Siemens Medical Solutions Usa, Inc.

Michal Cachovan

Alexander Hans Vija

Miesher Rodrigues

Xinhong Ding

Jun Ma

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.

Partial volume correction in multi-modality emission tomography

A system and method include training of an artificial neural network to generate an output three-dimensional image volume based on input two-dimensional projection images, the training based on a plurality of subsets of two-dimensional projection images of each of a plurality of sets of two-dimensional projection images and associated ones of three-dimensional image volumes reconstructed from each of the plurality of sets of two-dimensional projection images.

Network determination of limited-angle reconstruction

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.

Mobile tomography imaging

For calibration of internal dose in nuclear imaging, the dose model used for estimating internal dose in a patient is calibrated. One or more values of the dose model (e.g., a physics simulation, dose kernels, or a transport model) are set based on measured dose. The dose may be measured relative to specific tissues and/or isotopes, providing for tracer and tissue specific calibration. For example, dose from the tracer to be injected into the patient is estimated from emissions as well as measured by a dosimeter in a tissue mimicking tissue mimicking object. These doses are used to calibrate the dose model, which calibrated dose model is then used to determine internal dose for the patient.

Calibration of radiation dose estimation in medical nuclear imaging

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.

Multi-modal reconstruction network

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.

Internal dose tomography

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.

Deep learning-based denoising in quantitative single photon emission computed tomography

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.

Deep learning-based data rescue in emission tomography medical imaging

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.

Multi-cycle dosimetry and dose uncertainty estimation

A set of first modality data is provided to an intra-reconstruction motion correction method. The set of first modality data includes a plurality of views. A set of second modality data is provided to the method. A motion estimate is generated for each of the plurality of views in the set of first modality data by registering the set of first modality data with the set of second modality data. A motion corrected model of the set of first modality data is generated by a forward projection including the motion estimate.

Intra reconstruction motion correction

A set of set of first modality data is received including at least one view comprising a plurality of gates. The set of first modality data is received from a first imaging modality of an imaging system. A set of second modality data is received from a second imaging modality of the imaging system. A motion corrected model of the set of first modality data is generated by forward projecting the set of first modality data including a motion estimate. An update factor for each of the plurality of views is generated by comparing at least one of the plurality of gates to the motion corrected model. The motion corrected model is updated by the update factor to generate a motion corrected image.

One gate reconstruction

A method of clinical collaboration between a clinical site and an analysis site includes receiving scan data from a scanner via a first reconstruction computer system at the clinical site, implementing a reconstruction procedure on the received scan data using a second reconstruction computer system at the analysis site and configured in accordance with a reconstruction configuration parameter, the analysis site being remote from the clinical site, and transmitting data indicative of the reconstruction configuration parameter to the first reconstruction computer system to configure the first reconstruction computer system in accordance with the reconstruction configuration parameter.

Growing community of inventors

Baiersdorf, Germany

Michal Cachovan