Tomography (e.g., Cat Scanner) Patents (Class 382/131)
  • Patent number: 11127174
    Abstract: The individual emitters are operated in multiple groups each illuminating a region of interest between the emitter array and the detector array such that the cone of radiation rays projected on the detector array from any single emitter in any one such group is substantially spatially separated from the corresponding projected cones from all other emitters in that same group. At least the ROI portion of the 3D space between the emitter panel and the detector panel is represented by 3D volume elements (voxels), wherein at least some of those voxels represent respective portions of that space that are traversed by corresponding portions of a plurality of radiation rays each extending from a respective emitter to a respective detector and are associated with respective absorption coefficients representative of the radiation absorption characteristic of a corresponding portion of the ROI.
    Type: Grant
    Filed: January 25, 2016
    Date of Patent: September 21, 2021
    Assignee: ADAPTIX LTD.
    Inventors: Gil Travish, Raphael Hauser, Kishan Patel
  • Patent number: 11126649
    Abstract: A computer-implemented system is described for identifying and retrieving similar radiology images to a query image. The system includes one or more fetchers receiving the query image and retrieving a set of candidate similar radiology images from a data store. One or more scorers receive the query image and the set of candidate similar radiology images and generate a similarity score between the query image and each candidate image. A pooler receives the similarity scores from the one or more scorers, ranks the candidate images, and returns a list of the candidate images reflecting the ranking. The scorers implement a modelling technique to generate the similarity score capturing a plurality of similarity attributes of the query image and the set of candidate similar radiology images and annotations associated therewith.
    Type: Grant
    Filed: July 11, 2018
    Date of Patent: September 21, 2021
    Assignee: Google LLC
    Inventors: Krishnan Eswaran, Shravya Shetty, Daniel Shing Shun Tse, Shahar Jamshy, Zvika Ben-Haim
  • Patent number: 11120584
    Abstract: The present disclosure is related to systems and methods for image processing. The method may include obtaining a first set of image data. The method may also include generating a second set of image data by processing, based on a trained machine learning model, the first set of image data. The second set of image data may have a relatively high resolution and/or a relatively low level of artifacts with respect to the first set of image data. The method may further include generating a target image by performing a weighted fusion on the first set of image data and the second set of image data.
    Type: Grant
    Filed: January 25, 2019
    Date of Patent: September 14, 2021
    Assignee: SHANGHAI UNITED IMAGING INTELLIGENCE CO., LTD.
    Inventors: Guobin Li, Nan Liu, Xiaoqian Huang, Shu Liao
  • Patent number: 11116479
    Abstract: An ultrasonic diagnostic imaging system and method acquire a sequence of image data as a bolus of contrast agent washes into and out of the liver. The image data of contrast intensity is used to compute time-intensity curves of contrast flow for points in an ultrasound image. Time-dependent data is calculated from the data of the time-intensity curves which, in a described implementation, comprise first and second derivatives of the time-intensity curves. A color map is formed of the time-dependent data or the polarities of the data and displayed in a parametric image as a color overlay of a contrast image of the liver.
    Type: Grant
    Filed: January 2, 2018
    Date of Patent: September 14, 2021
    Assignee: KONINKLIJKE PHILIPS N.V.
    Inventors: Xiaolin Gu, Yinhui Deng, Xiaomin Li, Vijay Thakur Shamdasani
  • Patent number: 11118895
    Abstract: A three-dimensional measurement device includes: an optical system that splits incident light into two lights, radiates one of the two lights as measurement light to a measured object and the other of the two lights as reference light to a reference surface, and recombines the two lights into combined light to emit the combined light; a light emitter that emits predetermined light entering the predetermined optical system; an imaging system that takes an image of output light emitted from the optical system; and an image processor that performs three-dimensional measurement of a predetermined measurement area of the measured object based on an interference fringe image obtained by the imaging system. The image processor obtains intensity image data at a predetermined position along an optical axis direction at each coordinate position in the measurement area by reconstruction based on an interference fringe image of the measurement area.
    Type: Grant
    Filed: May 14, 2020
    Date of Patent: September 14, 2021
    Assignee: CKD CORPORATION
    Inventors: Hiroyuki Ishigaki, Takahiro Mamiya
  • Patent number: 11119170
    Abstract: Systems and methods for high-resolution STAGE imaging can include acquisition of relatively low-resolution k-space datasets with two separate multi-echo GRE sequences. The multi-echo GRE sequences can correspond to separate and distinct flip angles. Various techniques for combining the low-resolution k-space datasets to generate a relatively high-resolution k-space are described. These techniques can involve combining low-resolution k-space datasets associated with various echo types. The STAGE imaging approaches described herein allow for rapid imaging, enhanced image resolution with relatively small or no increase in MR data acquisition time.
    Type: Grant
    Filed: June 11, 2020
    Date of Patent: September 14, 2021
    Assignee: SPINTECH, INC.
    Inventors: E. Mark Haacke, Yongsheng Chen
  • Patent number: 11119172
    Abstract: A method for MRI may include obtaining one or more scan parameters. The one or more scan parameters may include information of a plurality of diffusion gradients. The method may include causing, based on the one or more scan parameters, an imaging device to perform a plurality of scans to one or more slices of an object by applying the plurality of diffusion gradients to the one or more slices. For two components in a specific direction of the plurality of diffusion gradients applied in any two successive scans of the plurality of scans, there may be at most one component exceeding a first threshold. The specific direction may be one of a readout direction, a phase-encoding direction, or a slice-selection direction. The first threshold may be less than diffusion gradient energy relating to a duration and strength associated with one of the plurality of diffusion gradients.
    Type: Grant
    Filed: September 17, 2019
    Date of Patent: September 14, 2021
    Assignee: SHANGHAI UNITED IMAGING HEALTHCARE CO., LTD.
    Inventor: Zhenhua Shen
  • Patent number: 11109843
    Abstract: Alignment of an ultrasonograph and volume data obtained beforehand is correctly performed without requiring a user to perform complicated operation. First volume data for an ultrasonograph and second volume data obtained by another imaging apparatus are received and aligned. A predetermined imaging part selected from a plurality of imaging parts of a subject is received from a user. The second volume data are initially rotated by a rotation angle corresponding to the imaging part received by the receptor, and alignment of the initially rotated second volume data and the first volume data after is further carried out.
    Type: Grant
    Filed: November 27, 2015
    Date of Patent: September 7, 2021
    Assignee: HITACHI, LTD.
    Inventors: Zisheng Li, Tsuneya Kurihara, Yasuhiro Akiyama
  • Patent number: 11112480
    Abstract: A method is provided for generating a signal-to-noise improved magnetic resonance (MR) image of an object under examination in an MR system using a compressed sensing technology. The method includes determining a first MR signal data set of the object under examination in which a corresponding k-space is randomly subsampled; determining a location dependent sensitivity map for each of at least one receiving coil used to detect MR signals of the first MR signal data set in the location where the object under examination is located; and determining the MR image using an optimization process of the compressed sensing technology in which a location dependent regularization parameter is used, wherein the location dependent regularization parameter is determined based on the location dependent sensitivity map.
    Type: Grant
    Filed: July 8, 2020
    Date of Patent: September 7, 2021
    Assignee: Siemens Healthcare GmbH
    Inventors: Ralf Kartäusch, Dominik Paul, Mario Zeller
  • Patent number: 11109758
    Abstract: Optical imaging or spectroscopy described can use laminar optical tomography (LOT), diffuse correlation spectroscopy (DCS), or the like. An incident beam is scanned across a target. An orthogonal or oblique optical response can be obtained, such as concurrently at different distances from the incident beam. The optical response from multiple incident wavelengths can be concurrently obtained by dispersing the response wavelengths in a direction orthogonal to the response distances from the incident beam. Temporal correlation can be measured, from which flow and other parameters can be computed. An optical conduit can enable endoscopic or laparoscopic imaging or spectroscopy of internal target locations. An articulating arm can communicate the light for performing the LOT, DCS, or the like. The imaging can find use for skin cancer diagnosis, such as distinguishing lentigo maligna (LM) from lentigo maligna melanoma (LMM).
    Type: Grant
    Filed: March 8, 2018
    Date of Patent: September 7, 2021
    Assignee: The Trustees of Columbia University in the City of New York
    Inventors: Elizabeth Marjorie Clare Hillman, Sean A. Burgess
  • Patent number: 11109822
    Abstract: There is provided a method of locating a tip of a metallic instrument inserted in a body, utilizing a baseline sinogram comprising projections in N exposure directions and derived from a prior computerized tomography (CT) scanning of the body, the method comprising: performing three-dimensional Radon space registration of a sparse repeat sinogram to the baseline sinogram, the repeat CT scanning having the metallic instrument inserted into the body, the metallic instrument having an attached marker located at a known distance from the instrument tip; subtracting the baseline sinogram from the repeat sinogram in accordance with the registration parameters to obtain projection difference images; and using the projection difference images and the known distance of the attached marker from the metallic instrument tip to determine a three-dimensional location of the metallic instrument tip.
    Type: Grant
    Filed: August 20, 2019
    Date of Patent: September 7, 2021
    Assignee: YISSUM RESEARCH DEVELOPMENT COMPANY OF THE HEBREW UNIVERSITY OF JERUSALEM LTD
    Inventors: Leo Joskowicz, Guy Medan
  • Patent number: 11105907
    Abstract: An ultrasound imaging system according to the present disclosure may include an ultrasound probe, a display unit, and a processor configured to receive source image data having a first dynamic range, wherein the source image data comprises log compressed echo intensity values based on the ultrasound echoes detected by the ultrasound probe, generate a histogram of at least a portion of source image data, generate a cumulative density function for the histogram, receive an indication of at least two points on the cumulative density function (CDF), and cause the display unit to display an ultrasound image representative of the source image data displayed in accordance with the second dynamic range.
    Type: Grant
    Filed: December 21, 2018
    Date of Patent: August 31, 2021
    Assignee: KONINKLIJKE PHILIPS N.V.
    Inventors: David Wesley Clark, Francois Guy Gerard Marie Vignon, Darwin Philip Adams, Roy Allan Sivley, Kirthi Radhakrishnan
  • Patent number: 11107211
    Abstract: The present application provides a medical imaging method and system and a non-transitory computer-readable storage medium. The medical imaging method comprises identifying an image quality type of a medical image based on a trained learning network, and generating, based on the identified image quality type, a corresponding control signal for controlling a medical imaging system.
    Type: Grant
    Filed: May 13, 2020
    Date of Patent: August 31, 2021
    Assignee: GE Precision Healthcare LLC
    Inventors: Dan Wu, Kun Wang, Weinan Tang, Longqing Wang
  • Patent number: 11103222
    Abstract: An apparatus (10) for calibrating electromagnetic (EM) tracking of an associated ultrasound probe (12) includes a calibration needle (16), an EM tracking device including a field generator (14) and a reference EM sensor (24), an EM sensor (18, 26) on the ultrasound probe and on the calibration needle; at least one processor (50); and a non-transitory storage medium storing instructions to perform a EM tracking calibration method including: determining a location of the calibration needle in an ultrasound imaging space at a measurement time using the ultrasound probe; determining an EM-tracked location of the calibration needle at the measurement time; and generating a registration relating the location of the calibration needle in the ultrasound imaging space and the EM-tracked location of the calibration needle at the measurement time.
    Type: Grant
    Filed: December 18, 2017
    Date of Patent: August 31, 2021
    Assignee: KONINKLIJKE PHILIPS N.V.
    Inventors: Shyam Bharat, Antonio Bonillas Vaca
  • Patent number: 11100612
    Abstract: Methods and systems for neural network based image restoration are disclosed herein. An example method at least includes acquiring a plurality of training image pairs of a sample, where each training image of each of the plurality of training image pairs are images of a same location of a sample, and where each image of the plurality of training image pairs are acquired using same acquisition parameters, updating an artificial neural network based on the plurality of training image pairs, and denoising a plurality of sample images using the updated artificial neural network, where the plurality of sample images are acquired using the same acquisition parameters as used to acquire the plurality of training image pairs.
    Type: Grant
    Filed: May 7, 2019
    Date of Patent: August 24, 2021
    Assignee: FEI Company
    Inventors: Maurice Peemen, Pavel Poto{hacek over (c)}ek, Remco Schoenmakers
  • Patent number: 11100611
    Abstract: Methods and systems are provided for reducing background noise in magnetic resonance (MR) image and parametric map visualization using segmentation and intensity thresholding. An example method includes segmenting the MR image or parametric map into foreground which includes a region of anatomy of interest and background which is outside of the region of anatomy of interest, applying an intensity threshold to the background and not applying the intensity threshold to the foreground of the MR image or parametric map to produce a noise reduced MR image or noise reduced parametric map, and displaying the noise reduced MR image or noise reduced parametric map via a display device.
    Type: Grant
    Filed: March 29, 2019
    Date of Patent: August 24, 2021
    Assignee: GE PRECISION HEALTHCARE LLC
    Inventors: Deepthi S, Dheeraj Kulkarni, Jignesh Dholakia
  • Patent number: 11089941
    Abstract: A method for identifying material to be removed from a patient may use an imaging device, a display, a control unit, and an insertion device. The method may include obtaining a first set of image data from the imaging device, sending the first set of image data to the control unit from the imaging device, and analyzing the first set of image data based on at least one of a darkness, a contrast, or a saturation. The method may include generating a coded image identifying the material to be removed from the patient to be displayed on the display. The method may further include displaying the coded image on a first screen of the display, and indicating the material to be removed with the insertion device based on the displayed coded image.
    Type: Grant
    Filed: May 3, 2018
    Date of Patent: August 17, 2021
    Assignee: Boston Scientific Scimed, Inc.
    Inventors: Peter J. Pereira, Chad Schneider, Brandon W. Craft, Kimberly Degraaf, Jozef Slanda, James M. Goddard, Christopher P. Gauvin
  • Patent number: 11094061
    Abstract: The disclosure herein relates to systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking. In some embodiments, the systems, devices, and methods described herein are configured to analyze non-invasive medical images of a subject to automatically and/or dynamically identify one or more features, such as plaque and vessels, and/or derive one or more quantified plaque parameters, such as radiodensity, radiodensity composition, volume, radiodensity heterogeneity, geometry, location, and/or the like. In some embodiments, the systems, devices, and methods described herein are further configured to generate one or more assessments of plaque-based diseases from raw medical images using one or more of the identified features and/or quantified parameters.
    Type: Grant
    Filed: March 26, 2021
    Date of Patent: August 17, 2021
    Assignee: Cleerly, Inc.
    Inventors: James K. Min, James P. Earls, Hugo Miguel Rodrigues Marques
  • Patent number: 11089974
    Abstract: A method of accounting for the movement of the lungs during an endoscopic procedure such that a previously acquired image may be dynamically registered with a display showing the position of a locatable guide. After an initial image set is acquired, an area of interest is identified and the movement thereof due to breathing is mathematically modeled. Patient movement sensors are then used to provide information on the patient's breathing patterns. This information is entered into the mathematical model in order to update the registration between the image set and a display showing the position of the locatable guide.
    Type: Grant
    Filed: March 19, 2019
    Date of Patent: August 17, 2021
    Assignee: COVIDIEN LP
    Inventor: Dorian Averbuch
  • Patent number: 11094060
    Abstract: The disclosure herein relates to systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking. In some embodiments, the systems, devices, and methods described herein are configured to analyze non-invasive medical images of a subject to automatically and/or dynamically identify one or more features, such as plaque and vessels, and/or derive one or more quantified plaque parameters, such as radiodensity, radiodensity composition, volume, radiodensity heterogeneity, geometry, location, and/or the like. In some embodiments, the systems, devices, and methods described herein are further configured to generate one or more assessments of plaque-based diseases from raw medical images using one or more of the identified features and/or quantified parameters.
    Type: Grant
    Filed: March 26, 2021
    Date of Patent: August 17, 2021
    Assignee: Cleerly, Inc.
    Inventors: James K. Min, James P. Earls, Hugo Miguel Rodrigues Marques
  • Patent number: 11090019
    Abstract: A computer-implemented system: at least one processor communicably coupled to at least one nontransitory processor-readable storage medium storing processor-executable instructions or data receives segmentation learning data comprising a plurality of batches of labeled anatomical image sets, each image set comprising image data representative of a series of slices of a three-dimensional bony structure, and each image set including at least one label which identifies the region of a particular part of the bony structure depicted in each image of the image set, wherein the label indicates one of a plurality of classes indicating parts of the bone anatomy; trains a segmentation CNN, that is a fully convolutional neural network model with layer skip connections, to segment semantically at least one part of the bony structure utilizing the received segmentation learning data; and stores the trained segmentation CNN in at least one nontransitory processor-readable storage medium of the machine learning system.
    Type: Grant
    Filed: October 9, 2018
    Date of Patent: August 17, 2021
    Assignee: Holo Surgical Inc.
    Inventors: Krzysztof B. Siemionow, Cristian J. Luciano, Marek Kraft
  • Patent number: 11092659
    Abstract: A magnetic resonance imaging (MRI) system (100) includes a memory (134) for storing machine executable instructions (140) and magnetic resonance fingerprinting (MRF) pulse sequence commands (142) which cause the MRI system to acquire MRF magnetic resonance data (144) according to an MRF protocol. The pulse sequence commands are configured for acquiring the MRF magnetic resonance data in two-dimensional slices (410, 412, 414, 416, 418, 420), having a slice selection direction. A train of pulse sequence repetitions includes a sampling event where the MRF data is repeatedly sampled.
    Type: Grant
    Filed: March 30, 2018
    Date of Patent: August 17, 2021
    Assignee: Koninklijke Philips N.V.
    Inventors: Thomas Erik Amthor, Mariya Ivanova Doneva, Karsten Sommer, Peter Koken
  • Patent number: 11086294
    Abstract: A design engine analyzes a complex polygonal mesh to identify regions of that mesh that can be simplified. The design engine then replaces those identified regions with simplified geometry that is more easily fabricated using traditional techniques. The remaining complex regions of the mesh are fabricated using additive fabrication techniques. The design engine interacts with both a traditional fabrication device and an additive fabrication device to fabricate the simplified and complex regions of the mesh, respectively. In this manner, a hybrid 3D structure is generated that includes both simplified geometry and complex geometry.
    Type: Grant
    Filed: December 13, 2017
    Date of Patent: August 10, 2021
    Assignee: AUTODESK, INC.
    Inventors: Niels Grafen, Francesco Iorio, Nigel Morris, Adrian Butscher
  • Patent number: 11087076
    Abstract: The described technology is directed towards a computer program such as a browser that outputs augmented objects. The program is coupled to obtain object-related recognizer data of an object, communicate the object-related recognizer data to a registration service, receive augmentation data from the recognizer service and output at least part of the augmentation data in association with the object as an augmented object. Aspects include obtaining object-related recognizer data of an object, communicating the object-related recognizer data to a registration service, receiving augmentation data from the recognizer service, and outputting at least part of the augmentation data in association with the object as an augmented object.
    Type: Grant
    Filed: March 12, 2020
    Date of Patent: August 10, 2021
    Inventor: Nishant Dani
  • Patent number: 11083421
    Abstract: Disclosed herein is a method of acquiring a medical image of an X-ray apparatus, including: acquiring an original radiation image of a target object and capturing condition information of the object; acquiring a scatter radiation image related to the original radiation image by inputting the original radiation image and the capturing condition information to a learning network model configured to estimate scatter radiation; and acquiring a scatter radiation-processed medical image from the original radiation image on the basis of the original radiation image and the scatter radiation image, wherein the learning network model configured to estimate scatter radiation is a learning network model taught using a plurality of scatter radiation images and a plurality of pieces of capturing condition information related to each of the plurality of scatter radiation images.
    Type: Grant
    Filed: November 27, 2017
    Date of Patent: August 10, 2021
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Jeong Yong Song, Byeong Won Lee
  • Patent number: 11087557
    Abstract: An augmented reality device is configured to capture a plurality of frames, each including an image of a field of vision of an onsite surgeon, generate a plurality of registrations matching the plurality of frames to a field coordinate system, including defining a first registration of a first frame, detecting a motion of the device from the first frame to a second frame, generating an affine motion transformation, and calculating a second registration of the second frame to the field coordinate system, transmit to an offsite device operated by an offsite surgeon a plurality of representations of the plurality of frames and a plurality of indices corresponding to the plurality of frames, to receive an illustration drawn on the second frame, and to register the illustration on a third frame of the plurality of frames by generating a third registration of the third frame to the field coordinate system.
    Type: Grant
    Filed: June 3, 2020
    Date of Patent: August 10, 2021
    Inventor: Tovy Kamine
  • Patent number: 11080830
    Abstract: Described herein are computationally efficient systems and methods for processing and analyzing two-dimensional (2D) and three-dimensional (3D) images using texture filters that are based on the Hessian eigenvalues (e.g., eigenvalues of a square matrix of second-order partial derivatives) of each pixel or voxel. The original image may be a single image or a set of multiple images. In certain embodiments, the filtered images are used to calculate texture feature values for objects such as cells identified in the image. Once objects are identified, the filtered images can be used to classify the objects, for image segmentation, and/or to quantify the objects (e.g., via regression).
    Type: Grant
    Filed: April 23, 2019
    Date of Patent: August 3, 2021
    Assignee: PerkinElmer Cellular Technologies Germany GmbH
    Inventors: Peet Kask, Kaupo Palo, Hartwig Preckel
  • Patent number: 11080901
    Abstract: Systems and methods include training a deep convolutional neural network (DCNN) to reduce one or more artifacts using a projection space or an image space approach. In a projection space approach, a method can include collecting at least one artifact contaminated cone beam computed tomography (CBCT) projection space image, and at least one corresponding artifact reduced, CBCT projection space image from each patient in a group of patients, and using the artifact contaminated and artifact reduced CBCT projection space images to train a DCNN to reduce artifacts in a projection space image. In an image space approach, a method can include collecting a plurality of CBCT patient anatomical images and corresponding registered computed tomography anatomical images from a group of patients, and using the plurality of CBCT anatomical images and corresponding artifact reduced computed tomography anatomical images to train a DCNN to remove artifacts from a CBCT anatomical image.
    Type: Grant
    Filed: January 10, 2020
    Date of Patent: August 3, 2021
    Assignee: Elekta, Inc.
    Inventors: Jiaofeng Xu, Xiao Han
  • Patent number: 11080895
    Abstract: A system for generating simulated body parts for images may include a body part recognition convolutional neural network (CNN) to recognize a body part in an input image. The body part recognition CNN may be trained using first training data including training images including body parts contained in the input image being identified. The system may also include a body part generative adversarial network (GAN) to complete an image of the body part in the input image based on a body part identification output by the body part recognition CNN. The body part GAN may be trained using second training data including at least partial training images.
    Type: Grant
    Filed: October 30, 2018
    Date of Patent: August 3, 2021
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Sun Young Park, Dusty Sargent
  • Patent number: 11080858
    Abstract: There is provided a method and apparatus for segmenting two-dimensional images of an anatomical structure. A time sequence of two-dimensional images of the anatomical structure is acquired (202) and a segmentation model for the anatomical structure is acquired (204). The segmentation model comprises a plurality of segments. The acquired segmentation model is applied to the entire time sequence of two-dimensional images of the anatomical structure simultaneously in time and space to segment the time sequence of two-dimensional images by way of the plurality of segments (206).
    Type: Grant
    Filed: December 8, 2017
    Date of Patent: August 3, 2021
    Assignee: KONINKLIJKE PHILIPS N.V.
    Inventors: Rolf Jürgen Weese, Alexandra Groth, Jochen Peters
  • Patent number: 11080898
    Abstract: Each of a plurality of slices of medical image data is adaptively processed using a noise reduction mode selected according to a target noise magnitude for all slices to an estimated noise magnitude for the respective slice to obtain consistent processed images for across slices, different size patients' and different reconstruction thickness. Unnecessary noise reduction and over-cleaning images resulting in inconsistent noise-level image data across slices or waxy/unnatural appearing processed images is avoided.
    Type: Grant
    Filed: April 4, 2019
    Date of Patent: August 3, 2021
    Assignee: AlgoMedica, Inc.
    Inventor: Akira Hasegawa
  • Patent number: 11080333
    Abstract: Exemplary systems and methods to improve capture of relationships within information are provided. In various embodiments, a system comprises a landmark module configured to choose a set of landmarks from data in a finite metric space, the set of landmarks being a subset of points in the finite metric space, a nearest neighbor module configured to compute, for each landmark, a predetermined number of nearest neighbor landmarks in the set of landmarks, a graph construction module configured to identify at least one pair of landmarks that are nearest neighbors to each other, an edge generator module configured to add an edge between the at least one pair of landmarks, and a non-landmark projection module configured to project non-landmark points based on the landmarks and one or more edges thereby enabling at least one shape to indicate relationships in the data.
    Type: Grant
    Filed: August 7, 2018
    Date of Patent: August 3, 2021
    Assignee: Ayasdi AI LLC
    Inventors: Harlan Sexton, Jennifer Kloke
  • Patent number: 11080857
    Abstract: Methods and systems for segmenting a medical image into classes are described. A system to segment a medical image includes a processor and memory with instructions that upon execution cause the system to perform a method for segmenting the image. The method includes using initial segmentation methods to derive at least one set of probabilities of belonging to the classes for each pixel of the image. The at least one set of probabilities and the image are input into a neural network which segments the image based on both the probabilities and the image provided. This system can also use patches or sub-sections of the original image and the at least one set of probabilities as inputs to the final neural network. The patch based method enables segmentation of larger images, which usually require large amounts of time and memory to segment, and can produce a highly trained neural network.
    Type: Grant
    Filed: April 25, 2019
    Date of Patent: August 3, 2021
    Assignee: NeuralSeg Ltd.
    Inventor: Anthony Gatti
  • Patent number: 11074670
    Abstract: An image processing apparatus designates a first partial region for a first image obtained by rendering a configuration of an object in accordance with a predetermined coordinate system, designates a second partial region corresponding to the first partial region for a second image including an image obtained by capturing the object, and converts an image of the second partial region into an image complying with the predetermined coordinate system based on a coordinate of the first partial region in the first image and a coordinate of the second partial region in the second image. In the designation of the first partial region, different first partial regions in the first image are sequentially designated, and a first partial region at a (k+1)-th time based on a first partial region designated at a k-th time.
    Type: Grant
    Filed: January 3, 2020
    Date of Patent: July 27, 2021
    Assignee: CANON KABUSHIKI KAISHA
    Inventors: Kohei Iwabuchi, Yuichi Nitto, Mahoro Anabuki
  • Patent number: 11069098
    Abstract: An imaging data set (22) comprising detected counts along lines of response (LORs) is reconstructed (24) to generate a full-volume image at a standard resolution. A region selection graphical user interface (GUI) (26) is provided via which a user-chosen region of interest (ROI) is defined in the full-volume image, and this is automatically adjusted by identifying an anatomical feature corresponding to the user-chosen ROI and adjusting the user-chosen ROI to improve alignment with that feature. A sub-set (32) of the counts of the imaging data set is selected (30) for reconstructing the ROI, and only the selected sub-set is reconstructed (34) to generate a ROI image (36) representing the ROI at a higher resolution than the standard resolution. A fraction of the sub-set of counts may be reconstructed using different reconstruction algorithms (40) to generate corresponding sample ROI images, and a reconstruction algorithm selection graphical user interface (42) employs these sample ROI images.
    Type: Grant
    Filed: November 22, 2017
    Date of Patent: July 20, 2021
    Assignee: KONINKLIJKE PHILIPS N.V.
    Inventors: Shekhar Dwivedi, Andriy Andreyev, Chuanyong Bai, Chi-Hua Tung
  • Patent number: 11065059
    Abstract: Methods and systems of registering a model of one or more anatomic passageways of a patient to a patient space are provided herein. An exemplary method may include accessing a set of model points of the model of the passageways, the model points being associated with a model space, collecting measured points along a length of a catheter inserted into the passageways of the patient, the measured points determined by a shape of the catheter, and assigning points of the first set to a plurality of subsets. The exemplary method may further include registering each of the subsets with the model points to produce a plurality of registration candidates, comparing the candidates to identify an optimal subset associated with an optimal registration of the plurality of candidates that translates the set of model points and at least one set of the sets of measured points into a common space.
    Type: Grant
    Filed: October 31, 2017
    Date of Patent: July 20, 2021
    Assignee: INTUITIVE SURGICAL OPERATIONS, INC.
    Inventors: Timothy D. Soper, Vincent Duindam
  • Patent number: 11064972
    Abstract: A method for generating an ultrasound image includes receiving a sequence of intravascular ultrasound (IVUS) data obtained as an IVUS imager moves through a body lumen; identifying at least one bifurcation of the body lumen from the sequence of IVUS data; determining a bifurcation angle between two branches of the body lumen; and displaying a longitudinal view of the body lumen using the IVUS data and incorporating the bifurcation angle to angularly align portions of the longitudinal view corresponding to the two portions of the body lumen.
    Type: Grant
    Filed: September 23, 2011
    Date of Patent: July 20, 2021
    Assignee: BOSTON SCIENTIFIC SCIMED, INC.
    Inventors: Simone Balocco, Marina Alberti, Carlo Gatta, Francesco Ciompi, Oriol Pujol, Xavier Carrillo, Josepa Mauri Ferre, Oriol Rodriguez, Eduard Fernandez-Nofrerias, Petia Radeva
  • Patent number: 11062473
    Abstract: A method of determining the position and orientation of an invasive medical device is described using altered devices and a machine learning algorithm for detecting the position and orientation of such devices from imagery. Such predictions can subsequently be displayed to an operator to improve the speed and accuracy by which they perform procedures.
    Type: Grant
    Filed: December 12, 2019
    Date of Patent: July 13, 2021
    Inventors: Gabriel Fine, Nathan Silberman
  • Patent number: 11062448
    Abstract: Retrieval means analyzes character strings of a plurality of interpretation reports to retrieve an interpretation report in which a retrieval keyword is included. Registration means performs image processing with respect to a medical image corresponding to the retrieved interpretation report, extracts an anatomic region related to the retrieval keyword, and registers information indicating the anatomic region and the medical image as correct answer data in a case where the size of the extracted anatomic region is different from a standard size of the anatomic region or in a case where the shape of the extracted anatomic region is different from a standard shape of the anatomic region.
    Type: Grant
    Filed: July 23, 2018
    Date of Patent: July 13, 2021
    Assignee: FUJIFILM Corporation
    Inventor: Keigo Nakamura
  • Patent number: 11062490
    Abstract: A magnetic resonance imaging scan performs an MRI acquisition using an undersampling pattern to produce undersampled k-space data; adds the undersampled k-space data to aggregate undersampled k-space data for the scan; reconstructs an image from the aggregate undersampled k-space data; updates the undersampling pattern from the reconstructed image and aggregate undersampled k-space data using a deep reinforcement learning technique defined by an environment, reward, and agent, where the environment comprises an MRI reconstruction technique, where the reward comprises an image quality metric, and where the agent comprises a deep convolutional neural network and fully connected layers; and repeats these steps to produce a final reconstructed MRI image for the scan.
    Type: Grant
    Filed: October 16, 2019
    Date of Patent: July 13, 2021
    Assignee: The Board of Trustees of the Leland Stanford Junior University
    Inventors: David Y. Zeng, Shreyas S. Vasanawala, Joseph Yitan Cheng
  • Patent number: 11062467
    Abstract: Machine logic (for example, software) for registering multiple medical images, each showing a common lesion, with each other. In performing this registration, registration points are chosen to be both: (i) outside of image portion that is potentially compromised by the lesion (in any of the multiple images); and (ii) as close to the lesion as possible. However, in at least one of the images the extent of the lesion is not known—so, in order to accommodate this uncertainty about the lesion boundaries, lesion predicting machine logic rules are used to predict the size, shape and/or location of the lesion. Machine learning is used to intermittently adjust and improve the lesion predicting machine logic rules.
    Type: Grant
    Filed: February 5, 2020
    Date of Patent: July 13, 2021
    Assignee: International Business Machines Corporation
    Inventors: Sun Young Park, Dustin M. Sargent
  • Patent number: 11062928
    Abstract: Using measurements from a metrology tool, combinations of tool settings on the metrology tool can be determined. Candidates can then be determined and a response surface model can be generated for each of the candidates. A list of the candidates of the tool settings that provide a maximum response and that are least sensitive to sources of noise can then be determined from the response surface models. The list of the candidates can each be from a denser region of the response surface model.
    Type: Grant
    Filed: October 7, 2019
    Date of Patent: July 13, 2021
    Assignee: KLA Corporation
    Inventor: Scott Beatty
  • Patent number: 11055845
    Abstract: A computing system (126) includes a computer readable storage medium (130) with computer executable instructions (128), including: a segmentation standardizer (120) configured to determine a standardized vascular tree from a segmented vascular tree segmented of volumetric image data and a predetermined set of pruning rules (206), and a biophysical simulator (122) configured to perform a biophysical simulation based on the standardized vascular tree. The computing system further includes a processor (124) configured to execute the segmentation standardizer to determine the standardized vascular tree from the segmented vascular tree segmented of volumetric image data and the predetermined set of pruning rules, and configured to execute the biophysical simulator to perform a biophysical simulation based on the standardized vascular tree. The computing system further includes a display configured to display at least one of the standardized vascular tree and a result of the biophysical simulation.
    Type: Grant
    Filed: November 16, 2017
    Date of Patent: July 6, 2021
    Assignee: KONINKLIJKE PHILIPS N.V.
    Inventors: Hannes Nickisch, Holger Schmitt, Sven Prevrhal, Mordechay Pinchas Freiman, Liran Goshen
  • Patent number: 11055855
    Abstract: Methods and systems for determining a motion amplitude of an object being scanned. For example, a computer-implemented method for determining a motion amplitude of an object being scanned includes determining an internal parameter set based at least in part on calibrating the scanning apparatus according to a first predetermined algorithm; determining an external parameter set based at least in part on a testing surface and the internal parameter set; determining a mapping relationship between a pixel coordinate system and a world coordinate system based at least in part on the determined internal parameter set and the determined external parameter set; determining a motion amplitude of the object in the pixel coordinate system; and determining a motion amplitude of the object in the world coordinate system based at least in part on the determined mapping relationship and the motion amplitude of the object in the pixel coordinate system.
    Type: Grant
    Filed: October 8, 2019
    Date of Patent: July 6, 2021
    Assignee: Shanghai United Imaging Intelligence Co., Ltd.
    Inventors: Jianlong Nie, Zhong Xue
  • Patent number: 11055884
    Abstract: A method of correcting a first CT image for shading artefacts using another CT image as reference, comprising the steps of creating a difference image between the images and a correction map based on the difference image. The correction map is used to correct the first CT image. A method of converting a CT image to the value range of another CT image is also disclosed.
    Type: Grant
    Filed: October 16, 2018
    Date of Patent: July 6, 2021
    Assignee: RaySearch Laboratories AB
    Inventors: Sebastian Andersson, Rasmus Nilsson, Erik Traneus
  • Patent number: 11045261
    Abstract: A method, system and apparatus for surface rendering using medical imaging data is provided. A display device is controlled to render a first model of imaging data showing depth positions corresponding to a given surface threshold value, and further controlled to replace the first model with a second model of the imaging data showing respective depth positions corresponding to the given surface threshold value, the second model being faster to compute than the first model. The given surface threshold value is changed to an updated surface threshold value, for example using a slider input. The display device updates rendering of the second model to show updated respective depth positions corresponding to the updated surface threshold value. When an acceptance is received, the display device is controlled to replace the second model with the first model showing updated depth positions corresponding to the updated surface threshold value.
    Type: Grant
    Filed: October 9, 2019
    Date of Patent: June 29, 2021
    Assignee: SYNAPTIVE MEDICAL INC.
    Inventors: David Bruce Gallop, Sean Jy-Shyang Chen
  • Patent number: 11049230
    Abstract: Image processing performed by a computer (22) includes iterative image reconstruction or refinement (26, 56) that produces a series of update images ending in an iteratively reconstructed or refined image. A difference image (34, 64) is computed between a first update image (30, 60) and a second update image (32, 62) of the series. The difference image is converted to a feature image (40) and is used in the iterative processing (26, 56) or in post-processing (44) performed on the iteratively reconstructed or refined images or images from different reconstruction or refinement techniques. In another embodiment, first and second image reconstructions (81, 83) are performed to generate respective first and second reconstructed images (80, 82). A difference image (84) is computed between two images each selected from the group: the first reconstructed image, an update image of the first reconstruction, the second reconstructed image, and an update image of the second reconstruction.
    Type: Grant
    Filed: August 22, 2017
    Date of Patent: June 29, 2021
    Assignee: KONINKLIJKE PHILIPS N.V.
    Inventors: Chuanyong Bai, Andriy Andreyev, Bin Zhang, Yang-Ming Zhu, Xiyun Song, Jinghan Ye, Zhiqiang Hu
  • Patent number: 11045663
    Abstract: A control unit 30 includes: an image storage unit 31 constituted by a first image storage unit 32 that stores multiple templates created on the basis of an image including a specific site of a subject and a second image storage unit 33 that stores multiple positive images created on the basis of an image including the specific site of the subject; a learning unit 34 that, on the basis of the multiple positive images, creates a discriminator by machine learning; a position selection unit 35 that, with use of multiple images obtained by collecting an image including the specific site of the subject at a predetermined frame rate, selects a region including the specific site by machine learning using the discriminator; and a position detection unit 36 that detects the position of the specific site by performing template matching using the multiple templates on the region including the specific site selected by the position selection unit 35.
    Type: Grant
    Filed: July 20, 2017
    Date of Patent: June 29, 2021
    Assignee: Shimadzu Corporation
    Inventors: Shinichiro Mori, Wataru Takahashi
  • Patent number: 11045227
    Abstract: A computer-implemented method of preoperatively planning a surgical procedure on a knee of a patient including determining femoral condyle vectors and tibial plateau vectors based on image data of the knee, the femoral condyle vectors and the tibial plateau vectors corresponding to motion vectors of the femoral condyles and the tibial plateau as they move relative to each other. The method may also include modifying a bone model representative of at least one of the femur and the tibia into a modified bone model based on the femoral condyle vectors and the tibial plateau vectors. And the method may further include determining coordinate locations for a resection of the modified bone model.
    Type: Grant
    Filed: May 4, 2020
    Date of Patent: June 29, 2021
    Assignee: Howmedica Osteonics Corporation
    Inventors: Ilwhan Park, Charlie W. Chi, Venkata Surya Sarva, Irene Min Choi, Elena Pavlovskaia, Oleg Mishin, Boris E. Shpungin
  • Patent number: 11049295
    Abstract: A system (300) includes input/output configured to receive line integrals from a contrast enhanced spectral scan by an imaging system. The system further includes (300) a processor (326) configured to: decompose (334) the line integrals into at least Compton scatter and a photo-electric effect line integrals; reconstruct the Compton scatter and a photo-electric effect line integrals to generate spectral image data, including at least Compton scatter and photo-electric effect images; de-noise (332) the Compton scatter and photo-electric effect images; identify (402) residual iodine voxels in the de-noised Compton scatter and the photo-electric effect images corresponding to residual iodine artifact; and produce a virtual non-contrast image using the identified residual iodine voxels.
    Type: Grant
    Filed: December 19, 2017
    Date of Patent: June 29, 2021
    Assignee: KONINKLIJKE PHILIPS N.V.
    Inventors: Kevin Martin Brown, Bernhard Johannes Brendel