Abstract: Systems, apparatus, methods, and computer-readable storage media to estimate scatter in an image are disclosed. An example apparatus includes a network generator to generate and train an inception neural network using first and second input to deploy an inception neural network model to process image data when first and second outputs of the inception neural network converge, the first input based on a raw sinogram of a first image and the second input based on an attenuation-corrected sinogram of the first image, the inception neural network including a first filter of a first size and a second filter of a second size in a layer to process the first input and/or the second input to generate an estimate of scatter in the first image. The example apparatus also includes an image processor to apply the estimate of scatter to a second image to generate a processed image.

Abstract: Systems, apparatus, methods, and computer-readable storage media to estimate scatter in an image are disclosed. An example apparatus includes a network generator to generate and train an inception neural network using first and second input to deploy an inception neural network model to process image data when first and second outputs of the inception neural network converge, the first input based on a raw sinogram of a first image and the second input based on an attenuation-corrected sinogram of the first image, the inception neural network including a first filter of a first size and a second filter of a second size in a layer to process the first input and/or the second input to generate an estimate of scatter in the first image. The example apparatus also includes an image processor to apply the estimate of scatter to a second image to generate a processed image.

Abstract: A method is provided that includes acquiring, with a non-emission imaging acquisition unit, non-emission modality imaging information of an object. The method also includes acquiring, with an emission imaging acquisition unit, emission modality imaging information of the object. Also, the method includes selecting at least one portion of the emission modality imaging information for motion assessment and/or correction based on the non-emission modality imaging information and a clinical task. Further, the method includes performing motion correction on the emission modality imaging information based on the selected at least one portion of the data to provide motion-aware emission modality imaging information, and reconstructing an image using the motion-aware emission modality imaging information.

Abstract: Methods and systems are provided for analyzing a respiratory motion waveform acquired during acquiring imaging data with a molecular imaging device. In one embodiment, a method comprises acquiring imaging data with a molecular imaging apparatus, analyzing a respiratory motion waveform acquired during the acquiring imaging data, and applying gating to the acquired imaging data based on the analyzed respiratory motion waveform. In this way, gating may be applied to the acquired imaging data in order to generate an image for medical diagnosis with increased image quality and accuracy.

Abstract: Methods and systems for processing a set of images are described. In accordance with this disclosure, images are registered and an analysis is performed in view of one or more constraints (such as constraints based upon anatomical or physiological considerations). Weighting factors are determined based on the analysis. The weighting factors are used in subsequent processing of the registered (and/or unregistered) images and/or to formulate a visualization that conveys the degree of confidence in the motion estimation used in the registration process.

Abstract: Methods and systems are provided for analyzing a respiratory motion waveform acquired during acquiring imaging data with a molecular imaging device. In one embodiment, a method comprises acquiring imaging data with a molecular imaging apparatus, analyzing a respiratory motion waveform acquired during the acquiring imaging data, and applying gating to the acquired imaging data based on the analyzed respiratory motion waveform. In this way, gating may be applied to the acquired imaging data in order to generate an image for medical diagnosis with increased image quality and accuracy.

Abstract: A method is provided that includes acquiring, with a detector defining a field of view (FOV), emission imaging data of an object over the FOV. The method also includes determining, with one or more processing units, a volume of interest (VOI) of the emission imaging data, wherein the VOI defines a volume smaller than an imaged volume of the object. Further, the method includes performing, with the one or more processing units, a multivariate data analysis on the VOI to generate a waveform for the VOI. Also, the method includes determining, with the one or more processing units, an amount of motion for at least the VOI based on the waveform. The method further includes displaying, on a display unit, at least one of the amount of motion or an image reconstructed based on the emission imaging data.

Abstract: Emission event data of an object of interest is acquired with a detector comprising a plurality of rings defining corresponding slices. Also, an amount of motion for each of a plurality of segments is determined with one or more processing units, wherein each segment corresponds to less than an axial field of view (AFOV) of the detector. Further, motion mitigation is performed for segments for which the amount of motion satisfies a threshold to provide motion mitigated data, and not performed for segments for which the amount of motion does not satisfy the threshold to provide non-mitigated data. An image is reconstructed using the motion mitigated data and the non-mitigated data, and the image is displayed on a display.

Abstract: A method for producing an attenuation-corrected time-gated PET image comprising includes obtaining a baseline MR image and a cine MR image of a structure; registering the baseline MR image to the cine MR image to create an image transform; and generating a corresponding cine ACF matrix using the image transform, and time-correlating the ACF matrix to a time-gated PET data set to produce an attenuation-corrected time-gated PET image.

Abstract: A method is provided that includes acquiring, with a detector comprising a plurality of rings defining corresponding slices, emission event data of an object of interest. The method also includes determining, with one or more processing units, an amount of motion for each of a plurality of segments, wherein each segment corresponds to less than an axial field of view (AFOV) of the detector. Further, the method includes performing, with the one or more processing units, motion mitigation for segments for which the amount of motion satisfies a threshold to provide motion mitigated data, and not performing motion mitigation for segments for which the amount of motion does not satisfy the threshold to provide non-mitigated data. Also, the method includes reconstructing an image using the motion mitigated data and the non-mitigated data. The method also includes displaying the image on a display.

Abstract: A method is provided that includes acquiring, with a detector defining a field of view (FOV), emission imaging data of an object over the FOV. The method also includes determining, with one or more processing units, a volume of interest (VOI) of the emission imaging data, wherein the VOI defines a volume smaller than an imaged volume of the object. Further, the method includes performing, with the one or more processing units, a multivariate data analysis on the VOI to generate a waveform for the VOI. Also, the method includes determining, with the one or more processing units, an amount of motion for at least the VOI based on the waveform. The method further includes displaying, on a display unit, at least one of the amount of motion or an image reconstructed based on the emission imaging data.

Abstract: A method and system for displaying a physiologic waveform. The method and system acquire positron emission tomography (PET) coincidence event data of an object of interest. The method and system further select a subset of the PET coincidence event data corresponding to a time window and apply a multivariate data analysis technique to the subset of the PET coincidence event data. The method and system also generate a physiologic waveform based on the multivariate data analysis, and display the physiologic waveform on a display.

Abstract: A method for correcting an emission tomography image includes obtaining a first modality image dataset, identifying areas in the first modality dataset that may be impacted by respiratory motion, and applying joint estimation attenuation correction techniques to improve emission image data. A medical imaging system is also described herein. Emission tomography may include positron emission tomography (PET) and single photon emission computed tomography (SPECT).

Abstract: A method for producing an attenuation-corrected time-gated PET image comprising includes obtaining a baseline MR image and a cine MR image of a structure; registering the baseline MR image to the cine MR image to create an image transform; and generating a corresponding cine ACF matrix using the image transform, and time-correlating the ACF matrix to a time-gated PET data set to produce an attenuation-corrected time-gated PET image.

Abstract: Methods and systems for processing a set of images are described. In accordance with this disclosure, images are registered and an analysis is performed in view of one or more constraints (such as constraints based upon anatomical or physiological considerations). Weighting factors are determined based on the analysis. The weighting factors are used in subsequent processing of the registered (and/or unregistered) images and/or to formulate a visualization that conveys the degree of confidence in the motion estimation used in the registration process.

Abstract: A method for attenuation correction of a plurality of time-gated PET images of a moving structure includes establishing an ACF matrix, based on a baseline MR image of the structure; developing a plurality of image transforms, each of the image transforms registering the baseline MR image to a respective cine MR image of the moving structure; applying each of the image transforms to the ACF matrix to generate a corresponding cine ACF matrix; time-correlating each of the cine MR images, and its corresponding cine ACF matrix, to one of the plurality of time-gated PET data sets; and producing from each of the time-gated PET data sets an attenuation-corrected time-gated PET image.

Abstract: Methods and systems for processing a set of images are described. In accordance with this disclosure, images are registered and an analysis is performed in view of one or more constraints (such as constraints based upon anatomical or physiological considerations). Weighting factors are determined based on the analysis. The weighting factors are used in subsequent processing of the registered (and/or unregistered) images and/or to formulate a visualization that conveys the degree of confidence in the motion estimation used in the registration process.

Abstract: A method for selecting data to reconstruct a three-dimensional (3D) image of a subject of interest includes acquiring a 3D emission dataset of the subject of interest, acquiring a respiratory signal of the subject of interest, the respiratory signal including a plurality of respiratory cycles, and calculating a respiratory profile using the respiratory signal. The method further includes, for each respiratory cycle, generating a gating window, calculating a minimum total squared difference (TSD) between a plurality of phases in the respiratory profile and the same plurality of phases in the respiratory cycle, and positioning the gating window based on the TSD values calculated, and reconstructing a 3D image using only the emission data within the plurality of gated windows. A system and non-transitory computer readable medium are also described herein.

Abstract: A method for attenuation correction of a plurality of time-gated PET images of a moving structure includes establishing an ACF matrix, based on a baseline MR image of the structure; developing a plurality of image transforms, each of the image transforms registering the baseline MR image to a respective cine MR image of the moving structure; applying each of the image transforms to the ACF matrix to generate a corresponding cine ACF matrix; time-correlating each of the cine MR images, and its corresponding cine ACF matrix, to one of the plurality of time-gated PET data sets; and producing from each of the time-gated PET data sets an attenuation-corrected time-gated PET image.

Abstract: A target object for aligning a multi-modality imaging system includes a body having a cavity therein, a first imaging source being disposed within the cavity, the first imaging source including a body having a cavity defined therein and an emission responsive material disposed within the first imaging source cavity, the first imaging source having a first shape, and a second imaging source being disposed within the cavity, the second imaging source including a body having a cavity defined therein and a magnetic resonance responsive material disposed within the second imaging source cavity, the second imaging source having a second shape that is different than the first shape. A method of aligning a multi-modality imaging system is also provided.