Siemens Medical Solutions Usa, Inc.

Vijay Shah

Vladimir Y Panin

Jicun Hu

Michael E Casey

Sven Zuehlsdorff

Frank Kehren

Bernard Bendriem

William Curtis Howe

Anne M Smith

Matthew Baker

Bruce S Spottiswoode

Fei Gao

A system and method include identification of a blood pool region of the body based on the acquired positron emission tomography data, determination of activity in the blood pool region associated with a first time based on the acquired positron emission tomography data, determination of a scale factor based on the determined activity in the blood pool region and on an input function associated with one or more other human bodies, determination of activity in a tissue region associated with a second time based on the acquired positron emission tomography data, determination of a specific uptake ratio associated with the second time based on the activity in the tissue region, the scale factor and a value of the input function at the second time, determination of an estimate of metabolic rate in the tissue region based on the specific uptake ratio and the input function, and determination of a diagnosis associated with the tissue region based on the estimate of metabolic rate.

Determination of metabolic rate from static pet scan

Methods and systems of revising image models for nuclear imaging are disclosed. A system receives first patient scan data corresponding to one or more nuclear imaging scans performed on one or more individuals and generates a first reconstructed image by applying a first image model to the first patient scan data. Feedback is received regarding the first reconstructed image and the feedback is provided as an input to a deep-reinforcement learning process. The deep-reinforcement learning process is configured to generate at least one modification for the first image model based on the feedback regarding the first reconstructed image. A second image model is generated by applying the at least one modification generated by the deep-reinforcement learning process to the first image model.

Deep reinforcement learning for computer assisted reading and analysis

A framework for multi-scan image processing. A single real anatomic image of a region of interest is first acquired. One or more emission images of the region of interest are also acquired. One or more synthetic anatomic images may be generated based on the one or more emission images. One or more deformable registrations of the real anatomic image to the one or more synthetic anatomic images are performed to generate one or more registered anatomic images. Attenuation correction may then be performed on the one or more emission images using the one or more registered anatomic images to generate one or more attenuation corrected emission images.

Multi-scan image processing

A system and method include acquisition of positron emission tomography data of an object while a radiation source moves within the object, determination of a plurality of locations within the object, each of the plurality of locations associated with a respective time at which the radiation source was located at the location, determination of a respective time period associated with each of the plurality of locations, determination, for each of the determined time periods, of a frame of the positron emission tomography data associated with the determined time period, and, for each frame of the positron emission tomography data, generation of an image based on the frame and on the location associated with the time period associated with the frame.

Radiolabeled cell tracking and imaging

A method of conducting a multi-pass dynamic positron emission tomography (PET) scans using continuous bed motion (CBM) mode is disclosed where the method involves acquiring PET sinogram data using CBM mode as the patient bed is moving in a first direction; acquiring PET sonogram data using CBM mode as the patient bed is moving in a second direction that is opposite from the first direction; and reconstructing 3-D PET image from the acquired PET sonogram data.

System and method for whole body continuous bed motion PET scanning with bi-directional data acquisition modes

A method for reconstructing medical images comprises: identifying a plurality of organs in a body of a subject based on an anatomic image; assigning a plurality of voxels in the body to respective ones of the plurality of organs based on the anatomic image; and reconstructing activity images of the body using respectively different processing for the voxels assigned to each respective one of the plurality of organs.

Activity image reconstruction using anatomy data

A method of processing and reconstructing dynamic positron emission tomography (PET) sinogram data comprises: acquiring PET sinogram data using continuous bed motion having a varying velocity; recording a plurality of position-time coordinate pairs while acquiring the PET sinogram data; determining respective acquisition times of each of a plurality of slices of the image, based on the plurality of position-time coordinates; and reconstructing respective parametric images for each respective slice in the plurality of slices.

Growing community of inventors

Knoxville, TN, United States of America

Vijay Shah