Abstract: Systems and techniques that facilitate extension of existing neural networks without affecting existing outputs are provided. In various embodiments, a receiver component can access a neural network, wherein the neural network includes a first set of layers trained to perform a first computing task. In various instances, an extension component can insert a second set of layers into the neural network, wherein the second set of layers receive as input latent activations from the first set of layers. In various aspects, a training component can train, without changing the first set of layers, the second set of layers to perform a second computing task that is different from the first computing task.

Abstract: Techniques are described for generating mono-modality training image data from multi-modality image data and using the mono-modality training image data to train and develop mono-modality image inferencing models. A method embodiment comprises generating, by a system comprising a processor, a synthetic 2D image from a 3D image of a first capture modality, wherein the synthetic 2D image corresponds to a 2D version of the 3D image in a second capture modality, and wherein the 3D image and the synthetic 2D image depict a same anatomical region of a same patient. The method further comprises transferring, by the system, ground truth data for the 3D image to the synthetic 2D image. In some embodiments, the method further comprises employing the synthetic 2D image to facilitate transfer of the ground truth data to a native 2D image captured of the same anatomical region of the same patient using the second capture modality.

Abstract: Techniques are described for generating mono-modality training image data from multi-modality image data and using the mono-modality training image data to train and develop mono-modality image inferencing models. A method embodiment comprises generating, by a system comprising a processor, a synthetic 2D image from a 3D image of a first capture modality, wherein the synthetic 2D image corresponds to a 2D version of the 3D image in a second capture modality, and wherein the 3D image and the synthetic 2D image depict a same anatomical region of a same patient. The method further comprises transferring, by the system, ground truth data for the 3D image to the synthetic 2D image. In some embodiments, the method further comprises employing the synthetic 2D image to facilitate transfer of the ground truth data to a native 2D image captured of the same anatomical region of the same patient using the second capture modality.

Abstract: Methods and systems are provided for inferring thickness and volume of one or more object classes of interest in two-dimensional (2D) medical images, using deep neural networks. In an exemplary embodiment, a thickness of an object class of interest may be inferred by acquiring a 2D medical image, extracting features from the 2D medical image, mapping the features to a segmentation mask for an object class of interest using a first convolutional neural network (CNN), mapping the features to a thickness mask for the object class of interest using a second CNN, wherein the thickness mask indicates a thickness of the object class of interest at each pixel of a plurality of pixels of the 2D medical image; and determining a volume of the object class of interest based on the thickness mask and the segmentation mask.

Abstract: Methods and systems are provided for generating ultrasound probe motion recommendations. In one example, a method includes obtaining an ultrasound image of a source scan plane, the ultrasound image acquired with an ultrasound probe at a first location relative to a patient, entering the ultrasound image as input to a probe recommendation model trained to output a set of recommendations to move the ultrasound probe from the first location to a plurality of additional locations at which a plurality of target scan planes can be imaged, and displaying the set of recommendations on a display device.

Abstract: Systems, computer-implemented methods, and computer program products that facilitate temporalizing and/or spatializing a machine learning and/or artificial intelligence network are provided. In various embodiments, a processor can combine output data from different layers of an artificial neural network trained on static image data. In various embodiments, the processor can employ the artificial neural network to infer an outcome from an image instance in a sequence of images based on combined output data from the different layers of the artificial neural network.

Abstract: Methods and systems are provided for generating user guidance for ultrasound imaging. In one example, a method includes determining, with a probe recommendation model, a user action to an ultrasound probe prior to and/or during acquisition of a current ultrasound image frame, one or more anatomical features in the current ultrasound image frame, and an anatomy view of the current ultrasound image frame, and outputting, for display on a display device, a probe motion recommendation based on the user action, the one or more anatomical features, and the anatomy view.

Abstract: A magneto-optic imaging apparatus adapted for use with an imaging device, such as a smartphone, tablet computer, or borescope, for visually detecting defects in the surface or subsurface of a component using a magneto-optic effect. The magneto-optic imaging apparatus includes a housing with an interface for connection with the imaging device such that a camera and light source of the imaging device may be implemented for magneto-optic visualization. The housing includes optical elements including one or more filters, a polarizer, a magneto-optic or garnet film, and an analyzer. The housing also includes a flexible coil or electrical terminals for inducing a magnetic field in the component. The magneto-optic imaging apparatus may include a translucent or transparent body of conformable material or materials to conform the magneto-optic film and flexible coil to a non-planar surface of the component.

Abstract: Systems, machine-readable media, and methods for ultrasound imaging can include acquiring three-dimensional data for one or more patient data sets and generating a three-dimensional environment based on one or more transition areas identified between a plurality of volumes of the three-dimensional data. A method can also include generating a set of probe guidance instructions based at least in part on the one or more transition areas and the plurality of volumes of the three-dimensional data, and acquiring, using an ultrasound probe, a first frame of two-dimensional data for a patient. The method can also include executing the set of probe guidance instructions to provide probe feedback for acquiring at least a second frame of two-dimensional data.

Abstract: Systems, methods and computer program products are provided to collect ultrasound (US) data. A processor is configured to acquire the US data along one or more acquisition scan planes. The US data defines a plurality of image frames that have a first image quality. The processor is further configured to apply a generative model to at least one of the US data or plurality of image frames to generate a synthetic scan plane image along a synthetic scan plane. The generative model is defined based on one or more training ultrasound data sets. The synthetic scan plane image has an image quality that is common with the first image quality of the plurality of image frames. The system further comprises a display configured to display the synthetic scan plane image.

Abstract: Methods and systems are provided for inferring thickness and volume of one or more object classes of interest in two-dimensional (2D) medical images, using deep neural networks. In an exemplary embodiment, a thickness of an object class of interest may be inferred by acquiring a 2D medical image, extracting features from the 2D medical image, mapping the features to a segmentation mask for an object class of interest using a first convolutional neural network (CNN), mapping the features to a thickness mask for the object class of interest using a second CNN, wherein the thickness mask indicates a thickness of the object class of interest at each pixel of a plurality of pixels of the 2D medical image; and determining a volume of the object class of interest based on the thickness mask and the segmentation mask.

Abstract: The current disclosure provides systems and methods for providing guidance information to an operator of a medical imaging device. In an embodiment, a method is provided, comprising training a deep learning neural network on training pairs including a first medical image of an anatomical neighborhood and a second medical image of the anatomical neighborhood as input data, and a ground truth displacement between a first scan plane of the first medical image and a second scan plane of the second medical image as target data; using the neural network to predict a displacement between a first scan plane of a new medical image of the anatomical neighborhood and a target scan plane of a reference medical image of the anatomical neighborhood; and displaying guidance information for an imaging device used to acquire the new medical image on a display screen.

Abstract: A system and method for automatically adjusting beamformer parameters based on ultrasound image analysis to enhance ultrasound image acquisition is provided. The method includes acquiring, by an ultrasound system, an ultrasound image. The method includes segmenting, by at least one processor, the ultrasound image to identify anatomical structure(s) and/or image artifact(s) in the ultrasound image. The method includes detecting, by the at least one processor, a location of each of the identified anatomical structure(s) and/or image artifact(s). The method includes automatically adjusting, by the at least one processor, at least one beamformer parameter based on the detected location of one or more of the identified anatomical structure(s) and/or the image artifact(s). The method includes acquiring, by the ultrasound system, an enhanced ultrasound image based on the automatically adjusted at least one beamformer parameter. The method includes presenting, at a display system, the enhanced ultrasound image.

Abstract: A magneto-optic imaging apparatus adapted for use with an imaging device, such as a smartphone, tablet computer, or borescope, for visually detecting defects in the surface or subsurface of a component using a magneto-optic effect. The magneto-optic imaging apparatus includes a housing with an interface for connection with the imaging device such that a camera and light source of the imaging device may be implemented for magneto-optic visualization. The housing includes optical elements including one or more filters, a polarizer, a magneto-optic or garnet film, and an analyzer. The housing also includes a flexible coil or electrical terminals for inducing a magnetic field in the component. The magneto-optic imaging apparatus may include a translucent or transparent body of conformable material or materials to conform the magneto-optic film and flexible coil to a non-planar surface of the component.

Abstract: Systems and methods for guided lung coverage and automated detection using ultrasound devices are disclosed. The method for guided coverage and automated detection of pathologies of a subject includes positioning an ultrasound probe on a region of the subject body to be imaged. The method includes capturing a video of the subject and processing the video to generate a torso image of the subject and identify location of the ultrasound probe on the subject body. The method includes registering the video to an anatomical atlas to generate a mask of the region of the subject body comprising a plurality of sub-regions of the subject body to be imaged and superimposing the mask over the torso image. The method further includes displaying an indicator corresponding to a location of the each of the plurality of the sub-regions on the torso image.

Abstract: Systems and methods for automatically tracking a minimal hiatal dimension plane of an ultrasound volume in real-time during a pelvic floor examination are provided. The method includes acquiring an ultrasound volume of an anatomical region over a time period. The method includes extracting an A-plane from the ultrasound volume and displaying the A-plane. The method includes receiving an OmniView (OV) line overlaid on the A-plane. The method includes rendering an OV-plane based on a position and trajectory of the OV-line and displaying the OV-plane. The method includes automatically identifying key points in regions of interest in the A-plane. The method includes automatically tracking the key points in the regions of interest in the A-plane over the time period to automatically adjust the position and trajectory of the OV-line, the rendering the OV-plane automatically updating over the time period based on adjustments of the position and trajectory of the OV-line.

Abstract: Methods and systems are provided for inferring thickness and volume of one or more object classes of interest in two-dimensional (2D) medical images, using deep neural networks. In an exemplary embodiment, a thickness of an object class of interest may be inferred by acquiring a 2D medical image, extracting features from the 2D medical image, mapping the features to a segmentation mask for an object class of interest using a first convolutional neural network (CNN), mapping the features to a thickness mask for the object class of interest using a second CNN, wherein the thickness mask indicates a thickness of the object class of interest at each pixel of a plurality of pixels of the 2D medical image; and determining a volume of the object class of interest based on the thickness mask and the segmentation mask.

Abstract: Various methods and systems are provided for individually analyzing a plurality of subregions within an ultrasound image for acoustic shadowing. In one embodiment, a method includes acquiring ultrasound data along a plurality of receive lines, generating an ultrasound image based on the ultrasound data, dividing the ultrasound image into a plurality of subregions, and individually analyzing each of the plurality of subregions for acoustic shadowing. The method includes detecting acoustic shadowing in one or more of the plurality of subregions, displaying the ultrasound image, and graphically indicating the one or more of the plurality of subregions in which the acoustic shadowing was detected on the ultrasound image while the ultrasound image is displayed on a display device.

Abstract: Techniques are described for generating mono-modality training image data from multi-modality image data and using the mono-modality training image data to train and develop mono-modality image inferencing models. A method embodiment comprises generating, by a system comprising a processor, a synthetic 2D image from a 3D image of a first capture modality, wherein the synthetic 2D image corresponds to a 2D version of the 3D image in a second capture modality, and wherein the 3D image and the synthetic 2D image depict a same anatomical region of a same patient. The method further comprises transferring, by the system, ground truth data for the 3D image to the synthetic 2D image. In some embodiments, the method further comprises employing the synthetic 2D image to facilitate transfer of the ground truth data to a native 2D image captured of the same anatomical region of the same patient using the second capture modality.

Abstract: Methods and systems are provided for an automated ultrasound exam. In one example, a method includes identifying a view plane of interest based on one or more 3D ultrasound images, obtaining a view plane image including the view plane of interest from a 3D volume of ultrasound data of a patient, where the one or more 3D ultrasound images are generated from the 3D volume of ultrasound data, segmenting an anatomical region of interest (ROI) within the view plane image to generate a contour of the anatomical ROI, and displaying the contour on the view plane image.