Koninklijke Philips Corporation N.V.

The United States of America, As Represented by the Secretary, Department of Health and Human Services

Sunnybrook Research Institute

Koninkluke Philips N.v.

Koninklijke Philips Electronics N.v.

Jochen Kruecker

Shyam Bharat

Cynthia Ming-fu Kung

Ehsan Dehghan Marvast

Amir Mohammad Tahmasebi Maraghoosh

Bradford Johns Wood

Sandeep M Dalal

Sheng Xu

Pingkun Yan

Shriram Sethuraman

Ananth Ravi

Molly Lara Flexman

Faik Can Meral

Douglas Allen Stanton

Grzegorz Andrzej Toporek

Christopher Stephen Hall

William Tao Shi

Falk Uhlemann

Man Nguyen

Ashish Panse

Peter A Pinto

Thomas Erik Amthor

Vijay Parthasarathy

Gary Cheng-How Ng

Sheng-Wen Huang

Ramon Quido Erkamp

James Robertson Jago

Heinrich Schulz

Andrew Lee Robinson

Neil Glossop

Peter Choyke

Thomas Heiko Stehle

Dirk Binnekamp

Luis Felipe Gutierrez

Jean-luc Robert

Claudia Errico

Raghavendra Srinivasa Naidu

Gary Lee Andrews

Niranjan Venugopal

Karen Irene Trovato

Balasundar Iyyavu Raju

Hua Xie

Vijay Thakur Shamdasani

Lyubomir Georgiev Zagorchev

Fabian Wenzel

Sven Prevrhal

Cecile Dufour

Alvin Chen

Antoine Collet-Billon

Sean Joseph Kyne

Eric Shen

Guy Shechter

Evgeniy Leyvi

Wei Lin

Xin Liu

Antonio Bonillas Vaca

Mahmoudreza Sharifi

Roberto Buizza

Alper Ayvaci

Hui Jiang

Samuel Kadoury

Marissa Patricia Dreyer

Ian Farmer

Jurgen Jan Rusch

Samuel Coons

Scott Frederic Thompson

Seyedali Sadeghi

Samer Bou Jawde

Shubham Patil

Naveen Balaraju

Guillaume Leopold Theodoros Frederik Hautvast

Sandeep Delal

Sandeep Dalal

Muqing Lin

Neil David Glossop

Luis F Gutierrez

Peter Lyle Choyke

A controller () for selecting images for presentation includes a memory (), a processor () and a receiver. The memory () stores instructions. The processor () executes the instructions. The receiver receives a stream of a plurality of images. When executed by the processor (), the instructions cause the controller () to apply trained artificial intelligence to the plurality of images and generate, based on the trained artificial intelligence, a 1-dimensional stream of a plurality of values corresponding respectively to the plurality of images. Each of the plurality of values of the 1-dimensional stream indicates a significance of a corresponding image of the plurality of images according to the trained artificial intelligence. The instructions also cause the controller () to output the plurality of values of the 1-dimensional stream for display with the plurality of images.

Image selection for presentation

System (SYS) and delated methods for supporting an imaging operation of an imaging apparatus (IA) capable of assuming different imaging geometries. The system comprises an input interface (IN) for receiving a current image acquired by the imaging apparatus (IA) of a current region of interest (ROI_1) at a current imaging geometry (p). A pre-trained machine learning component (MLC) computes output data that represents an imaging geometry change (Δp) for a next imaging geometry (p') in relation to a next region of interest (ROI_2). An output interface (OUT) outputs a specification of the imaging geometry change.

Patient model estimation for interventions

A lung injury monitoring system () configured to monitor a patient's lungs during ventilation, comprising: an ultrasound device () configured to obtain an ultrasound image of the patient's lungs during ventilation of the patient; a processor () configured to: (i) receive the obtained ultrasound image; (ii) determine a ventilation phase of the ventilator; (iii) analyze the received ultrasound image; and (iv) determine a risk score for a potential ventilator-associated lung injury (VALI); and a user interface () configured to display the determined risk score for the potential VALI.

Methods and systems for ventilation management using lung ultrasound

A method () for analyzing ultrasound image data, comprising: (i) receiving () ultrasound image data for a patient, comprising at least one lung-related clinical feature; (ii) selecting () a first clinical feature; (iii) analyzing (), using an image processing algorithm, the ultrasound image data to extract one or more image parameters of the selected clinical feature, wherein the image processing algorithm is defined to analyze the selected clinical feature; (iv) analyzing (), using a trained machine learning algorithm, the ultrasound image data to extract one or more learned parameters of the selected clinical feature, wherein the trained machine learning algorithm is trained to analyze the selected clinical feature; (v) combining () the image parameters and the learned parameters to generate a final lung-related clinical feature analysis; and (vi) providing () the generated final lung-related clinical feature analysis.

Methods and systems for clinical scoring a lung ultrasound

An ultrasound imaging system includes an a processor circuit that stores, in a memory in communication with the processor circuit, a target parameter representative of a target anatomical scan window. The processor circuit receives a first ultrasound image acquired by a first ultrasound probe with a first anatomical scan window during a first acquisition period. The processor circuit determines a first parameter representative of the first anatomical scan window. The processor circuit retrieves the target parameter from the memory. The processor circuit compares the target parameter and the first parameter. The processor circuit outputs a visual representation of the comparison to a display in communication with the processor circuit.

Ultrasound image-based identification of anatomical scan window, probe orientation, and/or patient position

A system (SYS) and related method for facilitating collimator adjustment in X-ray imaging or a radiation therapy delivery. The system comprises an input interface (IN) for receiving input data including i) an input image and/or ii) user input data including a partial collimator setting for a collimator (COL) of an X-ray imaging apparatus (IA). A collimator setting estimator (CSE) of the system computes a complemented collimator setting for the collimator based the input data. Preferably, the system uses machine learning.

Adaptive collimation for interventional x-ray

A training data modification system (TDM) for machine learning and related methods. The system comprises a data modifier (DM) configured to perform a modification operation to modify medical training X-ray imagery of a patient. The modification operation causes image structures in the modified medical training imagery. The image structure is representative of a property of i) a medical procedure, ii) an image acquisition operation by an X-ray-based medical imaging apparatus (IA), iii) an anatomy of the patient.

System and methods for augmenting X-ray images for training of deep neural networks

A system () and method (): access () a 3D reference image of a region of interest (ROI) () in a subject which was obtained using a first 3D imaging modality; segment () the ROI in the 3D reference image to define () a reference 3D coordinate system; acquire () 2D acoustic images of the ROI without absolute spatial tracking; generate () a standardized predicted pose for the 2D acoustic images with respect to a standardized 3D coordinate system () which was defined for a plurality of previously-obtained 3D images of corresponding ROIs in a plurality of other subjects which were obtained using the first 3D imaging modality; convert () the standardized predicted poses for the 2D acoustic images from the standardized 3D coordinate system to reference predicted poses in the reference 3D coordinate system; and use () the reference predicted poses for the 2D acoustic images to register the 2D acoustic images to the 3D reference image.

System and method for real-time fusion of acoustic image with reference image

Various embodiments of the present disclosure include a thermal ablation probabilistic controller () employing an ablation probability model () trained to render a pixel ablation probability for each pixel of an ablation scan image illustrative of a static anatomical ablation. In operation, the thermal ablation probabilistic controller () spatially aligns a temporal sequence of ablation scan datasets representative of a dynamic anatomical ablation, and applies the ablation probability model () to the spatial alignment of the temporal sequence of ablation scan datasets to render the pixel ablation probability for each pixel of the ablation scan image illustrative of the static anatomical ablation.

Temporal mapping of thermal ablation areas

Ultrasound image devices, systems, and methods are provided. An ultrasound imaging system comprising a processor circuit in communication with an ultrasound probe comprising a transducer array, wherein the processor circuit is configured to receive, from the ultrasound probe, a first image of a patients anatomy; detect, from the first image, a first anatomical landmark at a first location along a scanning trajectory of the patients anatomy; determine, based on the first anatomical landmark, a steering configuration for steering the ultrasound probe towards a second anatomical landmark at a second location along the scanning trajectory; and output, to a display in communication with the processor circuit, an instruction based on the steering configuration to steer the ultrasound probe towards the second anatomical landmark at the second location.

Point-of-care ultrasound (POCUS) scan assistance and associated devices, systems, and methods

Image co-registration entails: emitting energy, and responsively and dynamically acquiring images, the acquired images having a given dimensionality; selecting, repeatedly, and dynamically with the acquiring, from among the acquired images and, as a result of the selecting, changing, repeatedly, and dynamically, membership in a set of images of the given dimensionality; and, synchronously with the change, dynamically and iteratively registering the set to an image having a dimensionality higher than the given dimensionality. The co-registration is realizable with an imaging probe for the acquiring, and a tracking system for tracking a location, and orientation, of the probe, the registering being specialized for the acquiring with the probe being dynamically, during the acquiring, any one or more of angulated, rotated and translated. The registering is initialized by individual transformations of members of the set, but without need for reconstruction, of the set into an image of dimensionality higher than the given dimensionality, that derives, from the set, additional pixels external to the members.

Reconstruction-free automatic multi-modality ultrasound registration

A system for planning and performing a repeat interventional procedure is provided which includes a registration device and an image generation device which map current targets in a reference image for a first interventional procedure to at least one guidance image acquired from a different imaging modality. Biopsy locations are recorded to the guidance images during the first interventional procedure and the biopsy locations are mapped to the reference image to provide a planning image for use in a subsequent interventional procedure on the patient. In a subsequent interventional procedure, the prior planning image () may be registered to a current reference image and the prior biopsy locations and prior and current targets are mapped to a guidance image acquired from a different imaging modality. Biopsy locations are then mapped to the guidance image and mapped back to the current reference image.

System and method for planning and performing a repeat interventional procedure

The present disclosure describes ultrasound systems and methods configured to determine the elasticity of a target tissue. Systems can include an ultrasound transducer configured to acquire echoes responsive to ultrasound pulses transmitted toward the tissue, which may include a region of increased stiffness. Systems can also include a beamformer configured to control the transducer to transmit a push pulse into the tissue, thereby generating a shear wave in the region of increased stiffness. The beamformer can be configured to control the transducer to emit tracking pulses adjacent to the push pulse. Systems can further include a processor configured to determine a displacement amplitude of the shear wave and based on the amplitude, generate a qualitative tissue elasticity map of the tissue. The processor can combine the qualitative map with a quantitative map of the same tissue, and based on the combination, determine a boundary of the region of increased stiffness.

Shear wave amplitude reconstruction for tissue elasticity monitoring and display

An interventional instrument () is inserted into a patient () to perform an interventional medical procedure guided by a medical imaging device (). A trigger control () is activated. An electronic data processing device () is programmed to operate the medical imaging device to: acquire and display video () of the interventional instrument () inserted into the patient; detect activation of the trigger control; in response to the detecting, process a video segment () of the acquired video to identify a trigger image () as a frame of the video segment capturing a medical intervention event performed by the interventional instrument and a location () of the medical intervention event in the identified trigger image; and display a still image of the identified trigger image with a superimposed marker () indicating the identified location of the medical intervention event.

Workflow of needle tip identification for biopsy documentation

An ultrasound imaging system with an inertial tracking sensor () rigidly fixed to an ultrasound probe (). In a first embodiment, a real-time pose estimation unit () enhances image based tracking using the inertial data stream to calculate out-of-plane angles of rotation and determine an out-of-plane translation by iteratively selecting planes with the estimated out-of-plane rotations with varying out-of-plane offset, computing the differences between sub-plane distances computed by speckle analysis and the selected plane minimizing for the root mean square of the differences for all selected planes. In another embodiment, the real-time pose estimation unit enhances inertial tracking using the ultrasound image data stream to estimate an in-plane rotation angle; and substituting the in-plane rotation angle for an angle of rotation estimated using the inertial data stream.

Combining image based and inertial probe tracking

Growing community of inventors

Washington, DC, United States of America

Jochen Kruecker