Purdue Research Foundation

General Electric Company

University of Notre Dame Du Lac

Hewlett-packard Development Company, L.p.

Samsung Electronics Co., Ltd.

Xerox Corporation

Hewlett-packard Company

University of Michigan

Other

USA As Represented by Secretary of the Navy

Eastman-kodak Company

The University of Texas System

Ge Precision Healthcare LLC

Princeton University

Rochester Institute of Technology

Charles Addison Bouman

Ken David Sauer

Jean-Baptiste Thibault

Jiang Hsieh

Jan Philip Allebach

Zhou Yu

Bruno Kristiaan Bernard De Man

Hyung-soo Ohk

JongHyon Yi

Zhigang Fan

Raja Bala

Hengzhou Ding

Lin Fu

Jeffrey Allen Fessler

Debashish Pal

Eri Haneda

Kai Zeng

Peter Bauer

Somesh Srivastava

Michael George Fuchs

Guotong Feng

Zhen He

Maribel Figuera

Jean-Baptiste Daniel Marie Thibault

Yandong Guo

Ruoqiao Zhang

Reiner Eschbach

Samit Kumar Basu

Jay Stephen Gondek

Brian Edward Nett

Morgan Thomas Schramm

Garth Jason Simpson

Jie Tang

Ryan Douglas Muir

Brian J Atkins

Dejan Depalov

Justin Allen Newman

Shane Zachary Sullivan

Mark F Spencer

Casey J Pellizzari

Frank W Sliz

Mark Carlsen

Suhas Sreehari

Qian Lin

Anand Raghunathan

Swagath Venkataramani

C Brian Atkins

Xue Rui

Reuven J Sherwin

Sathish Ramani

Guangzhi Cao

Evgeny Drapkin

YouSun Bang

Peter G Anderson

Geoffrey John Woolfe

Brian C Atkins

Tae-yoon Hwang

Thyagarajan Balasubramanian

Bernd W Kolpatzik

Thyagarajan Blasubramanian

Michael T Orchard

Hung Nien

Madhuri Mahendra Nagare

Obaidullah Rahman

Roman Melnyk

Sherman Jordan Kisner

Changmeng Liu

Ti-Chiun Chang

Jiao Wang

Singanallur V Venkatakrishnan

Junshi Liu

Jay Allebach

Dong Ye

Yandong Guo Guo

Noise preserving models and methods for resolution recovery of x-ray computed tomography (e.g., using a computerized tool) are enabled. For example, a system can comprise: a memory that stores computer executable components, and a processor that executes the computer executable components stored in the memory, wherein the computer executable components comprise: a pair generation component that generates a pair of images, the pair of images comprising an input image and a ground truth image, a training component that trains a machine learning based sharpening algorithm by approximately minimizing a loss function that determines an error between a sharpened image and the ground truth image, and a sharpening component that, using the sharpening algorithm, sharpens the input image to generate the sharpened image, wherein the sharpened image comprises a second noise that is similar in intensity to a first noise of the input image.

Noise preserving models and methods for resolution recovery of x-ray computed tomography images

A computer-implemented method of latency reduction is disclosed for a digital holography optical imaging system. The method comprises receiving an incoming light field at a focal plane array of the digital holography optical imaging system, applying an interfering light field to the incoming light field at the focal plane array, and generating a holographic image based on the incoming light field and the interfering light field at the focal plane array. The method further comprises generating a sequence of phase errors based on the holographic image, generating at least one training parameter based on the sequence of phase errors, and training a neural network to revise the at least one training parameter using the sequence of phase errors, a time delay, and the at least one training parameter. The method further comprises predicting a future phase error for a future holographic image based on the revised training parameter.

System and method for latency reduction in an optical imaging system

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

Light reflected from an illuminated object is mixed with a reference beam and sensed at a sensor array of a digital hologram apparatus. Digital hologram data, determined from the sensed light, is dependent upon complex valued reflection coefficients of the object and upon phase perturbations in propagation paths between the object and the sensor array. Reflectance values, which may be dependent upon expected values of the absolute square of the reflection coefficients, and phase perturbations are determined for which a test function is at an extremum, where the test function contains a data fidelity term dependent upon the hologram data from a single hologram, a first regularization term dependent upon the phase perturbations and a second regularization term dependent upon the reflectance values. An image of the object may be formed from the reflectance values and a wavefront of the reflected light may be determined from the phase perturbations.

Method of single shot imaging for correcting phase errors

Single shot imaging using digital holography receiver

A beam-scanning optical design is described for achieving up to kHz frame-rate optical imaging on multiple simultaneous data acquisition channels. In one embodiment, two fast-scan resonant mirrors direct the optical beam on a circuitous trajectory through the field of view, with the trajectory repeat-time given by the least common multiplier of the mirror periods. Dicing the raw time-domain data into sub-trajectories combined with model-based image reconstruction (MBIR) 3D in-painting algorithms allows for effective frame-rates much higher than the repeat time of the Lissajous trajectory. Because sub-trajectory and full-trajectory imaging are different methods of analyzing the same data, both high-frame rate images with relatively low resolution and low frame rate images with high resolution are simultaneously acquired.

High frame-rate multichannel beam-scanning microscopy

A method of creating a hierarchical dictionary comprises, with a processor, extracting a number of symbols from a first image, constructing a number of refinement dictionary entries based on the symbols, the refinement dictionary entries forming a refinement dictionary, grouping a number of the refinement dictionary entries into clusters to form a number of refinement dictionary entry clusters, and constructing a number of direct dictionary entries for each of the refinement dictionary entry clusters, the direct dictionary entries forming a direct dictionary.

Creation of hierarchical dictionary

A system and method for text line detection are described Examples include detection of symbols in an image received from an image-capturing device. In examples, for each of at least some of the symbols, neighboring symbols within a local region a given distance from the symbol are analyzed in order to determine a direction for a line in the local region. In examples, based on the determined directions for the lines, text lines in the image are identified.

Tex line detection

A tomography system having a central processing unit, a system memory communicatively connected to the central processing unit, and a hardware acceleration unit communicatively connected to the central processing unit and the system memory, the hardware accelerator configured to perform at least a portion of an MBIR process on computer tomography data. The hardware accelerator unit may include one or more voxel evaluation modules which evaluate an updated value of a voxel given a voxel location in a reconstructed volume. By processing voxel data for voxels in a voxel neighborhood, processing time is reduces.

Tomographic reconstruction system

A framework for an iterative reconstruction algorithm is described which combines two or more of an ordered subset method, a preconditioner method, and a nested loop method. In one type of implementation a nested loop (NL) structure is employed where the inner loop sub-problems are solved using ordered subset (OS) methods. The inner loop may be solved using OS and a preconditioner method. In other implementations, the inner loop problems are created by augmented Lagrangian methods and then solved using OS method.

Accelerated iterative reconstruction

Methods and systems for model-based image processing are provided. One method includes selecting at least one reference image from a plurality of reference images, partitioning the at least one reference image into a plurality of patches, generating a probability distribution for each of the patches, and generating a model of a probability distribution for the at least one reference image using the probability distributions for each of the patches.

Methods and systems for performing model-based image processing

A method includes obtaining spectral computed tomography (CT) information via an acquisition unit having an X-ray source and a CT detector. The method also includes, generating, with one or more processing units, using at least one image transform, a first basis image and a second basis image using the spectral CT information. Further, the method includes performing, with the one or more processing units, guided processing on the second basis image using the first basis image as a guide to provide a modified second basis image. Also, the method includes performing at least one inverse image transform using the first basis image and the modified second basis image to generate at least one modified image.

Systems and methods for guided de-noising for computed tomography

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

As set forth herein, a computer-implemented method facilitates pre-analyzing an image and automatically suggesting to the user the most suitable regions within an image for text-based personalization. Image regions that are spatially smooth and regions with existing text (e.g. signage, banners, etc.) are primary candidates for personalization. This gives rise to two sets of corresponding algorithms: one for identifying smooth areas, and one for locating text regions. Smooth regions are found by dividing the image into blocks and applying an iterative combining strategy, and those regions satisfying certain spatial properties (e.g. size, position, shape of the boundary) are retained as promising candidates. In one embodiment, connected component analysis is performed on the image for locating text regions. Finally, based on the smooth and text regions found in the image, several alternative approaches are described herein to derive an overall metric for 'suitability for personalization.'

Methods and system for analyzing and rating images for personalization

Growing community of inventors

West Lafayette, IN, United States of America

Charles Addison Bouman