collimator blade positioned above the respective channel. The acts of the method also include independently estimating X-ray focal spot motion in an X-direction for the X-ray focal spot relative to an isocenter of the radiation detector and in a Y-direction along a direction of the X-rays for the X-ray focal spot relative to the isocenter based on respective channel gains for a first channel and a second channel of the subset of the channels.

A general workflow for deep learning based image restoration in X-ray and fluoroscopy/fluorography is disclosed. Higher quality images and lower quality images are generated as training data. This training data can further be categorized by anatomical structure. This training data can be used to train a learned model, such as a neural network or deep-learning neural network. Once trained, the learned model can be used for real-time inferencing. The inferencing can be more further improved by employing a variety of techniques, including pruning the learned model, reducing the precision of the learned mode, utilizing multiple image restoration processors, or dividing a full size image into snippets.

A plurality of radiographic images are captured of a portion of a patient in periodic motion, such as cardiac images (heartbeat motion) or lungs (breathing motion). A first subset of the captured radiographic images are identified as having a common first capture time relative to a phase of the periodic motion. A first 3D image is reconstructed using the first subset of captured radiographic images. Additional subsets of the radiographic images are processed similarly based on their common capture time relative to the phase of the periodic motion.

Apparatus for diagnosing breast cancer, the apparatus comprising a controller having a set of instructions executable to: acquire a contrast enhanced region of interest (CE-ROI) in an X-ray image of a patient's breast, the X-ray image comprising X-ray pixels that indicate intensity of X-rays that passed through the breast to generate the image; determine a texture neighborhood for each of a plurality of X-ray pixels in the CE-ROI, the texture neighborhood for a given X-ray pixel of the plurality of X-ray pixels extending to a bounding pixel radius of BPR pixels from the given pixel; generate a texture feature vector (TF) having components based on the indications of intensity provided by a plurality of X-ray pixels in the CE-ROI that are located within the texture neighborhood; and use a classifier to classify the texture feature vector TF to determine whether the CE-ROI is malignant.

The disclosure relates to systems and methods for evaluating a blood vessel. The method includes receiving image data of the blood vessel acquired by an image acquisition device, and predicting, by a processor, blood vessel condition parameters of the blood vessel by applying a deep learning model to the acquired image data of the blood vessel. The deep learning model maps a sequence of image patches on the blood vessel to blood vessel condition parameters on the blood vessel, where in the mapping the entire sequence of image patches contribute to the blood vessel condition parameters. The method further includes providing the blood vessel condition parameters of the blood vessel for evaluating the blood vessel.