A method for adaptive coincidence data processing is provided. The method includes detecting positron annihilation events with a detector array of a positron emission tomography (PET) scanner, wherein the PET scanner includes multiple detector rings disposed along a longitudinal axis of the PET scanner, and each detector ring includes multiple detectors. The method also includes, within a given time period, dynamically adjusting a number of positron annihilation events accepted and transmitted to acquisition circuitry for processing utilizing a numerical difference in detector rings along the longitudinal axis between a first detector and a second detector detecting respective annihilation photons from a positron annihilation event.

Embodiments discussed herein facilitate determination of risk of recurrence of atrial fibrillation (AF) after ablation based on fractal features. One example embodiment is configured to generate a binary mask of at least a portion of a CT scan of a heart of a patient with AF; compute one or more radiomic fractal-based features from at least one of the binary mask or the portion of the CT scan; provide the one or more radiomic fractal-based features to a trained machine learning (ML) classifier; and receive a prediction from the trained ML classifier of whether or not the AF will recur after AF ablation, wherein the prediction is based at least in part on the one or more radiomic fractal-based features.

A method and system for detecting an image of an object in an analyzer-based system with a polychromatic x-ray beam from an x-ray source, wherein an analyzer crystal and a detector simultaneously acquire a rocking curve of the x-ray beam for all energies of the x-ray beam. The x-ray beam is diffracted through the object using an asymmetrical monochromator. A detector movement is synchronized with one of the x-ray source or the object. The synchronization includes moving the detector at a first rate that is different than a second rate of the object or the x-ray source, wherein a ratio between the first rate and the second rate is determined by the magnification of the system.

Systems and methods for digital radiography are provided. The method may be implemented on the implemented on a DR system including an imaging device and a computing device. The computing device may include at least one processor and at least one storage device. The method may include directing multiple dose sensors to detect a dose of radiation rays emitted from a radiation source of the imaging device. The multiple dose sensors may correspond to multiple imaging detectors, respectively. The method may also include determining the dose of the radiation rays. The method may further include directing, based on the dose of the radiation rays, at least one imaging detector of the multiple imaging detectors to proceed to detect the radiation rays for generating an image of a target object to be examined.

Gamma cameras may be used to obtain two-dimensional images of an emitting object, of which the most common form is the “Anger-type” gamma camera. The primary components in a conventional Anger-type gamma camera include, but are not limited to: a plurality of photo-multiplier tubes, a scintillator material, and a collimator. The disclosed invention claims a novel use of a gamma camera which eliminates the collimator. The new method is a method of forming an initial image from the incident radiation, which does not depend on any mechanical or other means of restricting the incident radiation to be passed on to a position-sensitive radiation detector. This method then uses mathematical deconvolution to produce an image of the object without the need for a collimator and without reliance on a pre-existing image.

Methods and systems for deep learning based image reconstruction are disclosed herein. An example method includes receiving a set of imaging projections data, identifying a voxel to reconstruct, receiving a trained regression model, and reconstructing the voxel. The voxel is reconstructed by: projecting the voxel on each imaging projection in the set of imaging projections according to an acquisition geometry, extracting adjacent pixels around each projected voxel, feeding the regression model with the extracted adjacent pixel data to produce a reconstructed value of the voxel, and repeating the reconstruction for each voxel to be reconstructed to produce a reconstructed image.

Systems and methods are disclosed for providing a cardiovascular score for a patient. A method includes receiving, using at least one computer system, patient-specific data regarding a geometry of multiple coronary arteries of the patient; and creating, using at least one computer system, a three-dimensional model representing at least portions of the multiple coronary arteries based on the patient-specific data. The method also includes evaluating, using at least one computer system, multiple characteristics of at least some of the coronary arteries represented by the model; and generating, using at least one computer system, the cardiovascular score based on the evaluation of the multiple characteristics. Another method includes generating the cardiovascular score based on evaluated multiple characteristics for portions of the coronary arteries having fractional flow reserve values of at least a predetermined threshold value.

Emission imaging data are reconstructed to generate a low dose reconstructed image. Standardized uptake value (SUV) conversion (30) is applied to convert the low dose reconstructed image to a low dose SUV image. A neural network (46, 48) is applied to the low dose SUV image to generate an estimated full dose SUV image. Prior to applying the neural network the low dose reconstructed image or the low dose SUV image is filtered using a low pass filter (32). The neural network is trained on a set of training low dose SUV images and corresponding training full dose SUV images to transform the training low dose SUV images to match the corresponding training full dose SUV images, using a loss function having a mean square error loss component (34) and a loss component (36) that penalizes loss of image texture and/or a loss component (38) that promotes edge preservation.

A computer-implemented method is provided for improving live video quality. The method comprises: acquiring, using a medical imaging apparatus, a stream of consecutive image frames of a subject, and the stream of consecutive image frames are acquired with reduced amount of radiation dose; applying a deep learning network model to the stream of consecutive image frames to generate an image frame with improved quality; and displaying the image frame with improved quality in real-time on a display.

A medical imaging system comprises an operator terminal configured to obtain at least one image of a patient generated by a medical imaging device, receive one or more notes pertaining to the at least one image from an operator of the medical imaging device, store a clean set of images including the at least one image in at least one server, annotate the at least one image with the one or more notes to generate a set of annotated images; tag the set of annotated images as non-persistent, and store the set of annotated images in the at least one server; wherein the at least one server is configured to provide to a physician terminal both the clean set of images and the annotated set of images stored for the patient and automatically delete the one or more images tagged as non-persistent after review thereof by the physician.