General Electric Company

Ge Precision Healthcare LLC

Ge Medical Systems Global Technology Company, LLC

Sylvain Bernard

Razvan Iordache

Serge Muller

Gero L Peters

Serge Louis Wilfrid Muller

Henri Souchay

Vincent Jonas Bismuth

Bruno Le Corgne

Giovanni Palma

Xavier Mancardi

Xavier Bouchevreau

Gopal Biligeri Avinash

Gireesha Chinthamani Rao

Remy Klausz

Tao Tan

Vincent Stanley Polkus

Dejun Wang

Giovanni John Jacques Palma

Yaan Ge

Ann-Katherine Carton

Pablo Milioni De Carvalho

Jorge Corsino Espino

Fanny Patoureaux

Marco Blumenthal

Buer Qi

Yana Popova

Veronique Felix

Axel Crasemann

Qingming Peng

Mathilde Ravier

Cynthia Davis

Razvan Jordache

Francois Peter

Various systems are provided for non-uniform thickness and/or sampling of slabs of the breast to present DBT acquisitions. A method for generating a patient image as a set of slabs representing an imaged object, the method comprising acquiring a tomosynthesis projection, reconstructing a series of slab images, each slab representing a portion of a breast, and a plurality of slabs of non-uniform thickness and/or non-uniform sampling in a 3D reconstructed domain defined by x-, y-, and z-axes.

Methods and systems for breast tomosynthesis

A convolutional neural network (CNN) is employed in an automated feature and/or anomaly detection system for analyzing images provided by X-ray imaging system. The automated detection system operates in a manner that reduces the number of full-resolution CNN convolution layers required in order to speed up the network inference and learning processes for the detection system. To do so, the detection system utilizes as an input a more compact representation of the tomographic data to alleviate the CNN memory footprint and computation time issues in prior art X-ray systems.

Fast and low memory usage convolutional neural network for tomosynthesis data processing and feature detection

A tomosynthesis machine allows for faster image acquisition and improved signal-to-noise by acquiring a projection attenuation data and using machine learning to identify a subset of the projection attenuation data for the production of thinner slices and/or higher resolution slices using machine learning.

X-ray tomosynthesis system providing neural-net guided resolution enhancement and thinner slice generation

This disclosure proposes to speed up computation time of a convolutional neural network (CNN) by leveraging information specific to a pre-defined region, such as a breast in mammography and tomosynthesis data. In an exemplary embodiment, a method for an image processing system is provided, comprising, generating an output of a trained convolutional neural network (CNN) of the image processing system based on an input image, including a pre-defined region of the input image as an additional input into at least one of a convolutional layer and a fully connected layer of the CNN to limit computations to input image data inside the pre-defined region; and storing the output and/or displaying the output on a display device.

Systems and methods for fast mammography data handling

Systems and methods for synthesizing a two-dimensional (2D) image of an organ of a patient by obtaining an pre-exposure x-ray image of the organ in order to ascertain parameters needed for acquisition of 2D (tomosynthesis) projection images of the organ, imaging the organ to obtain a plurality of 2D (tomosynthesis) projection images of the organ, and generating a synthetic 2D image of the organ from a combination of both the plurality of tomosynthesis projection images and the pre-exposure x-ray image.

Tomosynthesis dataset generation using pre-exposure acquisition

Methods, apparatus and systems for deep learning based image reconstruction are disclosed herein. An example at least one computer-readable storage medium includes instructions that, when executed, cause at least one processor to at least: obtain a plurality of two-dimensional (2D) tomosynthesis projection images of an organ by rotating an x-ray emitter to a plurality of orientations relative to the organ and emitting a first level of x-ray energization from the emitter for each projection image of the plurality of 2D tomosynthesis projection images; reconstruct a three-dimensional (3D) volume of the organ from the plurality of 2D tomosynthesis projection images; obtain an x-ray image of the organ with a second level of x-ray energization; generate a synthetic 2D image generation algorithm from the reconstructed 3D volume based on a similarity metric between the synthetic 2D image and the x-ray image; and deploy a model instantiating the synthetic 2D image generation algorithm.

Systems and methods for deep learning-based image reconstruction

A system and method for the detection of ROIs in images obtained of a breast or other tissue of a patient significantly improves the speed and precision/accuracy of navigation between multimodality 2D and 3D images. In the system and method, images of the tissue are obtained in a DBT acquisition to generate a synthetic 2D image of the imaged tissue and in a 3D, e.g., ultrasound, image acquisition. The 2D image generation process creates a synthetic 2D image that embed a navigation map correlating pixels in the 2D images to sections of the 3D ultrasound volume, such as via a registration between the 3D ultrasound volume and a 3D volume created using the DBT image data. When a synthetic 2D image is reviewed, an ROI on the 2D image is selected and the system will additionally present the user with the section of the 3D volume containing that ROI.

Multimodality 2D to 3D imaging navigation

Apparatus, systems, and methods for computer-aided detection are disclosed and described. An example apparatus includes at least one processor and a memory. The example memory includes instructions which, when executed, cause the at least one processor to at least: associate first patient data and first outcome data according to a set of association rules; train a processing model using machine learning and the associated first patient data and first outcome data; generate a computer-aided decision processing algorithm using the processing model; update the computer-aided decision processing algorithm based on at least one of second patient data or second outcome data received from a cloud infrastructure; and deploy the updated computer-aided decision processing algorithm to be applied to third patient data.

Methods and apparatus for self-learning clinical decision support

A method and system for obtaining images of an object of interest using a system comprising an X-ray source facing a detector. The method and system enable the acquiring of a plurality of 2D projection images of the object of interest in a plurality of orientations. A selected 2D projection image such as the zero projection of the plurality of projections can be enhanced by using at least a subset of the plurality of tomosynthesis projection images. The obtained enhanced 2D projection image is displayed for review.

Method and system for tomosynthesis projection image enhancement and review

Abstract systems and methods of biopsy control include reconstructing a 3D volume from a plurality of tomosynthesis projection images and producing a plurality of synthetic stereo images from the plurality of tomosynthesis projection images. At least the synthetic stereo images are presented on a graphical display to a clinician to facilitate at least one input of a biopsy location for biopsy control.

Synthetic images for biopsy control

Systems and methods of imaging an organ of a patient include obtaining a plurality of two-dimensional (2D) tomosynthesis projection images of the organ. An x-ray image of the organ is obtained. A three-dimensional (3D) volume of the organ is reconstructed from the plurality of projection images and the x-ray image. A synthetic 2D image of the organ is generated from the plurality of projection images and the x-ray image. The x-ray image is mapped to the 3D volume. A user selection of an object of interest in the x-ray image or the synthetic 2D image is received. A plane through the 3D volume that crosses the selected object of interest is identified and displayed.

Combined medical imaging

Method and system for obtaining images of an object of interest using a system comprising an x-ray source facing a detector. The method and system enable the acquiring of a plurality of 2D projection images of the object of interest in a plurality of orientations. A selected 2D projection image such as the zero projection of the plurality of projections can be enhanced by using at least a subset of the plurality of tomosynthesis projection images. The obtained enhanced 2D projection image is displayed for review.

Method and system for tomosynthesis projection images enhancement

Method and system for obtaining tomosynthesis and material decomposition images of an object of interest using a system comprising an x-ray source facing a detector. The method comprises generating a 2D material decomposition image of an object of interest from at least two sets of acquisitions. Each set is performed at a different energy spectrum and comprises at least one projection image or a plurality of projection images acquired at different x-ray source angulation positions, and the 2D material decomposition image can be generated for a predetermined orientation selected from one of said different x-ray source angulation positions or from a virtual orientation. At least one of the plurality of 3D volume portion images and/or the 2D contrast enhanced material decomposition image are displayed for review by a health care professional.

Method and system for obtaining low dose tomosynthesis and material decomposition images

A method for obtaining tomosynthesis images of an object of interest using an imaging system, wherein the imaging system comprises an X-ray source arranged to facing a detector on which the object of interest is positioned. The method comprises acquiring a plurality of projected 2D images of the object of interest in a plurality of orientations identified relative to a perpendicular to the detector, wherein a zero orientation is closest to the perpendicular and applying at least one filter to the acquired projected 2D images to obtain filtered, projection images of the object of interest. The method further comprises determining a reconstruction slice of the object of interest from the backprojection of at least two of the filtered projections, the set of reconstruction slices being the filtered, reconstructed volume of the object of interest, wherein a filter used on the 2D projection images is an adaptive filter.

Method for obtaining tomosynthesis images

A method for processing tomosynthesis images of an object of interest, using an imaging system, the imaging system comprising an X-ray source positioned facing a detector on which the object of interest is positioned. With the method of an embodiment of the invention, it is possible to display a three-dimensional (3D) reconstruction slice, as well as a two-dimensional (2D) image of the object of interest.

Growing community of inventors

Montigny le Bretonneux, France

Sylvain Bernard