Ge Medical Systems Global Technology Company, LLC

General Electric Company

Ge Precision Healthcare LLC

Yasuhiro Imai

Akihiko Nishide

Jiang Hsieh

Bipul Das

Utkarsh Agrawal

Risa Shigemasa

Akira Hagiwara

Yoshihiro Oda

Rajesh Veera Venkata Lakshmi Langoju

Ayako Matsumi

Brian Edward Nett

Jerome F Knoplioch

Abdelaziz Ikhlef

Makoto Gohno

Paavana Sainath

Adam Israel Cohen

Hewei Gao

Mitsuru Yahata

Kotoko Morikawa

Arun Kumar Chandrashekarappa

Rajesh Langoju

Masaya Kumazaki

Motoki Watanabe

Pankaj Giri

Gobinath Mani

Haruna Onodera

Techniques are described for enhancing the quality of three-dimensional (3D) anatomy scan images using deep learning. 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 a reception component that receives a scan image generated from 3D scan data relative to a first axis of a 3D volume, and an enhancement component that applies an enhancement model to the scan image to generate an enhanced scan image having a higher resolution relative to the scan image. The enhancement model comprises a deep learning neural network model trained on training image pairs respectively comprising a low-resolution scan image and a corresponding high-resolution scan image respectively generated relative to a second axis of the 3D volume.

Deep learning-based image quality enhancement of three-dimensional anatomy scan images

Various methods and systems are provided for computed tomography imaging. In one embodiment, a method includes acquiring, with an x-ray detector and an x-ray source coupled to a gantry, a three-dimensional image volume of a subject while the subject moves through a bore of the gantry and the gantry rotates the x-ray detector and the x-ray source around the subject, inputting the three-dimensional image volume to a trained deep neural network to generate a corrected three-dimensional image volume with a reduction in aliasing artifacts present in the three-dimensional image volume, and outputting the corrected three-dimensional image volume. In this way, aliasing artifacts caused by sub-sampling may be removed from computed tomography images while preserving details, texture, and sharpness in the computed tomography images.

Method and systems for aliasing artifact reduction in computed tomography imaging

Systems/techniques that facilitate machine learning generation of low-noise and high structural conspicuity images are provided. In various embodiments, a system can access an image and can apply at least one of image denoising or image resolution enhancement to the image, thereby yielding a first intermediary image. In various instances, the system can generate, via execution of a plurality of machine learning models, a plurality of second intermediary images based on the first intermediary image, wherein a given machine learning model in the plurality of machine learning models receives as input the first intermediary image, wherein the given machine learning model produces as output a given second intermediary image in the plurality of second intermediary images, and wherein the given second intermediary image represents a kernel-transformed version of the first intermediary image. In various cases, the system can generate a blended image based on the plurality of second intermediary images.

Machine learning generation of low-noise and high structural conspicuity images

The present disclosure relates to a system and method with which an imaged range in the past can be reproduced with high precision. In accordance with certain embodiments, an X-ray CT apparatus includes a camera-image producing section for producing a first camera image of a patient, a landmark fixing section for fixing a landmark with reference to a chest of the patient, and an imaged-range defining section for defining a first imaged range in a first scan based on landmark data representing the landmark. The camera-image producing section acquires a second camera image of the patient in a follow-up examination, the landmark fixing section fixes a second landmark with reference to the chest of the patient contained in the second image, and the imaged-range defining section defines second imaged range in a second scan based on landmark data representing the landmarks, and imaged-range data representing the first imaged range.

Imaged-range defining apparatus, medical apparatus, and program

To provide a technique with which dose indices can be managed for body parts in a range to be imaged on a body part-by-body part basis, an X-ray CT apparatus comprises: image producing unit () for producing a scout image () of a patient; defining unit () for defining a range () to be imaged in the scout image (); segmenting unit () for segmenting the range () to be imaged into two body parts; identifying unit () for identifying which one of body parts () included in a human body each of the two body parts corresponds to; and calculating unit () for calculating a dose index for each of the two body parts.

Medical apparatus, and program

A method is provided including acquiring imaging data of an object to be imaged from a computed tomography (CT) detector. The method also includes reconstructing the acquired imaging data into an initial reconstruction image, and performing material characterization of an image volume of the initial reconstruction image to provide a re-mapped image volume. Further, the method includes performing forward projection on the re-mapped image volume to provide forward projection data, and providing an error projection based on the forward projection data. Also, the method includes filtering at least one of the initial reconstruction image, the re-mapped image volume, the forward projection data, or the error projection. The method also includes using the error projection to update the initial reconstruction image to provide an updated reconstruction image.

Systems and methods for filtering for image generation

In one embodiment, a method to reduce the radiation dose delivered by an imaging system is provided. The method comprises steps of selecting a virtual mask representation based on the shape of an organ to be masked, displaying the virtual mask representation on a scout image and manipulating radiation dose to be delivered so as to modify the virtual mask representation to obtain an optimum attenuation profile.

Method to reduce radiation dose delivered by imaging system

For the purpose of providing an X-ray tomographic imaging apparatus for displaying a dual-energy image to facilitate diagnosis by an operator, an X-ray tomographic imaging apparatus () comprises: an image comparison information calculating section () for calculating image comparison information between said first-energy projection dataset(LD) or first-energy tomographic image(LT) and said second-energy projection dataset(HD) or second-energy tomographic image(HT); a region-of-interest defining section () for defining a region of interest; a weighting factor determining section (-) for determining a weighting factor for use in weighted subtraction processing between said first-energy projection dataset or first-energy tomographic image and said second-energy projection dataset or second-energy tomographic image, such that said image comparison information in said region of interest can be substantially eliminated by conducting said weighted subtraction processing; and a dual-energy image reconstructing section () for reconstructing a dual-energy image by conducting weighted subtraction processing between said first-energy projection dataset or first-energy tomographic image and said second-energy projection dataset or second-energy tomographic image used in said image comparison information calculating section, using a weighting factor determined at said weighting factor determining section.

X-ray tomographic imaging apparatus

An X-ray CT apparatus includes an X-ray radiation unit which applies a first X-ray having a first energy spectrum and a second X-ray having a second energy spectrum different from the first energy spectrum to a subject, an X-ray data acquisition unit which acquires first X-ray projection data of the subject based on the first X-ray and second X-ray projection data of the subject based on the second X-ray, and an image reconstruction unit which determines information about a difference between the first X-ray and the second X-ray with respect to an image of the subject, segments the image into at least two pixel areas based on the difference information, and sets part of the segmented pixel areas to a dual energy image obtained by a weighted subtraction process based on X-ray projection data having a plurality of energy spectrums.

X-ray CT apparatus and image processing apparatus

Methods and systems for calibrating a Computed Tomography (CT) system are provided. The method includes selectively activating each of a plurality of elements of a detector in the CT system. The method further includes determining for each of the selectively activated elements, a crosstalk effect on elements adjacent to the activated elements, to calibrate the CT system.

Method and system for calibrating a computed tomography system

For the purpose of X-ray CT imaging a heart of a subject with high image quality while reducing stress on the subject, once an optimal cardiac phase has been set by an optimal cardiac phase setting sectionand a target position in a subject to be scanned when the cardiac phase of the subject is at an optimal cardiac phase is defined at a target position defining section, a transport-starting-cardiac-phase calculating sectioncalculates a transport-starting cardiac phase such that the target position is scanned at the optimal cardiac phase, using the optimal cardiac cycle, target position, scan start position, transport speed of an imaging table, and approach-run time for the imaging table. A scan control section starts transport at the imaging tablewhen the cardiac phase of the subject coincides with the transport-starting cardiac phase, and performs a helical scan with a helical pitch of one or more, for example.

X-ray CT apparatus

In X-ray CT imaging for scanning a subject in the same anatomical region with two kinds of X-rays having different energy distributions, for the purpose of reducing a subject's positional offset between two kinds of tomographic images representing the same slice by a simple control scheme while reducing stress on the subject, a cardiac cycle identifying sectionidentifies a cardiac cycle of a subjectby an electrocardiographor the like, and a scan start time interval setting sectionsets a time interval from the start of a first scan with first X-rays to the start of a second scan with second X-rays to a time approximately the same as the aforementioned cardiac cycle. A scan control sectioncontrols several sections to keep a constant rotation speed of a rotating sectionand start the scans at the aforementioned time interval. In each scan, projection data over a given view angle sufficient for reconstruction processing for a tomographic image are collected at once.

The present invention provides an X-ray CT apparatus for imaging an MD image having a better S/N. The X-ray CT apparatus for taking an image with one of two materials within a subject to be examined being fractionated, acquiring two sets of data corresponding to said two types of X-ray having different energy by scanning using said two types of X-ray, generating a first image based on the two sets of data with the pixel values made by weighted addition of two types of CT values corresponding to the two types of X-ray, generating a second image based on the two sets of data, wherein the other one of the two types of material being fractionated, and generating an image by weighted subtraction of the first image and the second image.

X-ray CT apparatus and method of generating an image

An X-ray CT apparatus includes an X-ray data acquisition device for acquiring X-ray projection data transmitted through a subject lying between an X-ray generator and an X-ray detector having a two-dimensional detection plane and detecting X rays in opposition to the X-ray generator, while the X-ray generator and the X-ray detector are being rotated about a center of rotation lying there between; an image reconstructing device for image-reconstructing the acquired projection data; an image display device for displaying the image-reconstructed tomographic image; and an imaging condition setting device for setting various kinds of imaging conditions for tomographic image, wherein the X-ray data acquisition device acquires X-ray projection data in sync with an external sync signal by a helical scan with a predetermined range of the subject with a helical pitch set to 1 or more.

Growing community of inventors

Tokyo, Japan

Yasuhiro Imai