Koninklijke Philips Corporation N.v.

Philips Image Guided Therapy Corporation

Jean-Luc Francois-Marie Robert

Francois Guy Gerard Marie Vignon

Jun Seob Shin

Sheng-Wen Huang

Man Nguyen

Hua Xie

Vijay Thakur Shamdasani

Seungsoo Kim

Faik Can Meral

Gerardus Henricus Maria Gijsbers

Ji Cao

David W Clark

Lars Jonas Olsson

Bruce Adrian Kincy

Alexey Viktorovich Cherepakhin

Shyam Bharat

Ramon Quido Erkamp

William Tao Shi

David Hope Simpson

Harm Jan Willem Belt

Andrew Hancock

Alexander Franciscus Kolen

Nenad Mihajlovic

Christine Menking Swisher

Carolina Amador Carrascal

Hong Liu

Ameet Kumar Jain

Vijay Parthasarathy

Kunal Vaidya

Emil George Radulescu

Robert Randall Entrekin

Franciscus Hendrikus Van Heesch

Shougang Wang

John Edward Dean

Shiying Wang

Roy B Peterson

Atul Gupta

Evgeniy Leyvi

Yan Shi

Anna Teresa Fernandez

Sibo Li

Bo Zhang

Benoit Jean-dominique Bertrand Maurice Mory

Muhammad Usman Ghani

William Hou

Jun Soeb Shin

Iason Zacharias Apostolakis

Gregory Tsiang Ely

An ultrasound imaging system which acquires short and/or undersampled radiofrequency ensembles for generating color Doppler images. The ultrasound imaging system processes the short and/or undersampled ensembles to simulate color Doppler images acquired from long radiofrequency ensembles. In some examples, the ultrasound imaging system includes one or more neural networks to process the ensembles.

Systems and methods for generating color doppler images from short and undersampled ensembles

In some examples, tissue types in B-mode images may be differentiated by multiparameter imaging and/or other segmentation techniques. The tissue types may be used to assign material properties to voxels of the B-mode image, such as color, translucency, and reflectivity. The material properties may be used to generate a rendered image. In some examples, one or more of the material properties assigned to the voxels may correspond to values of tissue parameters acquired during multiparameter imaging. The rendered image may include data based on both the B-mode image and the multiparameter imaging.

Rendering of B-mode images based on tissue differentiation

Systems and methods for suppressing random noise, acoustic clutter, and/or reverberation clutter in ultrasound images are disclosed. An autoregressive moving average (ARMA) filtering technique that includes generating a predictive error filter and estimating noise in ultrasound channel data is disclosed. Time-space and frequency-space ARMA filtering techniques are disclosed. An ultrasound imaging system capable of implementing the ARMA filtering techniques is disclosed.

Methods and systems for random noise supression and filtering of acoustic clutter via autoregressive moving average filter

The present disclosure describes medical imaging systems and methods configured to generate medical images based on undersampled imaging data. The images may be generated by applying a neural network trained with samples of known fully sampled data and undersampled data derived from the known fully sampled data to a acquired sparsely sampled data. The training of the neural network may involve training adversarial generative network including a generator and a discriminator. The generator is trained with sets of known undersampled data until the generator is capable of generating estimated image data, which the classifier is incapable of differentiation as either real or fake, and the trained generator may then be applied to unknown undersampled data.

Ultrasound system with a neural network for producing images from undersampled ultrasound data

The present invention relates to an ultrasound system () comprising a first non-invasive ultrasound probe () configured to acquire first ultrasound data having a first field of view; a second invasive ultrasound probe () configured to acquire second ultrasound data having a second field of view which is different from the first field of view; a tracking unit () configured to determine tracking data comprising a position and orientation of the first non-invasive ultrasound probe () relative to the second invasive ultrasound probe (); and a registration unit () configured to register the second field of view into the first field of view based on the tracking data.

Ultrasound system and method

Systems, methods, and apparatuses for confidence mapping of shear wave measurements are disclosed. Confidence maps of shear wave image measurements may be generated from one or more confidence factors. Masking of graphical overlays of tissue stiffness values, based at least in part on the confidence map is disclosed. The confidence map and/or masked graphical overlays of tissue stiffness values may be superimposed on ultrasound images and provided on a display.

Systems, methods, and apparatuses for confidence mapping of shear wave imaging

An ultrasound system produces maps of acoustic attenuation coefficients from B mode image signals. A plurality of maps located in different parallel and elevationally separated planes (A, B, C, D, E) are produced, then compounded in the elevation direction. Confidence maps may also be produced for one or more attenuation coefficient maps, and the confidence map displayed or its measures used to determine weighting for the compounding process. The compounding of elevationally separate planes improves attenuation coefficient estimation in the presence of blood vessels affecting the estimates in one or more of the planes.

Ultrasonic imaging of acoustic attenuation coefficients with elevation compounding

An ultrasound system produces maps of acoustic attenuation coefficients from pulse echo signals. Maps are produced using different attenuation coefficient or slope estimation methods, and a plurality of maps from different estimation methods are compounded to produce a final attenuation coefficient map. Confidence maps may also be produced for one or more attenuation coefficient maps, and the confidence map displayed or its measures used to determine weighting for the compounding process.

Ultrasonic imaging of acoustic attenuation coefficients with confidence estimation

The invention provides methods and systems for generating an ultrasound image. In a method, the generation of an ultrasound image comprises: obtaining channel data, the channel data defining a set of imaged points; for each imaged point: isolating the channel data; performing a spectral estimation on the isolated channel data; and selectively attenuating the spectral estimation channel data, thereby generating filtered channel data; and summing the filtered channel data, thereby forming a filtered ultrasound image. In some examples, the method comprises aperture extrapolation. The aperture extrapolation improves the lateral resolution of the ultrasound image. In other examples, the method comprises transmit extrapolation. The transmit extrapolation improves the contrast of the image. In addition, the transmit extrapolation improves the frame rate and reduces the motion artifacts in the ultrasound image. In further examples, the aperture and transmit extrapolations may be combined.

Methods and systems for processing an ultrasound image

Systems and methods for encoding radiofrequency, RF, data, e.g., electrical signals, by a microbeamformer are disclosed herein. The microbeamformer may use a pseudo-random sampling pattern () to sum samples of the RF data stored in a plurality of memory cells. The memory cells may be included in a delay line of the microbeamformer in some examples. The summed samples may form an encoded signal transmitted to a decoder which reconstructs the original RF data from the encoded signal. The decoder may use knowledge of the pseudo-random sampling pattern to reconstruct the original data in some examples.

Methods and systems for encoding and decoding radio frequency data

The present disclosure describes ultrasound imaging systems and methods configured to generate ultrasound images based on undersampled ultrasound data. The ultrasound images may be generated by applying a neural network trained with samples of known fully sampled data and undersampled data derived from the known fully sampled data to a acquired sparsely sampled data. The training of the neural network may involve training adversarial generative network including a generator and a discriminator. The generator is trained with sets of known undersampled data until the generator is capable of generating estimated image data, which the classifier is incapable of differentiation as either real or fake, and the trained generator may then be applied to unknown undersampled data.

Ultrasound image devices, systems, and methods are provided. An ultrasound imaging system, comprising an array of acoustic elements configured to transmit ultrasound energy into an anatomy and to receive ultrasound echoes associated with the anatomy; and a processor circuit in communication with the array of acoustic elements and configured to receive, from the array, ultrasound channel data corresponding to the received ultrasound echoes; normalize the ultrasound channel data by applying a first scaling function to the ultrasound channel data; generate beamformed data by applying a predictive network to the normalized ultrasound channel data; de-normalize the beamformed data by applying a second scaling function to the beamformed data; generate an image of the anatomy from the beamformed data; and output, to a display in communication with the processor circuit, the image of the anatomy.

Ultrasound imaging with deep learning-based beamforming and associated devices, systems, and methods

The present invention relates to an ultrasound system. A first non-invasive ultrasound probe receives first ultrasound data having a first field of view and a second invasive ultrasound probe receives second ultrasound data having a second field of view which is different from the first field of view. A tracking unit determines tracking data including a position and orientation of the first non-invasive ultrasound probe relative to the second invasive ultrasound probe. A registration unit registers the second field of view into the first field of view based on the tracking data.

Ultrasound system and method for interventional device tracking and guidance using information from non-invasive and invasive probes

Systems and methods for improving spectral-shift methods for calculating acoustic attenuation coefficients are disclosed. Systems, methods, and apparatuses for transmitting ultrasound pulse sequences for improved signal-to-noise outside the main passband of ultrasound transducers are disclosed. Systems, methods, and apparatuses for using the echoes from the transmitted pulse sequences to calculate the attenuation coefficient are disclosed.

Ultrasound systems and methods for measuring acoustic attenuation coefficients

Growing community of inventors

Cambridge, MA, United States of America

Jean-Luc Francois-Marie Robert