General Electric Company

Ge Precision Healthcare LLC

Ge Medical Systems Global Technology Company, LLC

Other

University Of Zürich

Sandeep Dutta

Saad Ahmed Sirohey

Jiang Hsieh

Gopal Biligeri Avinash

John Skinner

Patricia Le Nezet

Deann Marie Haas

Darin Robert Okerlund

Toshihiro Rifu

Robert F Senzig

Bipul Das

Peter Michael Edic

Jerome F Knoplioch

Paul Edgar Licato

Kishore Chandra Acharya

Xiangyang Tang

Sidharth Abrol

Giridhar Jothiprasad

Rahul Bhotika

Steven James Gray

John Irvin Jackson

Bijan Dorri

Ravikanth Avancha

Mukta Chandrashekhar Joshi

Maud Bonnard

Roy Arnulf Helge Nilsen

Basel Taha

Maria-Magdalena Nay

Sardar Gautham

Brian Edward Nett

Guy M Besson

Hui Hu

Rakesh Mullick

Laurent Launay

Jianying Li

Naveen Stephan Chandra

John Howard Londt

Bernice Hoppel

Melissa Liliane Vass

Deepa Anand

Srikanth Suryanarayanan

Roy A Nilsen

Ananth P Mohan

Elisabeth Angelos

Aleksandar Zavaljevski

Beth Ann Heckel

Tal Gilat Schmidt

Arunabha Shasanka Roy

Min Xie

John Fusco

Uday Damodar Patil

Rajendra Kurady

Amy Deubig

Girish Saligram

Vanika Singhal

Robert Wolfe

Umesha Perdoor Srinivas Adiga

Ronny Büchel

Philipp Kaufmann

Csongor Pal Sprencz

David Pazzani

Daniel Stassi

Darin R Okerland

Ferry Tamtoro

Stephen W Metz

Daphné Gerbaud

Bianca Sintini

John A Fusco

Techniques are described for automatically detecting scan characteristics of a medical image series. According to an embodiment, a system is provided that comprises a memory that stores computer executable components, and a processor that executes the computer executable components stored in the memory. The computer executable components comprise an image generation component that generates a representative image of a medical image series comprising a plurality of scan images, and a series characterization component that processes the representative image using one or more characteristic detection algorithms to determine one or more characteristics of the medical image series. The system can further tailor the visualization layout for viewing the medical image series based on the one or more characteristics and/or automatically perform various workflow tasks based on the one or more characteristics.

Automatically detecting characteristics of a medical image series

Systems/techniques that facilitate deep learning multi-planar reformatting of medical images are provided. In various embodiments, a system can access a three-dimensional medical image. In various aspects, the system can localize, via execution of a machine learning model, a set of landmarks depicted in the three-dimensional medical image, a set of principal anatomical planes depicted in the three-dimensional medical image, and a set of organs depicted in the three-dimensional medical image. In various instances, the system can determine an anatomical orientation exhibited by the three-dimensional medical image, based on the set of landmarks, the set of principal anatomical planes, or the set of organs. In various cases, the system can rotate the three-dimensional medical image, such that the anatomical orientation now matches a predetermined anatomical orientation.

Deep learning multi-planar reformatting of medical images

Systems/techniques that facilitate learning-based domain transformation for medical images are provided. In various embodiments, a system can access a medical image. In various aspects, the medical image can depict an anatomical structure according to a first medical scanning domain. In various instances, the system can generate, via execution of a machine learning model, a predicted image based on the medical image. In various aspects, the predicted image can depict the anatomical structure according to a second medical scanning domain that is different from the first medical scanning domain. In some cases, the first and second medical scanning domains can be first and second energy levels of a computed tomography (CT) scanning modality. In other cases, the first and second medical scanning domains can be first and second contrast phases of the CT scanning modality.

Learning-based domain transformation for medical images

Techniques are described for domain adaptation of image processing models using post-processing model correction According to an embodiment, a method comprises training, by a system operatively coupled to a processor, a post-processing model to correct an image-based inference output of a source image processing model that results from application of the source image processing model to a target image from a target domain that differs from a source domain, wherein the source image processing model was trained on source images from the source domain. In one or more implementations, the source imaging processing model comprises an organ segmentation model and the post-processing model can comprise a shape-autoencoder. The method further comprises applying, by the system, the source image processing model and the post-processing model to target images from the target domain to generate optimized image-based inference outputs for the target images.

Domain adaptation using post-processing model correction

A system and method for estimating vascular flow using CT imaging include a computer readable storage medium having stored thereon a computer program comprising instructions, which, when executed by a computer, cause the computer to acquire a first set of data comprising anatomical information of an imaging subject, the anatomical information comprises information of at least one vessel. The instructions further cause the computer to process the anatomical information to generate an image volume comprising the at least one vessel, generate hemodynamic information based on the image volume, and acquire a second set of data of the imaging subject. The computer is also caused to generate an image comprising the hemodynamic information in combination with a visualization based on the second set of data.

System and method for estimating vascular flow using CT imaging

A method is provided including determining at least one range of phases of a cardiac cycle from which to select a selected phase based on at least one of patient demographic information, patient physiological information, or a general physiological model. The method also includes generating corresponding intermediate images for each of the phases of the at least one range of phases. Further, the method includes selecting the selected phase based on at least one image quality (IQ) metric of the intermediate images. Also, the method includes generating an image for diagnostic use using imaging information from the selected phase.

Systems and methods for coronary imaging

An imaging system includes a detector configured to receive data that can be reconstructed into a three-dimensional (3D) image of an object, and a computer programmed to obtain 3D image data of the object, the 3D image data including an internal structure of the object, define a longitudinal dimension of the internal structure from the 3D image data along a length of the structure, extract a first set of parameter-of-interest data related to the internal structure from the 3D image data along a first ray extending from a first location along the length of the structure and at a first angular orientation with respect to a base vector that is generally perpendicular to the longitudinal dimension, and plot the extracted first set of parameter-of-interest data at a pixel location of a two-dimensional (2D) plot that corresponds to the first location and corresponds to the first angular orientation.

System and method of visualizing features in an image

A system and method for analyzing and visualizing spectral CT data includes access of a set of image data acquired from a patient comprising spectral CT data, identification of a plurality of target regions of interest (TROIs) and a reference region of interest (RROI) from the set of image data, extraction of a plurality of target spectral Hounsfield unit (HU) curves from image data representing the plurality of TROIs, extraction of a reference spectral HU curve from image data representing the RROI, normalization of the plurality of target spectral HU curves with respect to the reference spectral HU curve, and display of the plurality of normalized target spectral HU curves.

System and method for analyzing and visualizing spectral CT data

A non-transitory computer readable storage medium having stored thereon a computer program comprising instructions, which when executed by a computer, cause the computer to acquire an image comprising image data reconstructed from an imaging device. The instructions further cause the computer to apply a bloom reduction algorithm to the image configured to iteratively reduce a blooming of high-density objects in the image.

System and method for quality improvement in CT imaging

A system and method includes acquisition of a set of image data comprising a plurality of image voxels and isolation of a set of pulmonary emboli candidates from the plurality of image voxels. The system and method also includes application of a non-linear contrast enhancement to the set of pulmonary emboli candidates, filtration of the enhanced set of pulmonary emboli candidates, output of a final set of pulmonary emboli candidates, and creation of an image comprising the final set of pulmonary emboli candidates.

System and method of pulmonary emboli detection for computed tomography

A system and method for dual energy CT spectral imaging that provides for accurate blood vessel stenosis visualization and quantification is disclosed. The CT system includes an x-ray source configured to project x-rays toward a region-of-interest of a patient that includes a blood vessel in a stenosed condition and having a plaque material therein. The CT system also includes an x-ray detector to receive x-rays emitted by the x-ray source and attenuated by the region-of-interest, a data acquisition system (DAS) operably connected to the x-ray detector, and a computer programmed to obtain a first set of CT image data for the region-of-interest at a first chromatic energy level, obtain a second set of CT image data for the region-of-interest at a second chromatic energy level that is higher than the first chromatic energy level, and identify plaque material in the region-of-interest by analyzing the second set of CT image data.

System and method for blood vessel stenosis visualization and quantification using spectral CT analysis

Systems, methods and apparatus are provided through which coronary plaque is classified in an image and visually displayed using an iterative adaptive process, such as an expectation maximization process.

Systems, methods and apparatus for plaque visualization and quantification using fuzzy and adaptive region classes

Methods and systems for generating computed tomographic (CT) images from image data acquired during different biological cycles are provided. A computer is programmed to receive a plurality of scan data acquired during a gated acquisition window of each of a plurality of biological cycles, blend the scan data acquired during a first of the plurality of biological cycles with the scan data acquired during a second of the plurality of biological cycles, and construct a final image from the blended data.

Methods and systems to facilitate reducing banding artifacts in images

A phantom includes a housing enclosing an interior volume and having a plurality of passages formed therein, wherein each passage is fluidly isolated from the interior volume. First and second inserts are included and configured to be positioned in a first passage of the plurality of passages and include materials having a known material density. The material is selected from iodine, hydroxyapatite (HAP), tricalcium phosphate (TCP), body fat, fatty plaque, sodium chloride (NaCl), gold (Au), and iron (Fe). The material of the inserts can be different materials or the same material at different densities.

Phantom for spectral CT image system calibration

Growing community of inventors

Waukesha, WI, United States of America

Sandeep Dutta