Abstract: Techniques are described for computer-implemented techniques for managing various aspects of the cardiac care pathway using machine learning. According to an embodiment, a method can include training an outcomes forecasting model to predict patient outcomes resulting from undergoing a cardiac valve procedure using multi-modal training data for a plurality of different patients, wherein the training comprising separately training different machine learning sub-models of the forecasting model to predict preliminary patient outcome data and mapping the preliminary patient outcome data to the patient outcomes, resulting in a trained version of the outcome forecasting model. The method further includes applying the trained version of the outcomes forecasting model to new multi-modal data for a new patient to predict the patient outcomes for the new patient resulting from undergoing the cardiac value procedure.

Abstract: Various methods and systems are provided for a medical imaging system. In one embodiment, a method comprises acquiring medical imaging data while executing a first imaging protocol, detecting a potential abnormality by evaluating the acquired medical imaging data with an artificial intelligence system, and outputting a first notification regarding the potential abnormality to a display, the first notification including an option to accept the first notification and an option to reject the first notification. In this way, an operator of an ultrasound imaging system may be alerted to a patient abnormality during a scan, thereby enabling the operator to further evaluate the potential abnormality without distracting the operator from controlling the medical imaging system.

Abstract: Various methods and systems are provided for bicuspid valve detection with ultrasound imaging. In one embodiment, a method comprises acquiring ultrasound video of a heart over at least one cardiac cycle, identifying frames in the ultrasound video corresponding to at least one cardiac phase, and classifying a cardiac structure in the identified frames as a bicuspid valve or a tricuspid valve. A generative model such as a variational autoencoder trained on ultrasound image frames at the at least one cardiac phase may be used to classify the cardiac structure. In this way, relatively rare occurrences of bicuspid aortic valves may be automatically detected during regular cardiac ultrasound screenings.

Abstract: A method and ultrasound imaging system for detecting a coherent reflector includes acquiring ultrasound channel data from a volume with a probe, calculating a transform function from the ultrasound channel data, identifying a first angle of a projection of the coherent reflector in a plane parallel to the 2D aperture based on the transform function, detecting a line-shaped echo pattern in the ultrasound channel data, and determining a second angle of the coherent reflector with respect to the 2D aperture based on the position of the line-shaped echo pattern. The method and system includes determining a position and orientation of the coherent reflector based on the first angle and the second angle, enhancing a representation of the coherent reflector in an image generated based on the ultrasound channel data, and displaying the image on a display device after enhancing the representation of the coherent reflector.

Abstract: Various methods and systems are provided for bicuspid valve detection with ultrasound imaging. In one embodiment, a method comprises acquiring ultrasound video of a heart over at least one cardiac cycle, identifying frames in the ultrasound video corresponding to at least one cardiac phase, and classifying a cardiac structure in the identified frames as a bicuspid valve or a tricuspid valve. A generative model such as a variational autoencoder trained on ultrasound image frames at the at least one cardiac phase may be used to classify the cardiac structure. In this way, relatively rare occurrences of bicuspid aortic valves may be automatically detected during regular cardiac ultrasound screenings.

Abstract: Example apparatus, systems, and methods for image data processing are disclosed and described. An example system includes an image capturer to facilitate capture of an image. The example system includes a Doppler spectrum recorder to record a Doppler spectrum. The example system includes a study type inferrer to infer a study type associated with the Doppler spectrum by: processing the Doppler spectrum using at least one neural network to generate a first probability distribution among study type classifications; processing the image using the at least one neural network to generate a second probability distribution among the study type classifications; and combining the first probability distribution and the second probability distribution to infer a study type.

Abstract: Various methods and systems are provided for a medical imaging system. In one embodiment, a method comprises acquiring medical imaging data while executing a first imaging protocol, detecting a potential abnormality by evaluating the acquired medical imaging data with an artificial intelligence system, and outputting a first notification regarding the potential abnormality to a display, the first notification including an option to accept the first notification and an option to reject the first notification. In this way, an operator of an ultrasound imaging system may be alerted to a patient abnormality during a scan, thereby enabling the operator to further evaluate the potential abnormality without distracting the operator from controlling the medical imaging system.

Abstract: The systems and methods described herein generally relate to automatically determining an anatomical measurement of an ultrasound image. The systems and methods identify a view characteristic of an ultrasound image. The ultrasound image including one or more anatomical features. The systems and methods select a diagnostic measurement (DM) tool based on the view characteristic, on a graphical user interface (GUI), which is generated on a display. The systems and methods receive a first selection at a first position within the ultrasound image, and automatically determine an anatomical measurement, to be performed upon the ultrasound image utilizing the DM tool, based on the first position.

Abstract: A system and method for performing an ultrasound examination, analyzing the acquired images, and reporting image inadequacies and missing views at the end of the ultrasound examination is provided. The method includes acquiring ultrasound images during an examination, each of the images having an image view. The method includes receiving a user input to end the examination. The method includes automatically determining, with artificial intelligence, whether one or more images include an inadequacy. The method includes automatically determining, with the artificial intelligence, whether desired image views are not present in the images. The method includes presenting a report identifying any inadequate images and missing views. The method includes providing a selectable reopen exam option to reopen the examination.

Abstract: A method and ultrasound imaging system for detecting a coherent reflector includes acquiring ultrasound channel data from a volume with a probe, calculating a transform function from the ultrasound channel data, identifying a first angle of a projection of the coherent reflector in a plane parallel to the 2D aperture based on the transform function, detecting a line-shaped echo pattern in the ultrasound channel data, and determining a second angle of the coherent reflector with respect to the 2D aperture based on the position of the line-shaped echo pattern. The method and system includes determining a position and orientation of the coherent reflector based on the first angle and the second angle, enhancing a representation of the coherent reflector in an image generated based on the ultrasound channel data, and displaying the image on a display device after enhancing the representation of the coherent reflector.

Abstract: Example apparatus, systems, and methods for image data processing are disclosed and described. An example system includes an image capturer to facilitate capture of an image. The example system includes a Doppler spectrum recorder to record a Doppler spectrum. The example system includes a study type inferrer to infer a study type associated with the Doppler spectrum by: processing the Doppler spectrum using at least one neural network to generate a first probability distribution among study type classifications; processing the image using the at least one neural network to generate a second probability distribution among the study type classifications; and combining the first probability distribution and the second probability distribution to infer a study type.

Abstract: Methods and systems for segmenting structures in medical images are provided. The methods and systems drive a plurality of transducer element, and collect receive signals from the transducer array at a receive beamformer to form beam summed signals. The methods and systems generate a first ultrasound image of a region of interest (ROI) having tissue elements and blood elements, and generate a second ultrasound image of the ROI having tissue elements and blood elements. The tissue elements of the first ultrasound image having a higher intensity than the blood elements. The blood elements of the second ultrasound image having a higher intensity than the tissue elements. The methods and systems further perform segmentation by simultaneously applying edge detection on the first and second ultrasound images for the ROI.

Abstract: A method and ultrasound imaging system for detecting a coherent reflector comprises acquiring ultrasound channel data from a volume with a probe including a 2D aperture, calculating a MRT from the ultrasound channel data, identifying a first angle of a projection of the coherent reflector in a plane parallel to the 2D aperture based on the MRT, detecting a line-shaped echo pattern in the ultrasound channel data, determining a second angle of the coherent reflector with respect to the 2D aperture, determining a position and an orientation of the coherent reflector based on the first angle and the second angle, enhancing a representation of the coherent reflector in an image generated based on the ultrasound channel data, and displaying the image on a display device after enhancing the representation of the coherent reflector.

Abstract: Methods and systems are provided for automating analysis of diagnostic medical images. In one example, a method includes obtaining a set of medical images of a patient, automatically generating a set of clinical parameters from the set of medical images, automatically identifying a clinical finding of the patient based on at least one selected clinical parameter of the set of clinical parameters, outputting a graphical user interface for display on a display device, the graphical user interface including a visualization of the clinical finding and a link within the visualization of the clinical finding, and responsive to selection of the link, outputting, for display within the graphical user interface, a visualization of the at least one selected clinical parameter.

Abstract: A system and method for tracking an invasive device includes a localization system configured to be externally attached to a patient. The localization system includes a transducer module including a plurality of transducer elements. The system and method includes an invasive device including at least one device transducer element. The invasive device is configured to either transmit ultrasound position signals to the transducer module or receive ultrasound position signals from the transducer module.

Abstract: Systems and methods are provided for a visualization of a multi-modal medical image for diagnostic medical imaging. The systems and methods receive first and second image data sets of an anatomical structure of interest, register the first and second image data sets to a geometrical model of the anatomical structure of interest to form a registered image. The geometrical model includes a location of an anatomical marker. The systems and methods further display the registered image.

Abstract: The systems and methods described herein generally relate to automatically determining an anatomical measurement of an ultrasound image. The systems and methods identify a view characteristic of an ultrasound image. The ultrasound image including one or more anatomical features. The systems and methods select a diagnostic measurement (DM) tool based on the view characteristic, on a graphical user interface (GUI), which is generated on a display. The systems and methods receive a first selection at a first position within the ultrasound image, and automatically determine an anatomical measurement, to be performed upon the ultrasound image utilizing the DM tool, based on the first position.

Abstract: An ultrasonic diagnosis apparatus is provided. The ultrasonic diagnosis apparatus includes an ultrasonic probe configured to transmit ultrasonic push pulses to a biological tissue of a test object and further configured to transmit measuring ultrasonic pulses to the biological tissue subjected to the transmitted push pulses in order to measure an elasticity of the biological tissue, a respiration detection part configured to detect respiration of the test object, and a notification part which, based on the detection by the respiration detection part, is configured to give notification allowing a transmission timing of the push pulses to be recognized.

Abstract: Systems and methods are provided for a visualization of a multi-modal medical image for diagnostic medical imaging. The systems and methods receive first and second image data sets of an anatomical structure of interest, register the first and second image data sets to a geometrical model of the anatomical structure of interest to form a registered image. The geometrical model includes a location of an anatomical marker. The systems and methods further display the registered image.