General Electric Company

University of Michigan

Purdue Research Foundation

University of Notre Dame Du Lac

The Johns Hopkins University

Somesh Srivastava

Jean-Baptiste Thibault

Charles Addison Bouman

Ken David Sauer

Lin Fu

Jeffrey Allen Fessler

Debashish Pal

Bruno Kristiaan Bernard De Man

Zhou Yu

Donghwan Kim

Jiang Hsieh

Jang Hwan Cho

Xue Rui

Sathish Ramani

Evgeny Drapkin

Katsuyuki Taguchi

Madison Gray McGaffin

Ryan Thome

Dong Ye

The present approach relates to the training of a machine learning algorithm for image generation and use of such a trained algorithm for image generation. Training the machine learning algorithm may involve using multiple images produced from a single set of tomographic projection or image data (such as a simple reconstruction and a computationally intensive reconstruction), where one image is the target image that exhibits the desired characteristics for the final result. The trained machine learning algorithm may be used to generate a final image corresponding to a computationally intensive algorithm from an input image generated using a less computationally intensive algorithm.

Image generation using machine learning

A method for iteratively reconstructing an image is provided. The method includes acquiring, with a detector, computed tomography (CT) imaging information. The method also includes generating, with at least one processor, sinogram information from the CT imaging information. Further, the method includes generating, with the at least one processor, image domain information from the CT imaging information. Also, the method includes updating the image using the sinogram information. The method further includes updating the image using the image domain information. Updating the image using the sinogram information and updating the image using the image domain information are performed separately and alternately in an iterative fashion.

Systems and methods for parallel processing of imaging information

An embodiment in accordance with the present invention provides a new SR compensation (SRC) method, using a more efficient conjugate gradient method. In this method, the first and second derivatives are directly calculated analytically. The proposed SRC uses a sinogram restoration approach, integrates the SRF as a part of a forward imaging model, and compensates for the effect of the SR by maximizing the Poisson log-likelihood of measurements. The algorithm can be evaluated using as a simulated fan-beam x-ray CT scanner.

Spectral response effects (SRE) compensation method for photon counting detectors (PCDs)

A system and method include acquisition of projection data from a scanned object, the set of projection data comprising a plurality of projection measurements. The system and method also include calculation of a set of modified statistical weights from the projection data, wherein a respective modified statistical weight of the set of modified statistical weights comprises a deviation from an inverse variance of a corresponding projection measurement of the projection data. The system and method further include reconstruction of an image of the scanned object using the set of modified statistical weights as coefficients in an iterative reconstruction algorithm.

System and method of iterative image reconstruction for computed tomography

A method is provided for iteratively reconstructing an image of an object. The method includes accessing measurement data associated with the image, and using a simultaneous algorithm to reconstruct the image. Using the simultaneous algorithm to reconstruct the image includes determining a scaling factor that is voxel-dependent, and applying the voxel-dependent scaling factor to a gradient of an objective function to reconstruct the image.

Method and apparatus for iterative reconstruction

A method is provided for reconstructing an image of an object that includes image elements. The method includes accessing measurement data associated with the image elements, introducing an auxiliary variable to transform an original problem of reconstructing the image to a constrained optimization problem, and solving the constrained optimization problem using a method of multipliers to create a sequence of sub-problems and solve the sequence of sub-problems. Solving the sequence of sub-problems includes reconstructing the image by optimizing a first objective function. The first objective function is optimized by iteratively solving a nested sequence of approximate optimization problems. An inner loop iteratively optimizes a second objective function approximating the first objective function. An outer loop utilizes the solution of the second objective function to optimize the first objective function.

Growing community of inventors

Waukesha, WI, United States of America

Somesh Srivastava