Abstract: A physics-based network model is trained to learn weights such as trapping, detrapping, and/or transport of holes and/or electrons, as well as voltage distribution on a voxel-by-voxel basis throughout a solid-state detector model. The physics-based network may be used to estimate material property variation throughout the voxels. Anode and cathode signals as well as the voltage distribution are relatively strong signals compared to the weaker electron and hole signals. The relatively weaker signals may be limited in range across voxels. In order to expand the range or magnify the effect, the loss function used in training the physics-based neural network may use a weighted combination where the weaker signals are weighted more heavily than stronger signals without substantially reducing the influence of the stronger signals. This improves the inference, resulting in improvement of the accuracy and range of the trained physics-based model.

Abstract: Systems and methods for dose calibration. A dose calibrator may include one or more radiation sources, one or more solid-state detectors and one or more plates positioned between the one or more radiation sources and the one or more solid-state detectors. The one or more solid-state detectors capture one or more images based on emissions received from the one or more radiation sources through the one or more plates for estimating activity of the one or more radiation sources.

Abstract: For gamma ray detection, 3D tiling is made possible by modules that include a gamma ray detector with at least some electronics extending away from the detector as a side wall, leaving an air or low attenuation gap behind the gamma ray detector. The modules may be stacked to form arrays of any shape in 3D, including stacking to form a Compton detector with a scatter detector separated from the catcher detector by the low attenuation gap where the electronics form at least one side wall between the detectors. The modules may be stacked so that the detectors from the different modules are in different planes and/or not part of a same surface (e.g., same surface provided with just 1D or 2D tiling).

Abstract: Systems and methods for imaging. An external device may be used to acquire optical image data of a subject. One or more physical parameters of the subject may be determined based on the optical image data. The one or more physical parameters may be translated to one or more properties of the subject. The one or more properties may then be used to generate medical image data of the subject.

Abstract: For controlling reconstruction in emission tomography, the quality of data for detected emissions and/or the application controls the settings used in reconstruction. For example, a count density of the detected emissions is used to control the number of iterations in reconstruction to more likely avoid over and under fitting. The count density may be adaptively determined by re-binning through pixel size adjustment to find a smallest pixel size providing a sufficient count density. As another example, the detected data may have poor quality due to motion or high body mass index (BMI) of the patient, so the reconstruction is set to perform differently (e.g., less smoothing for high motion or a different number of iterations for high BMI). The quality of the data may be used in conjunction with the application or task for imaging the patient to control the reconstruction.

Abstract: For calibration in medical emission tomography, the dosimeter and/or detector is calibrated in the field, such as at the clinic or other patient scanning location. To allow for a fewer number of calibration sources used in calibrating and/or assist in calibration for multispectral emission tomography, a calibration source includes multiple isotopes and/or a proxy source or isotope is used instead of the same isotope used in factory calibration.

Abstract: Systems and methods for dose calibration. A dose calibrator may include one or more radiation sources, one or more solid-state detectors and one or more plates positioned between the one or more radiation sources and the one or more solid-state detectors. The one or more solid-state detectors capture one or more images based on emissions received from the one or more radiation sources through the one or more plates for estimating activity of the one or more radiation sources.

Abstract: A system and method include acquisition of a plurality of projection images of a subject, each of the projection images associated with a respective projection angle, determination, for each of the projection images, of a center-of-light location in a first image region, determination of a local fluctuation measure based on the determined center-of-light locations, and determination of a quality measure associated with the plurality of projection images based on the local fluctuation measure.

Abstract: A system and method include an array of sensors electrically coupled to a material capable of converting a gamma ray to electrical charge, where distances between a center of a first sensor and centers of each sensor immediately-adjacent to the first sensor are substantially equal. Signals are collected from each sensor immediately-adjacent to the first sensor, and one of a plurality of logical sub-pixels of the first sensor is determined based on the signals collected from each sensor immediately-adjacent to the first sensor.

Abstract: A multi-modality imaging system allows for selectable photoelectric effect and/or Compton effect detection. The camera or detector is a module with a catcher detector. Depending on the use or design, a scatter detector and/or a coded physical aperture are positioned in front of the catcher detector relative to the patient space. For low energies, emissions passing through the scatter detector continue through the coded aperture to be detected by the catcher detector using the photoelectric effect. Alternatively, the scatter detector is not provided. For higher energies, some emissions scatter at the scatter detector, and resulting emissions from the scattering pass by or through the coded aperture to be detected at the catcher detector for detection using the Compton effect. Alternatively, the coded aperture is not provided. The same module may be used to detect using both the photoelectric and Compton effects where both the scatter detector and coded aperture are provided with the catcher detector.

Abstract: A system and method includes acquisition of a plurality of images, each of the plurality of images representing radiotracer concentration in a respective volume at a respective time period, and training of a neural network, based on the plurality of images, to output data indicative of radiation dose associated with a first volume over a first time period based on a first image representing radiotracer concentration in the first volume over a second time period, the second time period being shorter than the first time period.

Abstract: A multi-modality imaging system allows for selectable photoelectric effect and/or Compton effect detection. The camera or detector is a module with a catcher detector. Depending on the use or design, a scatter detector and/or a coded physical aperture are positioned in front of the catcher detector relative to the patient space. For low energies, emissions passing through the scatter detector continue through the coded aperture to be detected by the catcher detector using the photoelectric effect. Alternatively, the scatter detector is not provided. For higher energies, some emissions scatter at the scatter detector, and resulting emissions from the scattering pass by or through the coded aperture to be detected at the catcher detector for detection using the Compton effect. Alternatively, the coded aperture is not provided. The same module may be used to detect using both the photoelectric and Compton effects where both the scatter detector and coded aperture are provided with the catcher detector.

Abstract: For partial volume correction, the partial volume effect is simulated using patient-specific segmentation. An organ or other object of the patient is segmented using anatomical imaging. For simulation, the locations of the patient-specific object or objects are sub-divided, creating artificial boundaries in the object. A test activity is assigned to each sub-division and forward projected. The difference of the forward projected activity to the test activity provides a location-by-location partial volume correction map. This correction map is used in reconstruction from the measured emissions, resulting in more accurate activity estimation with less partial volume effect.

Abstract: For partial volume correction, the partial volume effect is simulated using patient-specific segmentation. An organ or other object of the patient is segmented using anatomical imaging. For simulation, the locations of the patient-specific object or objects are sub-divided, creating artificial boundaries in the object. A test activity is assigned to each sub-division and forward projected. The difference of the forward projected activity to the test activity provides a location-by-location partial volume correction map. This correction map is used in reconstruction from the measured emissions, resulting in more accurate activity estimation with less partial volume effect.

Abstract: A system and method include training of an artificial neural network to generate a simulated attenuation-corrected reconstructed volume from an input non-attenuation-corrected reconstructed volume, the training based on a plurality of non-attenuation-corrected volumes generated from respective ones of a plurality of sets of two-dimensional emission data and on a plurality of attenuation-corrected reconstructed volumes generated from respective ones of the plurality of sets of two-dimensional emission data.

Abstract: A system and method includes input of a plurality of sets of training data to a neural network to generate a plurality of sets of output data, determination of a first loss based on the plurality of sets of output data and on the plurality of sets of ground truth data, determination if a second loss based on the plurality of sets of output data and one or more physics-based constraints, and modification of the neural network based on the first loss and the second loss.

Abstract: Systems and methods for imaging. An external device may be used to acquire optical image data of a subject. One or more physical parameters of the subject may be determined based on the optical image data. The one or more physical parameters may be translated to one or more properties of the subject. The one or more properties may then be used to generate medical image data of the subject.

Abstract: For denoising in SPECT, such as qSPECT, machine learning is used to relate settings to noise structure. Given the SPECT imaging arrangement for a patient, the machine-learned model estimates the structure of the noise. This noise structure may be used to denoise the reconstructed representation.

Abstract: A detector used for tomography imaging is mobile, allowing the detector to move about an object (e.g., patient to be imaged). A swarm of such detectors, such as a swarm of drones with detectors, may be used for tomography imaging. The trajectory or trajectories of the mobile detectors may account for the pose and/or movement of the object being imaged. The trajectory or trajectories may be based, in part, on the sampling for desired tomography. An image of an internal region of the object is reconstructed from detected signals of the mobile detectors using tomography.

Abstract: For controlling reconstruction in emission tomography, the quality of data for detected emissions and/or the application controls the settings used in reconstruction. For example, a count density of the detected emissions is used to control the number of iterations in reconstruction to more likely avoid over and under fitting. The count density may be adaptively determined by re-binning through pixel size adjustment to find a smallest pixel size providing a sufficient count density. As another example, the detected data may have poor quality due to motion or high body mass index (BMI) of the patient, so the reconstruction is set to perform differently (e.g., less smoothing for high motion or a different number of iterations for high BMI). The quality of the data may be used in conjunction with the application or task for imaging the patient to control the reconstruction.