Queen's University at Kingston

The University of British Columbia

Mckesson Financial Holdings

Motion Metrics International Corp.

Purang Abolmaesumi

Gabor Fichtinger

Robert Rohling

Parvin Mousavi

Teresa Tsang

Mehdi Moradi

Eric Sauerbrei

Robert Siemens

Pascal Fallavollita

Phillip Isotalo

Amir H Abdi

Zhibin Liao

Delaram Behnami

Mahmoud Ramze Rezaee

Shahram Tafazoli Bilandi

Mohammad Sameti

Mahdi Ramezani

Saman Nouranian

Ian Law Bell

Andras Lasso

Abtin Rasoulian

Mehran Pesteie

Clif E Burdette

Thomas Kuiran Chen

Tamas Heffter

Darya Abdollahzadeh

Ava Sheikhi Shoshtari

E Clif Burdette

Zahra Karimaghaloo

Teresa S M Tsang

D Robert Siemens

A computer-implemented method of facilitating neural network image analysis involves receiving signals representing a set of images, causing at least one neural network function to be applied to the set of images to determine at least one property confidence distribution parameter, and causing a cumulative distribution function defined at least in part by the at least one property confidence distribution parameter to be applied to a plurality of ranges, each range associated with a respective property that may be associated with the set of images, to determine a plurality of property confidences, each of the property confidences representing a confidence that the set of images should be associated with a respective one of the properties. Other methods, systems, and computer-readable media are disclosed.

Neural network image analysis

A computer-implemented system for facilitating echocardiographic image analysis is disclosed. The system includes at least one processor configured to receive signals representing a first at least one echocardiographic image, associate the image with a first view category of a plurality of predetermined view categories, determine, based on the first at least one echocardiographic image and the first view category, a first quality assessment value representing a view category specific quality assessment of the first at least one echocardiographic image, and produce signals representing the first quality assessment value for causing the first quality assessment value to be associated with the first at least one echocardiographic image. The at least one processor may also be configured to do the above steps for a second at least one echocardiographic and a second view category that is different from the first view category image. Other systems, methods, and computer-readable media are also disclosed.

Echocardiographic image analysis

A method of facilitating ultrasonic analysis of a subject is provided. The method involves producing signals for causing a set of outgoing ultrasonic signals to be transmitted to the subject, wherein the set of outgoing ultrasonic signals is defined at least in part by a variable imaging parameter that varies over time in accordance with a variable imaging parameter function, the variable imaging parameter function represented or representable at least in part by a function characteristic, receiving signals representing a time dependent representation of the subject generated from a set of received ultrasonic signals scattered by the subject, determining at least one property representation of the subject based on the function characteristic and the time dependent representation of the subject, and producing signals representing the at least one property representation of the subject to facilitate analysis of the subject. Systems, non-transitory computer readable media, and other methods are also provided.

Ultrasonic analysis of a subject

This invention relates to a method of analyzing an ultrasound signal. The method comprises obtaining a time series of sequential data frames associated with an ultrasound signal reflected from and/or backscattered from a fixed location of a material under investigation, each data frame comprising a plurality of samples of the ultrasound signal, and subjecting to an analysis a sequence of one or more samples of the ultrasound signal, or a sequence of at least one parameter derived from one or more samples of the ultrasound signal, wherein a result of the analysis is related to one or properties or characteristics of the material. In one embodiment the method may be used for detecting, diagnosing, and/or assessing cancer and/or abnormalities in biological tissue.

Method for improved ultrasonic detection

A method and apparatus for processing an image of fragmented material to identify fragmented material portions within the image is disclosed. The method involves receiving pixel data associated with an input plurality of pixels representing the image of the fragmented material. The method also involves processing the pixel data using a convolutional neural network, the convolutional neural network having a plurality of layers and producing a pixel classification output indicating whether pixels in the input plurality of pixels are located at one of an edge of a fragmented material portion, inwardly from the edge, and at interstices between fragmented material portions. The convolutional neural network includes at least one convolution layer configured to produce a convolution of the input plurality of pixels, the convolutional neural network having been previously trained using a plurality of training images including previously identified fragmented material portions. The method further involves processing the pixel classification output to associate identified edges with fragmented material portions.

Method and apparatus for identifying fragmented material portions within an image

Embodiments of a computer-implemented method of facilitating ultrasonic image analysis of a subject are disclosed. The method can involve receiving signals representing a set of ultrasound images of the subject, deriving one or more extracted feature representations from the set of ultrasound images, determining, based on the derived one or more extracted feature representations, a quality assessment value representing a quality assessment of the set of ultrasound images, determining, based on the derived one or more extracted feature representations, an image property associated with the set of ultrasound images, and producing signals representing the quality assessment value and the image property for causing the quality assessment value and the image property to be associated with the set of ultrasound images. Embodiments of a computer-implemented method of training one or more neural networks to facilitate ultrasonic image analysis is also disclosed. Other apparatuses, methods, systems, and computer-readable media are also disclosed.

Ultrasonic image analysis

A computer-implemented method of producing an augmented image of a spine of a patient is disclosed. The method involves: receiving a first ultrasonic volumetric dataset representing a three-dimensional depiction of anatomical features of the spine in a first volume; instantiating a three-dimensional atlas of at least two vertebrae according to the first ultrasonic volumetric dataset; and causing a display to display a rendering of the first ultrasonic volumetric dataset together with a rendering of the atlas. An apparatus for producing the augmented image of the spine of the patient is also disclosed.

Methods of, and apparatuses for, producing augmented images of a spine

An ultrasound calibration phantom comprises a portion including at least one fiducial structure having a selected geometric arrangement; a portion adapted for mechanical coupling of the ultrasound calibration phantom to a transrectal ultrasound (TRUS) stepper; and a guide for at least one surgical instrument, the guide being mechanically coupled to the fiducial structure and/or to the TRUS stepper at a selected pose relative to the fiducial structure. A calibration method uses the calibration phantom and provides automatic, intraoperative calibration of ultrasound imaging systems. The invention is useful in ultrasound-guided clinical procedures.

Automated intraoperative ultrasound calibration

A PACS viewer and an associated method and computer program product are provided for identifying patient orientation. With respect to a PACS viewer, the PACS viewer includes processing circuitry configured to register an image onto a template. The processing circuitry is also configured to determine a representative seed point within each of the left and right lungs as represented by the image. The processing circuitry is further configured to apply an active contour model to each of the left and right lungs to generate a binary image of the left and right lungs. In this regard, the processing circuitry is configured to apply the active contour model by initializing the active contour model with a mask constructed using the representative seed points. Further, the processing circuitry is configured to detect at least one feature from the binary image to permit identification of the left and right lungs.

PACS viewer and a method for identifying patient orientation

This invention provides a method for estimating C-arm fluoroscope pose. The method involves introducing a coordinate system into a C-arm image, and applying intensity-based 2D/3D registration without segmentation to the coordinate system C-arm image and an image or known model of the coordinate system, wherein the intensity-based 2D/3D registration yields the C-arm pose. The coordinate system may be provided by introducing one or more markers or a fiducial into an image.

C-arm pose estimation using intensity-based registration of imaging modalities

Provided are methods and systems for registering image data from two imaging modalities, to produce an image having features from both imaging technologies. In particular, the methods and systems relate to intensity-based registration of the image data. The imaging modalities may be, for example, ultrasound and x-ray, magnetic resonance imaging, or a pre-operative plan.

Marker localization using intensity-based registration of imaging modalities

Growing community of inventors

Vancouver, Canada

Purang Abolmaesumi