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: Parameterized model reconstruction is used for internal dose tomography. The parameterized model, solved for within the reconstruction, models the dose level and may account for diffusion, isotope half-life, and/or biological half-life. Using the detected emissions from different scans (e.g., from different scan sessions in a given cycle) as input for the one reconstruction, the parameterized model reconstruction determines the biodistribution of dose at any time.

Abstract: A framework for characterization of a collimator. In accordance with one aspect, first and second sides of the collimator are photographed to generate first and second image data. An optical characterization map (OCM) may be generated based on the first and second image data, wherein the optical characterization map characterizes the individual channels of the collimator. Quality assessment or image reconstruction may then be performed based on the OCM.

Abstract: A system and method include training of an artificial neural network to generate an output data set, the training based on the plurality of sets of emission data acquired using a first imaging modality and respective ones of data sets acquired using a second imaging modality.

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: An emission image is generated from poor quality emission data. A machine-learned model may be used to recover information. Emission imaging may be provided due to the recovery in a way that at least some diagnostically useful information is made available despite corruption that would otherwise result in less diagnostically useful information or no image at all.

Abstract: A system includes a scanner configured to generate scan data of a patient volume or area, a processor configured to implement control operations, the control operations being directed to acquisition of the scan data or to processing of the scan data, and a monitoring system including a range imaging camera positioned for a field of view such that the monitoring system is configured to capture spatial data indicative of movement of an object spaced from the scanner. The processor is configured to implement an adjustment in the control operations based on the spatial data.

Abstract: In nuclear medical imaging, respiratory motion is corrected. Rather than pairwise estimation of motion from projection views, a sequence-based technique is used to jointly estimate parameters for a motion model across many projection views. In one approach, this sequence-based method is iteratively solved with a maximum likelihood objective function incorporating the motion model. A surrogate respiration signal is used to gate for the joint estimation and used to convert gated motion parameters to temporal motion parameters.

Abstract: Single photon emission computed tomography (SPECT) is performed with multiple emission energies. For quantitative or qualitative SPECT, the image formation process for emissions at different energy ranges is modeled (44, 46, 48, 50) separately. Different scatter, different attenuation, and/or different collimator-detector response models corresponding to different energy ranges are used in the reconstruction.

Abstract: For a multi-modal emission tomography system, an improved control system increases the likelihood of optimal image quality, satisfaction of physician goals, and/or avoids repetition in scanning and the corresponding increase in dose burden. The control system is divided into two or more arrangements. One arrangement receives goal information and outputs reconstruction settings and generic scan settings to satisfy the goal information. Another arrangement converts the generic scan settings to emission tomography system-specific scan settings, which are used to detect emissions. The separation of the arrangements allows independent operation so that different system-specific conversions may be used for different systems.

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: 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 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 includes acquisition of a plurality of non-attenuation-corrected volumes, each of the non-attenuation-corrected volumes based on a respective one of a plurality of sets of two-dimensional emission data, acquisition of a plurality of attenuation coefficient maps, each of the plurality of attenuation coefficient maps corresponding to a respective one of the plurality of sets of two-dimensional emission data, training of a convolutional network to generate a generated attenuation coefficient map from an input image volume, the training based on the plurality of non-attenuation-corrected volumes and respective ones of the plurality of attenuation coefficient maps, and output of trained kernels of the trained convolutional network to an emission imaging system.

Abstract: In nuclear medical imaging, respiratory motion is corrected. Rather than pairwise estimation of motion from projection views, a sequence-based technique is used to jointly estimate parameters for a motion model across many projection views. In one approach, this sequence-based method is iteratively solved with a maximum likelihood objective function incorporating the motion model. A surrogate respiration signal is used to gate for the joint estimation and used to convert gated motion parameters to temporal motion parameters.

Abstract: For a multi-modal emission tomography system, an improved control system increases the likelihood of optimal image quality, satisfaction of physician goals, and/or avoids repetition in scanning and the corresponding increase in dose burden. The control system is divided into two or more arrangements. One arrangement receives goal information and outputs reconstruction settings and generic scan settings to satisfy the goal information. Another arrangement converts the generic scan settings to emission tomography system-specific scan settings, which are used to detect emissions. The separation of the arrangements allows independent operation so that different system-specific conversions may be used for different systems.

Abstract: In nuclear medical imaging, respiratory motion is corrected. Rather than pairwise estimation of motion from projection views, a sequence-based technique is used to jointly estimate parameters for a motion model across many projection views. In one approach, this sequence-based method is iteratively solved with a maximum likelihood objective function incorporating the motion model. A surrogate respiration signal is used to gate for the joint estimation and used to convert gated motion parameters to temporal motion parameters.

Abstract: In SPECT reconstruction, multi-modal reconstruction is combined with model-based multi-energy image formation. The scatter modeling of the model-based image formation uses resampling to facilitate convolution with the scatter kernels while maintaining resolution for the multi-energy projection. This combination of multi-modal and model-based multi-energy image formation simultaneously addresses the inaccuracy of the image formation process for complicated energy spectra and image blurring due to degradation of resolution. Varying the reconstruction by iteration may provide some of the benefits while reducing computational burden.

Abstract: A system and method include acquisition of a set of tomographic images of a patient volume associated with each of a plurality of timepoints of a first radiopharmaceutical therapy cycle, determination, for each of the plurality of timepoints, of a systematic uncertainty for each of a plurality of regions within the patient volume based on the set of tomographic images associated with the timepoint, determination, for each of the plurality of timepoints, of a quantitative statistical uncertainty based on the set of tomographic images associated with the timepoint, determination of a dose and a dose uncertainty for each of the plurality of regions based on the set of tomographic images, the systematic uncertainty and the quantitative statistical uncertainty for each of the plurality of timepoints, and display of a cumulative dose and cumulative dose uncertainty for each of the plurality of regions based on the dose and the dose uncertainty determined for each of the plurality of regions.