Tomography (e.g., Cat Scanner) Patents (Class 382/131)
  • Patent number: 10197697
    Abstract: Systems, methods, and software for modeling subterranean formation permeability are described. In some aspects, a method of training a subterranean formation permeability model based on NMR data includes accessing relaxation-time distributions generated from NMR measurements associated with a subterranean region. Multiple sets of principal components are generated from the relaxation-time distributions. Each set of principal components represents a respective one of the relaxation-time distributions. Parameters for weighted radial basis functions are computed based on the sets of principal components. A subterranean formation permeability model that includes the weighted radial basis functions and the computed parameters is produced.
    Type: Grant
    Filed: December 12, 2013
    Date of Patent: February 5, 2019
    Assignee: Halliburton Energy Services, Inc.
    Inventors: Wei Shao, Songhua Chen
  • Patent number: 10186035
    Abstract: Provided are an image registration device and an image registration method. The image registration device includes: an ultrasonic image acquirer configured to periodically acquire an ultrasonic image by using a probe of an object; a medical image acquirer configured to acquire a medical image of the object, the medical image having a different modality from the ultrasonic image; a storage unit configured to store pre-acquired ultrasonic images and position information of the probe corresponding to each of the pre-acquired ultrasonic images; and a processor configured to register the ultrasonic image and the medical image, based on a first feature point of the medical image, a second feature point of a first ultrasonic image of the pre-acquired ultrasonic images, and the position information of the probe corresponding to the first ultrasonic image.
    Type: Grant
    Filed: July 27, 2016
    Date of Patent: January 22, 2019
    Assignee: SAMSUNG MEDISON CO., LTD.
    Inventors: Sung-jin Choi, Chul-an Kim, Jae-moon Jo
  • Patent number: 10185419
    Abstract: An image display system may include a host device, a touch-sensing device connected to the host device, and a display device connected to the host device. A method of operating the image display system may include the following steps: determining, using the host device, a required-touch quantity; selecting, using at least one of the host device and the touch-sensing device, a designated area based on the required-touch quantity, wherein the designated area corresponds to a plurality of designated driving electrodes that is a subset of driving electrodes of the touch-sensing device; detecting, using the designated driving electrodes without using other driving electrodes of the touch-sensing device, touch input provided in the designated area; and responding to the touch input using at least one of the host device and the display device.
    Type: Grant
    Filed: June 2, 2016
    Date of Patent: January 22, 2019
    Assignee: Samsung Display Co., Ltd.
    Inventor: Ho Eung Lee
  • Patent number: 10176601
    Abstract: One example method to improve image quality of projection image data may include obtaining projection image data and channel offset data associated with the projection image data. The channel offset data may be acquired using the flat panel detector and include at least one set of channel offset data values associated with respective channels of the flat panel detector. The method may also include generating channel offset drift data representing one or more variations of the channel offset data from a reference channel offset data. The method may further include generating offset-compensated projection image data by modifying the projection image data based on the channel offset drift data to compensate for the one or more variations of the channel offset data.
    Type: Grant
    Filed: March 25, 2016
    Date of Patent: January 8, 2019
    Assignee: VARIAN MEDICAL SYSTEMS INTERNATIONAL AG
    Inventors: Daniel Morf, Viktor Steinlin
  • Patent number: 10176571
    Abstract: A compressive sensing system for dynamic video acquisition. The system includes a video signal interface including a compressive imager configured to acquire compressive sensed video frame data from an object, a video processing unit including a processor and memory. The video processing unit is configured to receive the compressive sensed video frame data from the video signal interface. The memory comprises computer readable instructions that when executed by the processor cause the processor to generate a motion estimate from the compressive sensed video frame data and generate dynamical video frame data from the motion estimate and the compressive sensed video frame data. The dynamical video frame data may be output.
    Type: Grant
    Filed: December 12, 2016
    Date of Patent: January 8, 2019
    Assignee: William Marsh Rice University
    Inventors: Jianing V. Shi, Aswin C. Sankaranarayanan, Christoph Emanuel Studer, Richard G. Baraniuk
  • Patent number: 10176576
    Abstract: A medical image processing apparatus includes a core line identifying unit that identifies a core line of a predetermined region of a tubular structure from medical three-dimensional image data, a center position identifying unit that identifies a center position of the tubular structure from a plurality of points forming the core line identified by the core line identifying unit, an obtaining unit that obtains positions where straight lines intersecting at the center position and the tubular structure in the medical three-dimensional image data are in contact with each other, and a calculating unit that calculates a length of the tubular structure based on the positions obtained by the obtaining unit.
    Type: Grant
    Filed: March 28, 2018
    Date of Patent: January 8, 2019
    Assignee: Canon Kabushiki Kaisha
    Inventor: Tsuyoshi Sakamoto
  • Patent number: 10175181
    Abstract: The invention relates to an X-ray imaging system wherein images are obtained using an X-ray blocking element, the system comprising means for determining a position of the detector (40) on the basis of coordinates of projected patterns of the blocker (20, 220) in an image in order to especially be able to perform a calibration and/or correct the contribution of the scatter radiation in a radiographic image obtained by the system.
    Type: Grant
    Filed: July 21, 2015
    Date of Patent: January 8, 2019
    Assignees: UNIVERSITE GRENOBLE ALPES, SURGIQUAL INSTITUTE
    Inventors: Philippe Cinquin, Laurent Desbat, Yannick Grondin
  • Patent number: 10169534
    Abstract: A display system for displaying medical images across a plurality of separate display devices, the system comprising a layout unit for providing layout data concerning the display of medical images, an allocation unit for allocating a plurality of medical images amongst a plurality of separate display devices according to the layout data, wherein at least one of the plurality of display devices comprises a mobile display device.
    Type: Grant
    Filed: September 30, 2013
    Date of Patent: January 1, 2019
    Assignee: Toshiba Medical Systems Corporation
    Inventors: Timothy Day, Dominic Ashmole
  • Patent number: 10169683
    Abstract: The disclosure relates to a method for classifying an object of a current image, a plurality of first landmarks representative of the shape of the object being associated with the current image, a first unique identifier being associated with each first landmark. According to the disclosure, the method includes, for at least a first landmark, a step of obtaining at least a first descriptor describing an area of the current image having the at least first selected landmark. Then, the first landmark is selected according to its first identifier, and when its first identifier corresponds to a second identifier of a second landmark, a second descriptor is used in a classifier for classifying the object. Finally, the method determines information representative of confidence of the shape according to the first descriptor and according to weighting information associated with the second descriptor.
    Type: Grant
    Filed: August 28, 2016
    Date of Patent: January 1, 2019
    Assignee: Thomson Licensing
    Inventors: Xavier Burgos, Nezha Kabbaj, Francois Le Clerc
  • Patent number: 10165989
    Abstract: A tomography apparatus includes a data obtainer configured to obtain first image data at a first point and second image data at a second point using tomography, the tomography being performed by irradiating an X-ray to an object; an image processor configured to perform noise reduction based on at least one from among the first image data and the second image data, and to obtain a first reference image corresponding to the first image data and a second reference image corresponding to the second image data using a result of the performed noise reduction; and an image reconstructor configured to reconstruct a target image representing the object based on the first reference image and the second reference image.
    Type: Grant
    Filed: July 18, 2016
    Date of Patent: January 1, 2019
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Chan-won Seo, Toshihiro Rifu, Duhgoon Lee, Do-il Kim, Sang-nam Nam, Kyoung-yong Lee
  • Patent number: 10166004
    Abstract: An ultrasonic contrast imaging method and apparatus thereof. The method includes acquiring N frames of contrast image in an imaging period; projecting the N frames of contrast image to obtain a projection result image of the N frames of contrast image, wherein an nth group of original contrast image is projected in a projection template to obtain a projection result image of an nth frame of original contrast image, wherein the projection template is one frame of the nth group of original contrast image, and n is a positive integer greater than or equal to 1 and less than or equal to N, wherein the nth group of original contrast images is within a projection period and includes the nth original contrast image, and the projection period is a fixed value less than the imaging period; and displaying or storing the projection result image.
    Type: Grant
    Filed: June 24, 2015
    Date of Patent: January 1, 2019
    Assignee: SHENZHEN MINDRAY BIO-MEDICAL ELECTRONICS CO., LTD.
    Inventors: Ziyan Zhu, Maodong Sang, Yongqiang Dong
  • Patent number: 10159513
    Abstract: A custom arthroplasty guide and a method of manufacturing such a guide are disclosed herein. The method of manufacturing the custom arthroplasty guide includes: a) generating medical imaging slices of the portion of the patient bone; b) identifying landmarks on bone boundaries in the medical imaging slices; c) providing model data including image data associated with a bone other than the patient bone; d) adjusting the model data to match the landmarks; e) using the adjusted model data to generate a three dimensional computer model of the portion of the patient bone; f) using the three dimensional computer model to generate design data associated with the custom arthroplasty guide; and g) using the design data in manufacturing the custom arthroplasty guide.
    Type: Grant
    Filed: April 28, 2017
    Date of Patent: December 25, 2018
    Assignee: Howmedica Osteonics Corporation
    Inventors: Elena Pavlovskaia, Oleg Mishin, Boris E. Shpungin
  • Patent number: 10159443
    Abstract: An apparatus and a method for determining vital sign information from a subject are disclosed. The proposed apparatus comprises a detection unit for detecting radiation received from the subject in a field of view, a first determining unit for determining a first time dependent signal from the radiation received from the subject, an evaluation unit for deriving at least one parameter from the first time dependent signal, a selection unit for selecting an area in the field of view on the basis of the detected radiation and the at least one parameter, a second determining unit for determining a second time dependent signal from the radiation received from the selected area, and an analysis unit for analyzing the second time dependent signal and for determining the vital sign information on the basis of the analysis of the second time dependent signal.
    Type: Grant
    Filed: March 7, 2014
    Date of Patent: December 25, 2018
    Assignee: KONINKLIJKE PHILIPS N.V.
    Inventors: Erik Bresch, Jens Muehlsteff, Mukul Julius Rocque, Marek Janusz Bartula
  • Patent number: 10163211
    Abstract: A method for enhancing the visualization of a plurality of objects within an imaged subject. The method includes acquiring a plurality of images of the plurality of objects disposed in the imaged subject and supported by a plurality of guide wires; generating a complex deformation field based at least in part on a plurality of landmarks disposed in the plurality of images; and generating a composite image based at least in part on the complex deformation field. The complex deformation field models deformation induced on the plurality of objects by at least two or more guide wires of the plurality.
    Type: Grant
    Filed: January 26, 2016
    Date of Patent: December 25, 2018
    Assignee: GENERAL ELECTRIC COMPANY
    Inventors: Regis Vaillant, Maxime Cazalas, Liliane Ramus, Sophie Amelot
  • Patent number: 10157489
    Abstract: The present invention relates to an ultrasound imaging system (10) comprising an ultrasound probe (20) having a transducer array (21) configured to provide an ultrasound receive signal. The system further comprises a B-mode volume processing unit (30) configured to generate a B-mode volume (31) based on the ultrasound receive signal, and a B-mode image processing unit (40) configured to provide a current B-mode image (41) based on the B-mode volume (31). The system further comprises a memory (50) configured to store a previously acquired 3D-vessel map (51). Also, the system comprises a registration unit (60) configured to register the previously acquired 3D-vessel map (51) to the B-mode volume (31) and to select a portion (61) of the 3D-vessel map corresponding to the current B-mode image (41). Further, the system comprises a display configured to display an ultrasound image (71) based on the current B-mode image (41) and the selected portion (61) of the 3D-vessel map (51).
    Type: Grant
    Filed: July 10, 2017
    Date of Patent: December 18, 2018
    Assignee: Koninklijke Philips N.V.
    Inventors: Gary Cheng-How Ng, James Robertson Jago, Andrew Lee Robinson
  • Patent number: 10152571
    Abstract: A chest x-ray differential diagnosis system is operable to generate abnormality pattern data is generated for each of a received plurality of chest x-rays by identifying at least one pattern in each chest x-ray corresponding to an abnormality by utilizing a computer vision model that is trained on a plurality of training chest x-rays. Differential diagnosis data is generated for each chest x-ray based on the abnormality pattern data. Filtering parameters are received from a client device, and a filtered chest x-ray queue that includes a subset of chest x-rays is selected based on the filtering parameters and the differential diagnosis data is generated for transmission to the client device for display. Differential diagnosis data corresponding a chest x-ray indicated in chest x-ray selection data received from the client device is transmitted to the client device for display via the display device in conjunction with the chest x-ray.
    Type: Grant
    Filed: June 20, 2017
    Date of Patent: December 11, 2018
    Assignee: Enlitic, Inc.
    Inventors: Kevin Lyman, Devon Bernard, Li Yao, Diogo Almeida, Ben Covington, Anthony Upton
  • Patent number: 10150248
    Abstract: A server is configured to store a number of different models of an object in machine-ready form corresponding to a number of different three-dimensional printers having differing capabilities and/or hardware configurations. When a user at a client device or a printer requests the object, the server automatically determines a printer type and selects a suitable, corresponding machine-ready model for immediate fabrication by the printer.
    Type: Grant
    Filed: June 20, 2018
    Date of Patent: December 11, 2018
    Assignee: MakerBot Industries, LLC
    Inventors: Nathaniel B. Pettis, Anthony James Buser, Justin Day, Jonah Gold, Bryan Vaccaro, Joseph Neal
  • Patent number: 10143390
    Abstract: A method is provided that determines velocity encoding direction of volumetric image data sets comprising three-directional velocity information (V0, V1, V2) of a target volume, which involves: a) defining a coordinate system (X, Y, Z); b) determining all the possible arrangements of the three velocity components (V0, V1, V2) along the three coordinate axes (X, Y, Z); c) determining reference point or points in the target volume either automatically or upon user input; d) determining streamlines for each point for all possible combinations of velocity components as determined in b); and e) considering as velocity encoding direction the arrangement of the three velocity components corresponding to the streamlines having the longest length or a length above a threshold. A corresponding apparatus and computer program are also disclosed.
    Type: Grant
    Filed: April 19, 2017
    Date of Patent: December 4, 2018
    Assignee: Pie Medical Imaging B.V.
    Inventors: Leon Ledoux, Bas Weijers, Jean-Paul Aben
  • Patent number: 10147225
    Abstract: An apparatus and method for sampling pattern generation in a ray tracing architecture. For example, one embodiment of a graphics processing apparatus comprises: a ray generation circuit to generate a ray stream from one or more image tiles; and a sample pattern generation circuit to generate samples for rays in the ray stream, the samples generated to exhibit at least some randomness across pixels of a given frame but be repeatable across multiple frames.
    Type: Grant
    Filed: April 1, 2016
    Date of Patent: December 4, 2018
    Assignee: Intel Corporation
    Inventor: David R. Baldwin
  • Patent number: 10147186
    Abstract: The present disclosure addresses above-mentioned issues by providing a system and method for preparing a correlation data set to be used in parametric grading of malignant tissues. Systems and methods of the present disclosure further provide for a visualization scheme, wherein all the parameters can be viewed at the same time and processed together to arrive at an accurate grading of the tissue based on threshold based comparison of the parameter values for each voxel.
    Type: Grant
    Filed: September 7, 2015
    Date of Patent: December 4, 2018
    Inventors: Amarnath Jena, Sangeeta Taneja, Shashi Bhushan Mehta
  • Patent number: 10143430
    Abstract: One aspect of the present disclosure relates to a system that can employ multi-modal imaging to provide an image with an enhanced resolution. In some instances, the multi-modal imaging can allow an operator to determine and control a tissue margin without the need for intra-operative tissue pathology. The system can include an imaging system that includes a gamma camera to detect a gamma image and an optical imaging modality to detect an optical image. The system can also include a display device to display an enhanced gamma image created based on a function of the optical image. The enhanced gamma image illustrates a characteristic of a disease in the field of view (e.g., a lymphatic pathway, a sentinel lymph node target, or a satellite disease state).
    Type: Grant
    Filed: June 20, 2016
    Date of Patent: December 4, 2018
    Assignees: THE CLEVELAND CLINIC FOUNDATION, THE UNIVERSITY OF AKRON
    Inventors: Yang Liu, Francis A. Papay
  • Patent number: 10136869
    Abstract: Presented herein are efficient and reliable systems and methods for calculating and extracting three-dimensional central axes of bones of animal subjects—for example, animal subjects scanned by in vivo or ex vivo microCT platforms—to capture both the general and localized tangential directions of the bone, along with its shape, form, curvature, and orientation. With bone detection and segmentation algorithms, the skeletal bones of animal subjects scanned by CT or microCT scanners can be detected, segmented, and visualized. Three dimensional central axes determined using these methods provide important information about the skeletal bones.
    Type: Grant
    Filed: March 25, 2016
    Date of Patent: November 27, 2018
    Assignee: PerkinElmer Health Sciences, Inc.
    Inventors: Ali Behrooz, Joshua Kempner
  • Patent number: 10140712
    Abstract: In part, the disclosure relates to methods of stent strut detection relative to a side branch region using intravascular data. In one embodiment, detecting stent struts relative to jailed side branches is performed using a scan line-based peak analysis. In one embodiment, false positive determinations relating to stent struts are analyzed using a model strut.
    Type: Grant
    Filed: December 18, 2015
    Date of Patent: November 27, 2018
    Assignee: LIGHTLAB IMAGING, INC.
    Inventor: Sonal Ambwani
  • Patent number: 10140713
    Abstract: Locating morphology in a tissue sample is achieved with devices and methods involving storage of a plurality of feature vectors, each associated with a specific named superpixel of a larger image of a tissue sample from a mammalian body. A microscope outputs, in some embodiments, a live image of an additional tissue sample or a digitized version of the output is used. At least one superpixel of the image is converted into a feature vector and a nearest match between the first feature vector and the plurality of stored feature vectors is made. A first name suggestion is then made based on the nearest match comparison to a store feature vector. Further, regions of interest within the image can be brought to a viewer's attention based on their past history of selection, or that of others.
    Type: Grant
    Filed: December 26, 2017
    Date of Patent: November 27, 2018
    Inventors: Edward M. Schwalb, Tammy April Schwalb
  • Patent number: 10130324
    Abstract: According to one embodiment, an image analysis device includes a parameter value acquisition unit, a color allocation unit and a time phase image generation unit. The parameter value acquisition unit acquires a parameter value per pixel, on the basis of time variation of pixel values per pixel corresponding to the same region of an object in image data of a plurality of sequential DSA images. The color allocation unit generates a color map in which a (chromatic) color in accordance with the parameter value is allocated per pixel corresponding to the same region of the object. The time phase image generation unit generates color image data of time phase images respectively corresponding to a plurality of time phases, by reflecting information in accordance with pixel values of the DSA images to each pixel of the color map.
    Type: Grant
    Filed: October 27, 2017
    Date of Patent: November 20, 2018
    Assignee: TOSHIBA MEDICAL SYSTEMS CORPORATION
    Inventors: Ryoichi Nagae, Yoshinori Shimizu, Nobuo Kobayashi, Keisuke Nakamura, Kunio Shiraishi
  • Patent number: 10126439
    Abstract: In quantitative SPECT with multiple photopeaks, the combination for the multiple photopeaks is performed within or as part of reconstruction rather than post-reconstruction. Reconstruction is performed iteratively, so the combination for the multiple photopeaks is performed within the iteration loop of the reconstruction, such as combining back projected feedback of the different photopeaks for updating the volume.
    Type: Grant
    Filed: June 18, 2015
    Date of Patent: November 13, 2018
    Assignee: Siemens Medical Solutions USA, Inc.
    Inventors: Jun Ma, Alexander Hans Vija, Amos Yahil, Xing Rong
  • Patent number: 10127675
    Abstract: Systems and methods for generating a locally adaptive threshold image for foreground detection performing operations including creating a saliency edge strength image or layer indicating edge or border pixels of the nuclei by performing tensor voting on pixels neighboring the initial edge pixels within an image region to refine true edges are featured. Further, for each of a plurality of regions or blocks of the image, an adaptive threshold image is determined by sampling a foreground pixel and a background pixel for each initial edge pixel or refined edge pixel, generating histograms for both background and foreground saliency (or gradient magnitude) modulated histograms, determining a threshold range for each block of the image, and interpolating the threshold at each pixel based on the threshold range at each block. Comparing the input image with the resulting locally adaptive threshold image enables extraction of significantly improved foreground.
    Type: Grant
    Filed: December 21, 2016
    Date of Patent: November 13, 2018
    Assignee: Ventana Medical Systems, Inc.
    Inventors: Christophe Chefd'hotel, Srinivas Chukka, Xiuzhong Wang
  • Patent number: 10127664
    Abstract: Embodiments relate to digital image processing for diagnosis of a subject. More specifically, the embodiments relate to automation of diagnoses through data interpretation. An image is acquired from the subject. Elements are recognized within the image based on morphological features. The image is compared to learned data. Based on the comparison, a probability of a potential diagnosis(es) is calculated. A diagnosis of the subject is determined based on the potential diagnosis(es) and the calculated probability. The diagnosis may be changed based on a new image acquired from the subject.
    Type: Grant
    Filed: November 21, 2016
    Date of Patent: November 13, 2018
    Assignee: International Business Machines Corporation
    Inventors: Anita Govindjee, Lakshminarayanan Krishnamurthy, Niyati Parameswaran, Shanker Parameswaran
  • Patent number: 10123757
    Abstract: An overall controller of a console acquires a radiation image of an imaging subject captured by a radiation image capture device for radiographic imaging. The overall controller also acquires body thickness information indicating a body thickness of the imaging subject in a direction in which radiation passes through. The overall controller also adds to the radiation image an assist line image that have would be expected to be obtained if a predetermined member had been disposed and captured at a position inside the imaging subject determined based on the acquired body thickness information, or at a position between the imaging subject and the radiation image capture device.
    Type: Grant
    Filed: December 12, 2016
    Date of Patent: November 13, 2018
    Assignee: FUJIFILM CORPORATION
    Inventor: Takashi Tajima
  • Patent number: 10127690
    Abstract: A positron emission tomography (PET) imaging system (10) includes a singles unit (24), a delay unit (26), a scaling unit (28), and a reconstruction unit (30). The singles unit (24) is configured to generate a correction sinogram of random coincidences defined by a coincidence time window tw and a time period t based on rij=2 t si sj where rij is an estimate of the random coincidences in the time period t between singles at detector locations si and sj. The delay unit (26) is configured to determine delay coincidences in the time period t defined by a delay coincidence time window of a paired coincidences including tw to 2 tw. The scaling unit (28) is configured to scale the correction sinogram of random coincidences based on the delay coincidences. The reconstruction unit (30) is configured to iteratively reconstruct one or more images based on the scaled random sinogram and a prompt sinogram for the time period t.
    Type: Grant
    Filed: April 23, 2015
    Date of Patent: November 13, 2018
    Assignee: KONINKLIJKE PHILIPS N.V.
    Inventors: Jinghan Ye, Xiyun Song
  • Patent number: 10127655
    Abstract: Provided is a method of operating a medical imaging apparatus, comprising: acquiring a first image of a first type corresponding to a first respiratory state of an object; determining motion information of the object with respect to a respiratory state, based on first and second images of a second type respectively corresponding to the first respiratory state and a second respiratory state of the object; and generating a second image of the first type corresponding to the second respiratory state by applying the motion information to the first image of the first type.
    Type: Grant
    Filed: June 1, 2016
    Date of Patent: November 13, 2018
    Assignee: SAMSUNG MEDISON CO., LTD.
    Inventors: Ji-won Ryu, Jae-il Kim, Won-chul Bang, Young-taek Oh, Kyong-joon Lee, Jung-woo Chang, Ja-yeon Jeong
  • Patent number: 10120980
    Abstract: Improved pulmonary embolism (PE) detection may be obtained through computer aided-diagnosis. In particular, PE detection may be accomplished through patient-level diagnosis, embolus-level detection, or a combination of the two. Patient-level diagnosis operates to quickly exclude non-PE patients and dispatch PE-patients to treatment. Embolus-level detection operates to localize individual emboli to support personalized medicine via risk stratification. Multiple instance-based learning (MIBL) classification at the patient level explores the key observation that once any TP candidate of a patient is classified as positive, the patient is identified as PE positive. That is, MIBL focuses on correct classification of patients rather than individual candidates, to effectively and rapidly distinguish between PE patients and non-PE patients.
    Type: Grant
    Filed: January 27, 2015
    Date of Patent: November 6, 2018
    Assignee: Arizona Board of Regents on Behalf of Arizona State University
    Inventor: Jianming Liang
  • Patent number: 10115039
    Abstract: A method and apparatus for learning based classification of vascular branches to distinguish falsely detected branches from true branches is disclosed. A plurality of overlapping fixed size branch segments are sampled from branches of a detected centerline tree of a target vessel extracted from a medical image of a patient. A plurality of 1D profiles are extracted along each of the overlapping fixed size branch segments. A probability score for each of the overlapping fixed size branch segments is calculated based on the plurality of 1D profiles extracted for each branch segment using a trained deep neural network classifier. The trained deep neural network classifier may be a convolutional neural network (CNN) trained to predict a probability of a branch segment being fully part of a target vessel based on multi-channel 1D input.
    Type: Grant
    Filed: March 1, 2017
    Date of Patent: October 30, 2018
    Assignee: Siemens Healthcare GmbH
    Inventors: Mehmet Akif Gulsun, Yefeng Zheng, Gareth Funka-Lea, Mingqing Chen
  • Patent number: 10109081
    Abstract: There is described herein a method for recovering missing information in diffusion magnetic resonance imaging (dMRI) data. The data are modeled according to the theory of moving frames and regions where frame information is missing are reconstructed by performing diffusions into the regions. Local orthogonal frames computed along the boundary of the regions are rotated into the regions. Connection parameters are estimated at each new data point obtained by a preceding rotation, for application to a subsequent rotation.
    Type: Grant
    Filed: May 13, 2016
    Date of Patent: October 23, 2018
    Assignee: THE ROYAL INSTITUTION FOR THE ADVANCEMENT OF LEARNENG / MGGILL UNIVERSITY
    Inventors: Kaleem Siddiqi, Emmanuel Piuze-Phaneuf, Jon Sporring
  • Patent number: 10108002
    Abstract: Provided is an optical scanning image forming apparatus, including: a light source section; an illumination scanning section scanning illumination light from the light source section and irradiating the illumination light onto an object; a light detection section detecting detection light from the object; a calculation section calculating a drive waveform for providing a light scanning pattern to be formed by the illumination scanning section; and a coordinate for image construction; and an image drawing section drawing an image based on the detection light detected by the light detection section and the coordinate for image construction, the drive waveform consisting of, in a predetermined period, a plurality of frames of different phases. Also provided is an optical scanning image forming method.
    Type: Grant
    Filed: June 24, 2016
    Date of Patent: October 23, 2018
    Assignee: OLYMPUS CORPORATION
    Inventor: Junichi Nishimura
  • Patent number: 10098557
    Abstract: A system and method for cardiac activation imaging includes non-invasively or minimally invasively acquiring data about an electrical activation of a heart of a subject using at least one sensor. An activation image of the heart of the subject is reconstructed using a weighted sparse constrained reconstruction.
    Type: Grant
    Filed: November 17, 2014
    Date of Patent: October 16, 2018
    Assignee: Regents of the University of Minnesota
    Inventors: Bin He, Long Yu
  • Patent number: 10102451
    Abstract: Systems and methods are provided for generating a pseudo-CT prediction model using multi-channel MR images. An exemplary system may include a processor configured to retrieve training data including multiple MR images and at least one CT image for each of a plurality of training subjects. For each training subject, the processor may determine at least one tissue parameter map based on the multiple MR images and obtain CT values based on the at least one CT image. The processor may also generate the pseudo-CT prediction model based on the tissue parameter maps and the CT values of the plurality of training subjects.
    Type: Grant
    Filed: October 13, 2015
    Date of Patent: October 16, 2018
    Assignee: Elekta, Inc.
    Inventor: Xiao Han
  • Patent number: 10102650
    Abstract: Model-based scatter correction is used in SPECT with a non-parallel-hole collimator. Model-based scatter correction uses scatter kernels based on simulation to model the scatter for a given system and patient. For non-parallel-hole collimators, the measured sensitivity and measured vector maps are used in the modeling of scatter. The measured sensitivity is used to normalize the scatter kernels simulated for a parallel-hole collimator rather than attempting to simulate scatter with the complicated arrangement of holes. The measured vector maps are used to accurately project the model-based scatter sources into a data or emissions space.
    Type: Grant
    Filed: May 22, 2017
    Date of Patent: October 16, 2018
    Assignee: Siemens Medical Solutions USA, Inc.
    Inventors: Xing Rong, Alexander Hans Vija
  • Patent number: 10102633
    Abstract: A method for segmenting a vessel from an image data that includes accessing the image data from which the vessel is segmented through a user display interface. A first seed point is then received from a user, the first seed point placed by the user on a first location on the image data. A second seed point is further received from the user, the second seed point placed by the user on a second location on the image data.
    Type: Grant
    Filed: December 30, 2015
    Date of Patent: October 16, 2018
    Assignee: HYLAND SWITZERLAND SARL
    Inventors: Ingmar Bitter, Raghavendra Chandrashekara, Sandra Stapleton, Sameer Zaheer
  • Patent number: 10098533
    Abstract: An AMD prediction model utilizes an OCT image estimation model. The OCT image estimation module is created by segmenting an OCT image to generate an OCT projection image for each of multiple biological layers; extracting from each of the generated OCT projection images a first set of features; extracting a second set of features from an input retinal fundus image; for each respective biological layer, registering the input retinal fundus image to the respective OCT projection image by matching at least some of the second set of features with corresponding ones of the first set of features; repeating the above with changes to the input retinal fundus image; and modelling how the changes to the input retinal fundus image are manifest at the correspondingly registered projection images. Estimated OCT projection images can then be generated for the multiple biological layers from a given retinal fundus image.
    Type: Grant
    Filed: December 27, 2017
    Date of Patent: October 16, 2018
    Assignee: International Business Machines Corporation
    Inventors: Rajib Chakravorty, Rahil Garnavi, Dwarikanath Mahapatra, Pallab Roy, Suman Sedai
  • Patent number: 10102651
    Abstract: According to an embodiment, a device includes first and second generators, a detector, and a corrector. The first generator is configured to generate a first image based on data corresponding to photons with a first energy from among data that is obtained based on an energy of radiation that has passed through a subject. The second generator is configured to generate a second image based on data corresponding to photons with a second energy. The detector is configured to detect, in the second image, a second block having a similar pattern of pixel values to a first block included in the second image. The corrector is configured to correct pixel values of a third block in the first image corresponding to the first block based on new pixel values of the third block that are calculated by using pixel values included in a fourth block in the first image.
    Type: Grant
    Filed: March 26, 2018
    Date of Patent: October 16, 2018
    Assignee: Toshiba Medical Systems Corporation
    Inventors: Takashi Ida, Toshiyuki Ono, Shuhei Nitta, Taichiro Shiodera, Hidenori Takeshima, Tomoyuki Takeguchi, Hiroaki Nakai
  • Patent number: 10102682
    Abstract: A system and method for visualizing data obtained by performing a three-dimensional scan with penetrating radiation. Raw density arrays are formed from the scan, each raw density array being a three-dimensional array. A processed density array is formed by one or more operations, such as taking the difference between two raw density arrays, rotating the processed density array, multiplying the processed density array by a front-lighting array, and projecting the processed density array onto a plane to form an image, the projecting including calculating one or more of a plurality of statistics for each of a set of vectors each corresponding to a pixel of the image, the plurality of statistics including a vector mean, a vector maximum, and a vector standard deviation.
    Type: Grant
    Filed: April 17, 2017
    Date of Patent: October 16, 2018
    Assignee: RAYTHEON COMPANY
    Inventors: Raymond Samaniego, John L. Tomich
  • Patent number: 10095919
    Abstract: An image processing apparatus, an image processing method, and a storage medium are shown. According to one implementation, the image processing apparatus includes the following. A detecting unit detects a subject in a moving image. A clipping unit clips a region corresponding to the subject detected by the detecting unit from each frame image composing the moving image. A setting unit sets a planned clipping region to be newly clipped by the clipping unit based on at least one of a position and a size of a region corresponding to the subject already clipped by the clipping unit.
    Type: Grant
    Filed: February 4, 2016
    Date of Patent: October 9, 2018
    Assignee: CASIO COMPUTER CO., LTD.
    Inventors: Masanori Ishihara, Kei Ideguchi
  • Patent number: 10096094
    Abstract: Methods and systems are described for removing reflective artifacts from an imaging model. An x-ray detector captures x-ray images that include a structure and an imaging device captures a surface scan of the same structure. An image processor constructs a three-dimensional CT model of the structure from the x-ray images and constructs a three-dimensional surface model of the structure from the surface scan. The image processor is configured to resize and orient the surface model and/or the CT model so that they are the same scale and orientation, overlay the surface model onto the CT model, and detect data points in the combined data set that extend beyond a surface of the structure in the surface model. The detected data points represent artifacts in the CT model and are adjusted by interpolation to produce an artifact-reduced CT model.
    Type: Grant
    Filed: December 26, 2017
    Date of Patent: October 9, 2018
    Assignee: Dental Imaging Technologies Corporation
    Inventors: Bradley S. Carlson, Edward Marandola, David A. Sebok, Uwe Mundry
  • Patent number: 10096109
    Abstract: A method of improving diagnostic and functional imaging is provided by obtaining at least two input images of a subject, using a medical imager, where each input image includes a different contrast, generating a plurality of copies of the input images using non-local mean (NLM) filtering, using an appropriately programmed computer, where each input image copy of the subject includes different spatial characteristics, obtaining at least one reference image of the subject, using the medical imager, where the reference image includes imaging characteristics that are different form the input images of the subject, training a deep network model, using data augmentation on the appropriately programmed computer, to adaptively tune model parameters to approximate the reference image from an initial set of the input and reference images, with the goal of outputting an improved quality image of other sets of low SNR low resolution images, for analysis by a physician.
    Type: Grant
    Filed: March 31, 2017
    Date of Patent: October 9, 2018
    Assignee: The Board of Trustees of the Leland Stanford Junior University
    Inventors: Greg Zaharchuk, Enhao Gong, John M. Pauly
  • Patent number: 10089752
    Abstract: In an approach to tracking markers in one or more images, one or more computer processors identify objects that exist in more than one image from a plurality of images. The one or more computer processors analyze the identified objects for one or more physical characteristics. The one or more computer processors assign a marker to at least one object of the identified objects on at least one image of the more than one image, wherein the marker is annotated based upon the one or more physical characteristics of the object of the identified objects. The one or more computer processors store the more than one images, analysis data, and marker data associated with the identified objects and one or more markers. The one or more computer processors manipulate the one or more images based on a change in the objects across the more than one image.
    Type: Grant
    Filed: December 21, 2017
    Date of Patent: October 2, 2018
    Assignee: International Business Machines Corporation
    Inventors: Mark D. Bronkalla, Murray A. Reicher, James G. Thompson
  • Patent number: 10088545
    Abstract: For prospective motion correction in magnetic resonance imaging, first magnetic resonance data that map a first sub-region of a region of interest are acquired. Motion correction parameters are determined based on a comparison of at least the first magnetic resonance data with reference magnetic resonance data that map the region of interest. Second magnetic resonance data that map a second sub-region of the region of interest are determined using prospective motion correction based on the motion correction parameters. A magnetic resonance image is determined based on the first magnetic resonance data and based on the second magnetic resonance data.
    Type: Grant
    Filed: September 17, 2015
    Date of Patent: October 2, 2018
    Assignee: Siemens Aktiengesellschaft
    Inventor: Thomas Beck
  • Patent number: 10089736
    Abstract: A local high-resolution imaging method and apparatus for a three-dimensional (3D) skeletal image is provided. The method includes determining a volume of interest (VOI) to perform high-resolution imaging from the 3D skeletal image in which an object to be inspected is captured, localizing the VOI based on a finite element method (FEM), and setting a multi-resolution constraint based on a bone mineral density (BMD) between the 3D skeletal image and the localized VOI and reconstructing a skeletal image in which high-resolution imaging is performed on the localized VOI.
    Type: Grant
    Filed: October 21, 2016
    Date of Patent: October 2, 2018
    Assignee: Korea Advanced Institute of Science and Technology
    Inventors: InGwun Jang, Jung Jin Kim
  • Patent number: 10083515
    Abstract: A method for segmenting a medical image. The method comprises providing a registration of a medical image depicting a plurality of bones with a skeletal atlas mapping an exemplary skeletal structure having a plurality of exemplary bones, identifying at least one component having at least one anatomical characteristic indicative of a predefined organ in the medical image, each the at least one component depicting at least one of the plurality of bones, and segmenting at least one region of interest (ROI) around the at least one component within the medical image according to at least one respective the exemplary bone pertaining to the predefined organ.
    Type: Grant
    Filed: November 24, 2009
    Date of Patent: September 25, 2018
    Assignee: Algotec Systems Ltd.
    Inventors: Yaron Ostrovsky-Berman, Tiferet Ahavah Gazit
  • Patent number: 10083543
    Abstract: Method and/or apparatus embodiments can process volume image data of a subject. An exemplary method includes obtaining a first group of two-dimensional radiographic images of the subject, wherein each of the images is obtained with a detector and a radiation source at a different scan angle. The method arranges image data from the first group of images in an image stack so that corresponding pixel data from the detector is in register for each of the images in the image stack. Pixels that represent metal objects are segmented from the image stack and data replaced for at least some of the segmented pixels to generate a second group of modified two-dimensional radiographic images. The second group of images is combined with the first group to generate a three-dimensional volume image according to the combined images and an image slice from the three-dimensional volume image is displayed.
    Type: Grant
    Filed: December 19, 2014
    Date of Patent: September 25, 2018
    Assignee: Carestream Dental Technology Topco Limited
    Inventors: Dong Yang, Lawrence A. Ray, Andre Souza, Alexandre X. Falcao