Abstract: A dynamic frame reconstruction apparatus and method for medical image processing is disclosed which reduces the computationally expensive reconstruction of images but which retains the accuracy of the image reconstruction. A convolutional neural network is used to cluster the dynamic data into groups of frames, each group sharing similar radiotracer distribution. In one embodiment, groups of frames that have similar reconstruction parameters are determined, and scatter and random estimations are computed once and shared among each of the frames in the same frame group.

Abstract: A method of detecting a malicious wireless vehicle-to-everything (V2X) communication includes retrieving perception data from a perception system on an ego vehicle, determining information about nearby objects from the perception data, receiving a first Basic Safety Message (BSM) from a first V2X source and determining if a vehicle location indicated in the first BSM corresponds to a location visible to the ego vehicle. In the event that the vehicle location indicated in the first BSM does not correspond to a location visible to the ego vehicle, the method further includes receiving a second V2X communication from a second V2X source and determining if the second V2X communication indicates a vehicle at the vehicle location indicated in the first BSM. In the event that the second V2X communication does not indicate a vehicle at the vehicle location indicated in the first BSM, the first BSM data is flagged as malicious.

Abstract: A method is provided for count loss correction based on detector dead time in a radiation diagnosis apparatus. The method includes acquiring scan data from a scan of a patient performed using the radiation diagnosis apparatus; determining, from the acquired scan data, a first count rate occurring in a first energy window spanning a first energy range; determining, from the acquired scan data, a second count rate occurring in a second window spanning a second energy range, the second energy range being different from the first energy range; calculating a particular count loss correction factor based on the determined first count rate and the determined second count rate; and reconstructing an image based on the acquired scan data and the calculated particular count loss correction factor.

Abstract: A system comprises a computer including a processor and a memory. The memory includes instructions such that the processor is programmed to: determine, via a trained neural network model, a route for a vehicle to traverse based on vehicle sensor data, and update the trained neural network model based on data received from at least one of an edge computing device or an infrastructure (V2I) device.

Abstract: A method of normalizing detector elements in an imaging system is described herein. The method includes a line source that is easier to handle for a user, and decouples the normalization of the detector elements into a transaxial domain and an axial domain in order to isolate errors due to positioning of the line source. Additional simulations are performed to augment the real scanner normalization. A simulation of a simulated line source closely matching the real line source can be performed to isolate errors due to physical properties of the crystals and position of the crystals in the system, wherein the simulated detector crystals are otherwise modeled uniformly. A simulation of a simulated cylinder source can be performed to determine errors due to other effects stemming from gaps between the detector crystals.

Abstract: A method, apparatus, and computer instructions stored on a computer-readable medium perform latent image feature extraction by performing the functions of receiving image data acquired during an imaging of a patient, wherein the image data includes motion by the patient during the imaging; segmenting the image data to include M image data segments corresponding to at least N motion phases having shorter durations than a duration of the motion by the patient during the imaging, wherein M is a positive integer greater than or equal to a positive integer N; producing, from the M image data segments, at least N latent feature vectors corresponding to the motion by the patient during the imaging; and performing a gated reconstruction of the N motion phases by reconstructing the image data based on the at least N latent feature vectors.

Abstract: A system comprises a computer including a processor and a memory. The memory includes instructions such that the processor is programmed to: execute an autonomous vehicle algorithm simulating vehicle operations determine whether a notification that provides information on how a driver intervention for actuation by system feature functions has been at least one of previously presently or confirmed and cause the notification to be generated. The notification includes information for responding to a finite number of driving options determined by the driver intervention for actuation by system.

Abstract: A method of generating an image, including: receiving, via a monitoring device, time-dependent data corresponding to a patient parameter; obtaining emission data representing radiation detected during a medical imaging scan; identifying time frames during the medical imaging scan to exclude from the obtained emission data, the identified time frames corresponding to a stressed emotional state for the patient based on the patient parameter; modifying the obtained emission data to exclude the emission data corresponding to the time frames corresponding to the stressed emotional state; and generating an emotional-state-corrected image based on the modified emission data excluding the emission data corresponding to the time frames corresponding to the stressed emotional state.

Abstract: At least two vehicle behavior reports are received at a reputation score management system. Each of the vehicle behavior reports is received from a corresponding traffic autonomous vehicle and includes a unique vehicle identifier and a classification result associated with a source autonomous vehicle. A reputation score is generated for association with the unique vehicle identifier based at least in part on the classification results received in the at least two vehicle behavior reports. A request for the reputation score associated with the unique vehicle identifier is received from an ego autonomous vehicle. The requested reputation score is transmitted to the ego autonomous vehicle to enable the ego autonomous vehicle to determine whether a V2V message including the unique vehicle identifier associated with the requested reputation score is one of an honest V2V message and a malicious V2V message based in part on the reputation score.

Abstract: The present disclosure is related to removing scatter from a SPECT scan by utilizing a radiative transfer equation (RTE) method. An attenuation map and emission map are acquired for generating scatter sources maps and scatter on detectors using the RTE method. The estimated scatter on detectors can be removed to produce an image of a SPECT scan with less scatter. Both first-order and multiple-order scatter can be estimated and removed. Additionally, scatter caused by multiple tracers can be determined and removed.

Abstract: An automated driving system (ADS) of an autonomous vehicle includes a communication module, a perception module, a misbehavior detection module, and a processor. The communication module is configured to receive a vehicle-to-vehicle (V2V) message comprising message-based vehicle data. The perception module configured to receive sensor data from at least one vehicle sensing device. The misbehavior detection module is configured to determine whether the V2V message is one of a legitimate message and a malicious message based at least in part on a comparison of the message-based vehicle data with sensor-based vehicle data generated based on the sensor data. The processor is configured to manage performance of the autonomous vehicle in accordance with the message-based vehicle data based on the determination. Other embodiments are described and claimed.

Abstract: A vehicle collaboration system of a first autonomous vehicle includes a transceiver and a collaboration controller. The transceiver is configured to broadcast a first collaboration message including first vehicle data associated with the first autonomous vehicle in connection with a collaboration application to a collaboration domain group via a hybrid distributed-connected network (HYDIN). The collaboration domain group includes at least the first autonomous vehicle and a second autonomous vehicle. The transceiver is configured to receive a second collaboration message including second vehicle data associated with the second autonomous vehicle in connection with the collaboration application via the HYDIN. The second collaboration message is broadcast from the second autonomous vehicle to the collaboration domain group via the HYDIN.

Abstract: Upon receiving list-mode data by detecting radiation emitted from a radiation source positioned with a field of view of a medical imaging scanner, each photon included in the list-mode data can be classified according to one or more interaction properties, such as energy or number of crystals interacted with. Grouped pairs of photons can be generated based on the classifying, and a corresponding interaction-property-specific correction kernel (e.g., a corresponding interaction-property-specific point spread function correction kernel) can be selected for each group. Corresponding interaction-property-specific correction kernels can then be utilized to generate higher quality images.

Abstract: An automated driving system (ADS) of an autonomous vehicle includes a communication module, a misbehavior detection module, and a processor. The communication module is configured to receive a vehicle-to-vehicle (V2V) message including source vehicle data and receive a fusion data message including fusion data from a mobile edge computing (MEC) system including a roadside unit (RSU). The source vehicle data includes a source vehicle location. The fusion data is based on RSU sensed data and on vehicle sensed data received at the RSU from at least one vehicle. The misbehavior detection module is configured to determine whether a source vehicle is disposed at the source vehicle location based on the fusion data. The processor is configured to manage performance of the autonomous vehicle in accordance with the source vehicle data based at least in part on the determination. Other embodiments are described and claimed.

Abstract: A method, apparatus, and non-transitory computer-readable storage medium for image denoising whereby a deep image prior (DIP) neural network is trained to produce a denoised image by inputting the second medical image to the DIP neural network and combining a converging noise and an output of the DIP network during the training such that the converging noise combined with the output of the DIP network approximates the first medical image at the end of the training, wherein the output of the DIP network represents the denoised image.

Abstract: Multiple interactions, such as Compton scattering, inside a PET detector are used to predict an incident photon's direction for identifying true coincidence events versus scatter/random coincidence events by creating a cone shaped shell projection defining a range of possible flight directions for the incident photon. The disclosed techniques can be used as prior information to improve the image reconstruction process. The disclosed techniques can be implemented in a LYSO/SiPM-based layer stacked detector, which can precisely register multiple interactions' 3D position.

Abstract: A method, system, and computer readable medium to perform nuclear medicine scatter correction estimation, sinogram estimation and image reconstruction from emission and attenuation correction data using deep convolutional neural networks. In one embodiment, a Deep Convolutional Neural network (DCNN) is used, although multiple neural networks can be used (e.g., for angle-specific processing). In one embodiment, a scatter sinogram is directly estimated using a DCNN from emission and attenuation correction data. In another embodiment a DCNN is used to estimate a scatter-corrected image and then the scatter sinogram is computed by a forward projection.

Abstract: The present disclosure is related to removing scatter from a SPECT scan by utilizing a radiative transfer equation (RTE) method. An attenuation map and emission map are acquired for generating scatter sources maps and scatter on detectors using the RTE method. The estimated scatter on detectors can be removed to produce an image of a SPECT scan with less scatter. Both first-order and multiple-order scatter can be estimated and removed. Additionally, scatter caused by multiple tracers can be determined and removed.

Abstract: An apparatus for reconstructing a positron emission tomography (PET) image, comprising processing circuitry configured to extract, from raw data obtained from a PET scanner, energy data and timing data associated with a plurality of annihilation events, the extracted energy data and the extracted timing data for each annihilation event corresponding to interactions between each of a pair of gamma rays generated by each annihilation event and one or more gamma ray detectors of the PET scanner, classify each annihilation event based on respective extracted energy data and respective extracted timing data, determine, for each annihilation event and based on a calculated timing resolution of the annihilation event, a width of a time-of-flight kernel, and reconstruct, by processing circuitry, the PET image based on the obtained raw data from the PET scanner and the determined width of the time-of-flight kernel associated with each annihilation event.

Abstract: Multiple interactions, such as Compton scattering, inside a PET detector are used to predict an incident photon's direction for identifying true coincidence events versus scatter/random coincidence events by creating a cone shaped shell projection defining a range of possible flight directions for the incident photon. The disclosed techniques can be used as prior information to improve the image reconstruction process. The disclosed techniques can be implemented in a LYSO/SiPM-based layer stacked detector, which can precisely register multiple interactions' 3D position.