Abstract: The current disclosure provides systems and methods for an automated image comparison system that generates natural language descriptions of images. In an example, the image comparison system is configured to carry out a method that includes acquiring a current image of a patient during a current exam, generating, with a computer vision-enabled large language model (CV/LLM), a first compressed representation (CR) of the current image, obtaining a second CR of a similar image, the similar image similar to the current image and acquired in a prior exam, generating a text-based comparison of the current image and the similar image using the CV/LLM by entering the first CR and the second CR as input to the CV/LLM, and outputting the text-based comparison.

Abstract: Methods and systems are provided for training machine learning models to filter medical images with a reduced incidence of filtering artifact inclusion. In one example, training data may be generated by applying a filter to a medical image to produce a filtered medical image, wherein a subregion of the filtered medical image includes a filtering artifact, displaying the filtered medical image via a display device, receiving a selection of the subregion of the filtered medical image from a user input device, blending, in the subregion, pixel intensity values from the filtered medical image with pixel intensity values from the medical image, to produce a blended image, wherein a visibility of the filtering artifact is attenuated in the blended image, and displaying the blended image via the display device.

Abstract: Systems and methods are provided for super resolution for electronic 4D (e4D) cardiovascular ultrasound (CVUS) probes. In a medical imaging system, signals associated with a medical imaging technique may be acquired and processed, with the processing including applying one or both of a first type of correction to address a first type of degradation and a second type of correction to address a second type of degradation, with the first type of degradation being based on or caused by sparse acquisition, and the second type of degradation being based on or caused by choice of beamforming/reconstruction methodology.

Abstract: Methods and systems are provided for removing visual artifacts from a medical image acquired during a scan of an object, such as a patient. In one example, a method for an image processing system comprises receiving a medical image; performing a wavelet decomposition on image data of the medical image; performing one or more 2-D Fourier transforms on wavelet coefficients resulting from the wavelet decomposition; removing image artifacts from the Fourier coefficients determined from the 2-D Fourier transforms using a filter; reconstructing the medical image using the filtered Fourier coefficients; and displaying the reconstructed medical image on a display device of the image processing system.

Abstract: Methods and systems are provided for training machine learning models to filter medical images with a reduced incidence of filtering artifact inclusion. In one example, training data may be generated by applying a filter to a medical image to produce a filtered medical image, wherein a subregion of the filtered medical image includes a filtering artifact, displaying the filtered medical image via a display device, receiving a selection of the subregion of the filtered medical image from a user input device, blending, in the subregion, pixel intensity values from the filtered medical image with pixel intensity values from the medical image, to produce a blended image, wherein a visibility of the filtering artifact is attenuated in the blended image, and displaying the blended image via the display device.

Abstract: Methods and systems are provided for improving image quality of ultrasound images by automatically determining one or more image quality parameters via a plurality of separate image quality models. In one example, a method for an ultrasound system includes determining a plurality of image quality parameters of an ultrasound image acquired with the ultrasound system, each image quality parameter determined based on output from a separate image quality model, and outputting feedback to a user of the ultrasound system based on the plurality of image quality parameters.

Abstract: An ultrasound imaging system and method of multi-planar ultrasound imaging includes repetitively scanning both a main image plane and a reference image plane with an ultrasound probe while in a multi-planar imaging mode, wherein the reference image plane intersects the main image plane along a line and where the main image plane is repetitively scanned at a higher-resolution than the reference image plane. The ultrasound imaging system and method includes displaying a main real-time image of the main image plane and a reference real-time image of the reference image plane concurrently on a display device.

Abstract: Methods and systems are provided for sequentially selecting scan parameter values for ultrasound imaging. In one example, a method includes selecting a first parameter value for the a first scan parameter based on an image quality of each ultrasound image of a first plurality of ultrasound images of an anatomical region, each ultrasound image of the first plurality of ultrasound images having a different parameter value for the first scan parameter, selecting a second parameter value for a second scan parameter based on an image quality of each ultrasound image of a second plurality of ultrasound images of the anatomical region, each ultrasound image of the second plurality of ultrasound images having a different parameter value for the second scan parameter, and applying the first parameter value for the first scan parameter and the second parameter value for the second scan parameter to one or more additional ultrasound images.

Abstract: Methods and systems are provided for reducing anomalies in ultrasound images. One example method includes combining a plurality of sub-band components to attenuate anomalies in a first ultrasound image formed by the combination of the plurality of sub-band components, wherein the plurality of sub-band components are combined based on a plurality of adaptive weights output from a machine learning model and wherein the plurality of adaptive weights are associated with the plurality of sub-band components. The method further includes outputting for a display device, the first ultrasound image.

Abstract: Methods and systems are provided for improving image quality of ultrasound images by automatically determining one or more image quality parameters via a plurality of separate image quality models. In one example, a method for an ultrasound system includes determining a plurality of image quality parameters of an ultrasound image acquired with the ultrasound system, each image quality parameter determined based on output from a separate image quality model, and outputting feedback to a user of the ultrasound system based on the plurality of image quality parameters.

Abstract: Methods and systems are provided for improving image quality of ultrasound images by jointly selecting optimal scan parameter values. In one example, a method includes acquiring a plurality of ultrasound images of an anatomical region, each ultrasound image acquired at a different combination of parameter values for a first scan parameter and a second scan parameter, selecting a first parameter value for the first scan parameter and a second parameter value for the second scan parameter based on an image quality of each image, and acquiring one or more additional ultrasound images at the first parameter value and the second parameter value.

Abstract: Methods and systems are provided for sequentially selecting scan parameter values for ultrasound imaging. In one example, a method includes selecting a first parameter value for the a first scan parameter based on an image quality of each ultrasound image of a first plurality of ultrasound images of an anatomical region, each ultrasound image of the first plurality of ultrasound images having a different parameter value for the first scan parameter, selecting a second parameter value for a second scan parameter based on an image quality of each ultrasound image of a second plurality of ultrasound images of the anatomical region, each ultrasound image of the second plurality of ultrasound images having a different parameter value for the second scan parameter, and applying the first parameter value for the first scan parameter and the second parameter value for the second scan parameter to one or more additional ultrasound images.

Abstract: Methods and systems are provided for reducing anomalies in ultrasound images. One example method includes combining a plurality of sub-band components to attenuate anomalies in a first ultrasound image formed by the combination of the plurality of sub-band components, wherein the plurality of sub-band components are combined based on a plurality of adaptive weights output from a machine learning model and wherein the plurality of adaptive weights are associated with the plurality of sub-band components. The method further includes outputting for a display device, the first ultrasound image.

Abstract: Various methods and systems are provided for generating a volume-rendered image with shading from a three-dimensional ultrasound dataset. As one example, a method for ultrasound imaging includes generating a volume-rendered image with shading and shadowing from a three-dimensional ultrasound dataset, the shading and shadowing based on an angle between a probe axis of a transducer probe used to acquire the three-dimensional ultrasound dataset and a viewing direction of the volume-rendered image.

Abstract: A processor receives sensor feedback indicating a focal point of an HMD user. The processor casts rays through an image volume based on the sensor feedback. Each of the rays is associated with a pixel of a rendered image. The rendered image has a first plurality of pixels associated with the rays and a second plurality of unassociated pixels. The rays comprise a first portion cast at or near the focal point and a second portion that is cast farther away from the focal point. A first spacing between rays of the first portion is less than a second spacing between rays of the second portion. The processor determines color values corresponding with each of the first plurality of pixels associated with the rays. The processor determines color values corresponding with each of the second plurality of unassociated pixels of the rendered image. The HMD displays the rendered image.

Abstract: A processor receives sensor feedback indicating a focal point of an HMD user. The processor casts rays through an image volume based on the sensor feedback. Each of the rays is associated with a pixel of a rendered image. The rendered image has a first plurality of pixels associated with the rays and a second plurality of unassociated pixels. The rays comprise a first portion cast at or near the focal point and a second portion that is cast farther away from the focal point. A first spacing between rays of the first portion is less than a second spacing between rays of the second portion. The processor determines color values corresponding with each of the first plurality of pixels associated with the rays. The processor determines color values corresponding with each of the second plurality of unassociated pixels of the rendered image. The HMD displays the rendered image.

Abstract: Various embodiments include systems and methods for adaptive visualization enhancement in volumetric ultrasound images. One or more structures may be determined or identified to be visually enhanced in the volumetric ultrasound images, and one or more visualization changes may be determined, for each of the one or more structures to be visually enhanced. Rendering adjustments required to achieve each of the one or more visualization changes, for each of the one or more structures to be visually enhanced, may then be determined; and the rendering adjustments may be applied during volume rendering of the volumetric ultrasound images.

Abstract: Various methods and systems are provided for generating a volume-rendered image with shading from a three-dimensional ultrasound dataset. As one example, a method for ultrasound imaging includes generating a volume-rendered image with shading and shadowing from a three-dimensional ultrasound dataset, the shading and shadowing based on an angle between a probe axis of a transducer probe used to acquire the three-dimensional ultrasound dataset and a viewing direction of the volume-rendered image.

Abstract: Various embodiments include systems and methods for providing motion blur reduction to one or more three-dimensional (3D) images, and/or for improving accuracy of motion-compensated frame up-interpolations. The motion blur reduction may comprise application of iterative motion estimation, starting with an initial block size and with reduced block size in each iteration, with a final velocity vector being determined by summing displacement vectors from all iterations. Accuracy of motion-compensated frame up-interpolations may be improved by use of lower resolution frames (or portions of frames), which may be used in generating information used in enhancing motion related features or characteristics of motion-compensated frames.

Abstract: Certain embodiments provide a method and system for enhancing visualization of an image acquired with a handheld ultrasound scanner by automatically adjusting the image to optimize the color and contrast. The method may include performing, by a probe of an ultrasound system, an ultrasound scan to acquire ultrasound scan data. The method may also include detecting, by a sensor, lighting conditions. The method may include measuring, by a processor of the ultrasound system, a characteristic of the detected lighting conditions. The method may also include selecting, by the processor, a color map based on the measured characteristic. The method may include applying, by the processor, the selected color map to the acquired ultrasound scan data to generate processed ultrasound scan data.