Biomedical Applications Patents (Class 382/128)
  • Patent number: 9898839
    Abstract: A medical image diagnosis apparatus emits radiation to a breast as a subject, detects radiation that has passed through the subject, and generates three-dimensional image data including a plurality of tomographic images of the subject. The medical image diagnosis apparatus includes an image generator, a setting unit, an image detector, and a display controller. The image generator projects the three-dimensional image data in a predetermined direction to generate a two-dimensional image. The setting unit sets a region of interest in the two-dimensional image. Based on the region of interest and a corresponding region that corresponds to the region of interest in each of the tomographic images, the image detector detects a tomographic image including the corresponding region that is similar in pixel value to the region of interest from the three-dimensional image data. The display controller displays the tomographic image detected by the image detector on a display unit.
    Type: Grant
    Filed: March 18, 2015
    Date of Patent: February 20, 2018
    Assignee: Toshiba Medical Systems Corporation
    Inventor: Yoshimasa Kobayashi
  • Patent number: 9895077
    Abstract: A method of analyzing neurophysiological data is disclosed. The method comprises: identifying activity-related features in the data, constructing a brain network activity (BNA) pattern having a plurality of nodes, each representing a feature of the activity-related features, and assigning a connectivity weight to each pair of nodes in the BNA pattern.
    Type: Grant
    Filed: January 18, 2011
    Date of Patent: February 20, 2018
    Assignee: Elminda Ltd.
    Inventors: Goded Shahaf, Amit Reches, Amir B. Geva, Noga Pinchuk, Guy Ben-Bassat, Ayelet Kanter, Revital Shani-Hershkovich, Ronen Gadot, Yaki Stern
  • Patent number: 9898855
    Abstract: The invention provides, in some aspects, a system for implementing a rule derived basis to display image sets. In various embodiments of the invention, the selection of the images to be displayed, the layout of the images, as well as the rendering parameters and styles can be determined using a rule derived basis. In an embodiment of the present invention, the user is presented with images displayed based on their preferences without having to first manually adjust parameters.
    Type: Grant
    Filed: December 15, 2016
    Date of Patent: February 20, 2018
    Assignee: PME IP PTY LTD
    Inventors: Malte Westerhoff, Detlev Stalling
  • Patent number: 9895126
    Abstract: A system and method for quantifying muscle and fat from abdominal image data. An input is configured to receive the abdominal image data from a CT imaging system. A non-transitive computer-readable storage medium having stored thereon instructions. A processor is configured to receive the abdominal image data and access the storage medium to execute instructions. The executed instructions perform automated segmentation of the abdominal image data into at least one of a subcutaneous fat compartment, a muscle compartment, or a visceral fat compartment. One or more of the compartments are compared to a predetermined threshold to identify corresponding boundaries thereof. An area of one or more of the compartments is calculated based on the corresponding boundaries and predetermined threshold. A display is coupled to the processor and configured to display the at least one subcutaneous fat compartment, muscle compartment, or visceral fat compartment on the abdominal image data.
    Type: Grant
    Filed: September 1, 2016
    Date of Patent: February 20, 2018
    Assignee: MAYO FOUNDATION FOR MEDICAL EDUCATION AND RESEARCH
    Inventor: Naoki Takahashi
  • Patent number: 9895128
    Abstract: In order to provide a technique for reducing system noise from an output signal value (measurement data), an X-ray CT apparatus includes an X-ray generation unit that irradiates X-rays to an object, an X-ray detector that detects the X-rays transmitted through the object, a correction processing unit that corrects an output signal from the X-ray detector, and a reconstruction calculating unit that reconstructs an image on the basis of an output from the correction processing unit, in which the X-ray detector includes arranged detection elements, and in which the correction processing unit maintains an average value of output signal values of a plurality of predetermined detection elements centering on a focused detection element among the detection elements, and also reduces a variance of the output signal values of the plurality of predetermined detection elements centering on the focused detection element.
    Type: Grant
    Filed: August 6, 2014
    Date of Patent: February 20, 2018
    Assignee: HITACHI, LTD.
    Inventors: Hisashi Takahashi, Taiga Goto, Koichi Hirokawa
  • Patent number: 9888876
    Abstract: The present invention, referred to as Oasis is Automated Statistical Inference for Segmentation (OASIS), is a fully automated and robust statistical method for cross-sectional MS lesion segmentation. Using intensity information from multiple modalities of MRI, a logistic regression model assigns voxel-level probabilities of lesion presence. The OASIS model produces interpretable results in the form of regression coefficients that can be applied to imaging studies quickly and easily. OASIS uses intensity-normalized brain MRI volumes, enabling the model to be robust to changes in scanner and acquisition sequence. OASIS also adjusts for intensity inhomogeneities that preprocessing bias field correction procedures do not remove, using BLUR volumes. This allows for more accurate segmentation of brain areas that are highly distorted by inhomogeneities, such as the cerebellum.
    Type: Grant
    Filed: March 21, 2013
    Date of Patent: February 13, 2018
    Assignees: The Johns Hopkins University, The Henry M. Jackson Foundation for the Advancement of Military Medicine, Inc., The United States of America, as Represented by the Secretary, Department of Health and Human Services
    Inventors: Ciprian Crainiceanu, Arthur Jeffrey Goldsmith, Dzung Pham, Daniel S. Reich, Navid Shiee, Russell T. Shinohara, Elizabeth M. Sweeney
  • Patent number: 9892564
    Abstract: Augmenting real-time views of a patient with three-dimensional (3D) data. In one embodiment, a method may include identifying 3D data for a patient with the 3D data including an outer layer and multiple inner layers, determining virtual morphometric measurements of the outer layer from the 3D data, registering a real-time position of the outer layer of the patient in a 3D space, determining real-time morphometric measurements of the outer layer of the patient, automatically registering the position of the outer layer from the 3D data to align with the registered real-time position of the outer layer of the patient in the 3D space using the virtual morphometric measurements and using the real-time morphometric measurements, and displaying, in an augmented reality (AR) headset, one of the inner layers from the 3D data projected onto real-time views of the outer layer of the patient.
    Type: Grant
    Filed: March 30, 2017
    Date of Patent: February 13, 2018
    Assignee: NOVARAD CORPORATION
    Inventors: Steven Cvetko, Wendell Arlen Gibby
  • Patent number: 9892343
    Abstract: The present invention relates to a computer-implemented method for classification of a picture to be analyzed, by attribution of a grade thereto, comprising: a) determining the distance between the picture to be analyzed and pictures from a database of graded pictures; b) selecting from within the database of graded pictures a predetermined number of the closest neighboring pictures or neighboring pictures which are at a distance from the picture to be analyzed below a threshold; c) determining the mean of the grades of the selected neighboring pictures; d) attributing the mean grade to the picture to be analyzed; and e) displaying the mean grade attributed to the picture to be analyzed on an output device.
    Type: Grant
    Filed: July 25, 2014
    Date of Patent: February 13, 2018
    Assignee: STATLIFE
    Inventors: Stéphane Ragusa, Valérie Helin
  • Patent number: 9883807
    Abstract: An object information acquiring apparatus includes a probe configured to detect a photoacoustic wave generated from an object irradiated with light, a signal collector configured to generate a first detection signal from the photoacoustic wave, a signal processor configured to generate, from the first detection signal, a second detection signal in which a component having a phase inverted from the phase of a component deriving from the photoacoustic wave is reduced, by using a differential signal of an impulse response of the probe, and an image generator configured to generate image data on the inside of the object using the second detection signal.
    Type: Grant
    Filed: February 4, 2014
    Date of Patent: February 6, 2018
    Assignee: CANON KABUSHIKI KAISHA
    Inventor: Kazuhiko Fukutani
  • Patent number: 9887870
    Abstract: Communication systems are described that use signal constellations, which have unequally spaced (i.e. ‘geometrically’ shaped) points. In many embodiments, the communication systems use specific geometric constellations that are capacity optimized at a specific SNR. In addition, ranges within which the constellation points of a capacity optimized constellation can be perturbed and are still likely to achieve a given percentage of the optimal capacity increase compared to a constellation that maximizes dmin, are also described. Capacity measures that are used in the selection of the location of constellation points include, but are not limited to, parallel decode (PD) capacity and joint capacity.
    Type: Grant
    Filed: September 10, 2012
    Date of Patent: February 6, 2018
    Assignee: Constellation Designs, Inc.
    Inventors: Maged F. Barsoum, Christopher R. Jones
  • Patent number: 9886619
    Abstract: The present invention discloses a fingerprint template and a fingerprint identification method based on fuzzy feature point information. The fingerprint template contains several pieces of incomplete feature point information, including registration information and comparison information, wherein only coordinate information and attribute information of feature points and a value of a polynomial are recorded. In the polynomial P(Xi)=C0+C1Xi+C2Xi2 . . . CnXin, n is an order of the polynomial, and Xi is a numerical value obtained by quantifying one or multiple pieces of feature point information except the registration information in the feature point information and is a coefficient having a certain preset rule. Corresponding feature point information of a scene fingerprint is substituted into the polynomial to figure out C0-Cn, and whether the C0-Cn meet the preset rule is judged to judge whether the scene fingerprint is matched with a template fingerprint.
    Type: Grant
    Filed: December 24, 2014
    Date of Patent: February 6, 2018
    Inventor: Feng Shi
  • Patent number: 9886546
    Abstract: Methods and apparatus are disclosed to label radiology images. An example system includes a processor and a database. In response to receiving a first user input via a data input, the processor is to generate first annotations on a spinal image. The processor is to cause the spinal image having the first annotations to be displayed at a user interface. The processor is to prompt a user to provide second user input identifying an error in the first annotations. In response to receiving the second user input, the processor is to generate second annotations on the spinal image. The second annotations is to correct the error in the first annotations.
    Type: Grant
    Filed: June 26, 2013
    Date of Patent: February 6, 2018
    Assignee: General Electric Company
    Inventors: Ismail Ben Ayed, Dmitry Pavlov, Kumaradevan Punithakumar, Seyed-Parsa Hojjat, Gregory Garvin
  • Patent number: 9886617
    Abstract: Systems and methods are described for providing reliable biometric access control using an optical biometric sensor in a miniaturized form factor. Some implementations include multiple light sources that can illuminate skin or other tissue at multiple locations during a single measurement session. An imaging array can be arranged to form images of the light exiting the tissue only after undergoing diffuse reflectance in the tissue. Some implementations use the images to perform biometric functions. For example, the images can be used to identify an individual, verify identity of an individual, estimate demographic characteristics of an individual, etc. Such biometric functions can further be used to determine and affect access to secured assets.
    Type: Grant
    Filed: May 21, 2015
    Date of Patent: February 6, 2018
    Assignee: HID Global Corporation
    Inventors: Robert K. Rowe, Ryan Eric Martin
  • Patent number: 9886781
    Abstract: To provide an image processing device, a region extraction method, and an image processing method capable of extracting a target region based on minute variations in a concentration value that exist locally and clearly displaying the extracted target region, the image processing device extracts a blood vessel region A from an image to extract a region where a CT value is smaller than an average concentration value of the blood vessel region A as a soft plaque region B. For unextracted soft plaque, a pixel pair is set in a difference region between the region A and the region B, and for each pixel Pj between the pixel pairs, whether or not the pixel value is even smaller than a value slightly smaller than the CT value of the pixel pair is determined. Hence, a portion where a pixel value slightly varies locally is extracted as soft plaque.
    Type: Grant
    Filed: February 18, 2014
    Date of Patent: February 6, 2018
    Assignee: HITACHI, LTD.
    Inventor: Yoshihiro Goto
  • Patent number: 9883093
    Abstract: A method for processing, saving and viewing a digital image of a microscope slide includes inserting a microscope slide into a digital slide scanner connected to an acquisition computer. A pre-scan formed from a plurality of image tiles uploaded to a network server while the pre-scan is being generated. The network server analyzes the image tiles in realtime to identify an area of interest. The acquisition computer generates a high magnification local scan of the area of interest. The local scan is formed from a plurality of local image tiles that are uploaded to the network server while the local scan is being generated. Each local image tile is viewable by a client computer in communication with the computer network while the plurality of local image tiles is being uploaded. A raw final image is then saved on the network server independent of the acquisition computer.
    Type: Grant
    Filed: November 15, 2016
    Date of Patent: January 30, 2018
    Assignee: MIKROSCAN TECHNOLOGIES, INC.
    Inventor: Victor Casas
  • Patent number: 9881426
    Abstract: An electronic apparatus for use in selecting a patient interface device and including a geometric fit score determining unit (42) configured to calculate a geometric fit score for each of one or more of patient interface devices, a patient criteria fit score determining unit (44) configured to calculate a patient criteria fit score for each of the one or more patient interface devices, and an overall fit score determining unit (46) configured to calculate an overall fit score for each of the one or more patient interface devices based on the calculated geometric fit score and the calculated patient criteria fit score for each of the one or more patient interface devices.
    Type: Grant
    Filed: April 25, 2014
    Date of Patent: January 30, 2018
    Assignee: KONINKLIJKE PHILIPS N.V.
    Inventors: Ruud Vlutters, Karl Catharina Van Bree
  • Patent number: 9881191
    Abstract: A method of controlling operation of cataloged smart devices includes generating an image of an item using a camera of a mobile computing device, the item corresponding to a smart device, identifying the item in the image, establishing a link to the smart device in response to identifying the item in the image, and controlling the smart device using the mobile computing device after establishing the link to the smart device.
    Type: Grant
    Filed: December 14, 2015
    Date of Patent: January 30, 2018
    Assignee: LEADOT INNOVATION, INC.
    Inventor: Justin Wang
  • Patent number: 9880243
    Abstract: A method includes applying a pulse train to a spin system in a scanner. The pulse train has a plurality of discontinuities in a time domain. The method includes receiving a response from the spin system. The response corresponds to a gated signal. The method includes accessing a correction factor corresponding to the scanner. The method includes calculating a correction to the response based on the correction factor. The method includes generating an output based on the correction.
    Type: Grant
    Filed: June 19, 2012
    Date of Patent: January 30, 2018
    Assignee: Regents of the University of Minnesota
    Inventors: Curtis A. Corum, Steen Moeller, Djaudat S. Idiyatullin, Ryan Chamberlain, Michael G. Garwood
  • Patent number: 9881355
    Abstract: Embodiments of the present invention can resolve molecules beyond the optical diffraction limit in three dimensions. A double-helix point spread function can be used to in conjunction with a microscope to provide dual-lobed images of a molecule. Based on the rotation of the dual-lobed image, the axial position of the molecule can be estimated or determined. In some embodiments, the angular rotation of the dual-lobed imaged can be determined using a centroid fit calculation or by finding the midpoints of the centers of the two lobes. Regardless of the technique, the correspondence between the rotation and axial position can be utilized. A double-helix point spread function can also be used to determine the lateral positions of molecules and hence their three-dimensional location.
    Type: Grant
    Filed: February 12, 2014
    Date of Patent: January 30, 2018
    Assignee: THE REGENTS OF THE UNIVERSITY OF COLORADO
    Inventors: Rafael Piestun, Sri Rama Prasanna Pavani, Michael A. Thompson, Julie S. Biteen, William E. Moerner
  • Patent number: 9881364
    Abstract: An image processing apparatus includes a reflectivity image generation unit that generates a reflectivity image in which a reflectivity component of an original image is used as a pixel value, from the original image, a determining unit that determines a degree of maintenance of at least one of a dark part and a bright part of the original image using the original image and a degree of enhancement of the reflectivity component of the original image and an enhancement image generation unit that generates an enhancement image in which the reflectivity component of the original image is enhanced using the reflectivity image, the degree of enhancement, and the degree of maintenance.
    Type: Grant
    Filed: August 2, 2016
    Date of Patent: January 30, 2018
    Assignee: FUJI XEROX CO., LTD.
    Inventors: Shota Narumi, Makoto Sasaki
  • Patent number: 9881126
    Abstract: In a method and system for populating multi-segment layouts with related multimodal medical images, a relationship is determined between subsets of the multimodal medical images. The relationship is used to determine selected subsets initially selected for display in respective segments of a segmented display. Appropriate images relating to selected subsets are used to populate the remaining display segments.
    Type: Grant
    Filed: December 1, 2014
    Date of Patent: January 30, 2018
    Assignee: Siemens PLC
    Inventors: Joan Alvarez Del Castillo, Kevin Scott Hakl, Christian Mathers, Abhinav Shanker
  • Patent number: 9881368
    Abstract: The invention provides an image processing method in a diagnostic apparatus of diagnosing a disease using a captured image of an affected area, comprising the steps of: (i) separating the captured image memorized into a brightness component and a color information component (Step S131); (ii) separating the brightness component into a base component and a detail component (Step S132); (iii) performing a highlighting process on the base component and/or the detail component (Step S133-S140); and (iv) restoring a brightness component from a highlighted base component and the detail component, and/or from the base component and a highlighted detail component, and using the restored brightness component and the color information component to generate a highlighted image (Step S141).
    Type: Grant
    Filed: September 21, 2015
    Date of Patent: January 30, 2018
    Assignee: CASIO COMPUTER CO., LTD.
    Inventor: Mitsuyasu Nakajima
  • Patent number: 9875544
    Abstract: The present invention is a method to register 3D image data with fluoroscopic images of the chest of a patient. The ribs and spine, which are visible in the fluoroscopic images, are analyzed and a rib signature or cost map is generated. The rib signature or cost map is matched to corresponding structures of the 3D image data of the patient. Registration is evaluated by computing a difference between the fluoroscopic image and a virtual fluoroscopic projected image of the 3D data. Related systems are also described.
    Type: Grant
    Filed: August 7, 2014
    Date of Patent: January 23, 2018
    Assignee: BRONCUS MEDICAL INC.
    Inventors: Lav Rai, Jason David Gibbs, Henky Wibowo
  • Patent number: 9872759
    Abstract: Devices and methods for assisting valve function, replacing venous valves, and predicting valve treatment successes. In at least one exemplary embodiment of an endograft body configured for expansion within a luminal organ of the present disclosure, the endograft body comprises (a) a first portion having a proximal end defining a proximal end aperture and a distal end defining a distal end aperture, the first portion configured to increase a velocity of fluid flowing therethrough, (b) a second portion having a second portion proximal end defining a second portion proximal end aperture and a second portion distal end defining a second portion distal end aperture.
    Type: Grant
    Filed: September 17, 2012
    Date of Patent: January 23, 2018
    Assignee: 3DT Holdings, LLC
    Inventor: Ghassan S. Kassab
  • Patent number: 9875569
    Abstract: In rendering in medical imaging, the MIP and VRT modes are emulated using physically-based rendering, such as Monte Carlo ray tracing. By weighting the rendering based on user or other input, where along a continuum of MIP to VRT to render is selected. A sequence of different images may be rendered with different settings at different points on the continuum using the same window level, classification, or other parameters.
    Type: Grant
    Filed: March 8, 2016
    Date of Patent: January 23, 2018
    Assignee: Siemens Healthcare GmbH
    Inventors: Daphne Yu, Feng Qiu, Lining Yang
  • Patent number: 9875538
    Abstract: A device and method integrates a lesion stager in a reporting tool. The method includes receiving a user input. The user input is image data including at least one variable value. The variable value is indicative of a variable parameter of the image data. The method includes associating each of the at least one variable value with a corresponding variable parameter to generate at least one variable-value pair. The method includes determining a computed output value as a function of select ones of the at least one variable-value pair.
    Type: Grant
    Filed: July 28, 2014
    Date of Patent: January 23, 2018
    Assignee: Koninklijke Philips N.V.
    Inventors: Merlijn Sevenster, Paul Joseph Chang
  • Patent number: 9875539
    Abstract: A medical image processing apparatus includes, an unit (12) extracting a blood vessel wall region from the image in a range including an aneurysm in an object, an unit (13) calculating the blood vessel diameter change rates of the neck portions of the aneurysm, blood vessel curvature, and blood vessel flattening ratio at each of discrete points on a blood vessel region based on the extracted blood vessel region, an unit (14) extracting, from discrete points, feature points at each of which at least one of a blood vessel diameter change rate, blood vessel curvature, and blood vessel flattening ratio exceeds a corresponding one of thresholds and decide a range for the indwelling of a stent graft in accordance with the extracted feature points, and a display unit (19) superimposing and display unrecommended ranges on a stored image.
    Type: Grant
    Filed: September 6, 2016
    Date of Patent: January 23, 2018
    Assignee: TOSHIBA MEDICAL SYSTEMS CORPORATION
    Inventors: Kazuo Imagawa, Ryuji Zaiki, Takayuki Ishikawa, Masaki Kobayashi
  • Patent number: 9875540
    Abstract: A medical data processing method of matching a medical image of an anatomical structure of a patient's body with an atlas-based representation of the anatomical structure, the method being constituted to be executed by a computer and comprising the following steps; acquiring patient image data describing a medical image representation of the anatomical structure in the medical image; determining, based on the patient image data, patient substructure data describing a plurality of patient substructure representations each describing a different patient substructure of the anatomical structure; acquiring general substructure data describing a general substructure representation of each of a plurality of general substructures for each of the patient substructures; determining, for each of the patient substructures and based on the patient substructure data and the general substructure data, substructure matching data describing a matching general substructure representation which matches the respective patient s
    Type: Grant
    Filed: July 11, 2013
    Date of Patent: January 23, 2018
    Assignee: Brainlab AG
    Inventors: Andreas Blumhofer, Bálint Várkuti, Stefan Achatz
  • Patent number: 9870576
    Abstract: Concepts and technologies are disclosed herein for detecting body language via bone conduction. According to one aspect, a device can detect body language of a user. The device can generate a signal and send the signal to a sensor network connected to a user. The device can receive a modified signal from the sensor network and compare the modified signal to a body language reference model. The device can determine the body language of the user based upon comparing the modified signal to the body language reference model.
    Type: Grant
    Filed: October 29, 2013
    Date of Patent: January 16, 2018
    Assignee: AT&T Intellectual Property I, L.P.
    Inventors: Christopher Baldwin, Brian S. Amento
  • Patent number: 9870438
    Abstract: The invention concerns a computerized method for producing a two-dimensional plant model of a modular production plant for producing a chemical product, the production plant comprising at least two processing modules, which can be connected to one another for production purposes, and at least one processing container in which the processing modules can be accommodated at least partially, as required, wherein, for each processing container, a common two-dimensional container model (2) of its the base area (3) and of the base area (3) of a container environment at least partially surrounding the processing container and of predefinable size being generated, wherein, for each processing module, a two-dimensional module model (5) of its base area is generated, wherein the container model (2) and the module model (5) are divided into fields (1, 4) which are of equal size and preferably square, there being assigned to each field (4) of a module model (5) a module property concerning the occupancy of the particular
    Type: Grant
    Filed: December 18, 2013
    Date of Patent: January 16, 2018
    Assignees: BAYER TECHNOLOGY SERVICES GMBH, BAYER AKTIENGESELLSCHAFT
    Inventors: Lars Frye, Dietmar Günther, Nicolai Krasberg
  • Patent number: 9870294
    Abstract: Dimensionality reduction, such as principal component analysis, may be performed against a time series of performance observations for a computer application. A visual representation of the results may be displayed in one, two, or three dimensions, and often show clusters of operational behavior. The representation may be animated to show a sequence of observations and how the behavior of an application may change from one cluster of operation to another. The representation may be further applied to show both a historical view of the observations and new observations. The time series may contain performance and operational data, as well as metadata observed from a computer application.
    Type: Grant
    Filed: January 13, 2015
    Date of Patent: January 16, 2018
    Assignee: Microsoft Technology Licensing, LLC
    Inventor: Tetsuo Seto
  • Patent number: 9870614
    Abstract: A fully automatic brain tumor segmentation and classification method and system improve the healthcare experience with machine intelligence. The automatic brain tumor segmentation and classification method and system utilize whole tumor segmentation and multi-class tumor segmentation to provide accurate analysis.
    Type: Grant
    Filed: July 25, 2016
    Date of Patent: January 16, 2018
    Assignee: Sony Corporation
    Inventors: Chen-Rui Chou, Bi Song, Ming-Chang Liu
  • Patent number: 9871960
    Abstract: A method for processing, saving and viewing a digital image of a microscope slide includes inserting a microscope slide into a digital slide scanner connected to an acquisition computer. A pre-scan formed from a plurality of image tiles uploaded to a network server while the pre-scan is being generated. The network server analyzes the image tiles in realtime to identify an area of interest. The acquisition computer generates a high magnification local scan of the area of interest. The local scan is formed from a plurality of local image tiles that are uploaded to the network server while the local scan is being generated. Each local image tile is viewable by a client computer in communication with the computer network while the plurality of local image tiles is being uploaded. A raw final image is then saved on the network server independent of the acquisition computer.
    Type: Grant
    Filed: September 8, 2015
    Date of Patent: January 16, 2018
    Assignee: MIKROSCAN TECHNOLOGIES, INC.
    Inventor: Victor Casas
  • Patent number: 9869740
    Abstract: A method including determining a cerebral ischemia region of a patient based on a magnetic resonance diffusion weighted imaging of the patient; determining a DWI gray scale distribution parameter in a region with low ADC values in the magnetic resonance diffusion weighted imaging; and judging whether the DWI in the region with low ADC values in the magnetic resonance diffusion weighted imaging and the ADC values in the region with low ADC values in the magnetic resonance diffusion weighted imaging are mismatched according to the DWI gray scale distribution parameter in the region with low ADC values in the magnetic resonance diffusion weighted imaging is disclosed. The method provides a more scientific and objective basis for making a decision on whether the acute cerebral ischemia patient should be treated with thrombolysis, thereby improving a cure rate of the cerebral ischemia patient.
    Type: Grant
    Filed: September 26, 2014
    Date of Patent: January 16, 2018
    Assignee: Shenzhen Institutes of Advanced Technology
    Inventors: Qingmao Hu, Huimin Zheng
  • Patent number: 9864046
    Abstract: The mathematical majorize-minimize principle is applied in various ways to process the image data to provide a more reliable image from the backscatter data using a reduced amount of memory and processing resources. A processing device processes the data set by creating an estimated image value for each voxel in the image by iteratively deriving the estimated image value through application of a majorize-minimize principle to solve a maximum a posteriori (MAP) estimation problem associated with a mathematical model of image data from the data. A prior probability density function for the unknown reflection coefficients is used to apply an assumption that a majority of the reflection coefficients are small. The described prior probability density functions promote sparse solutions automatically estimated from the observed data.
    Type: Grant
    Filed: June 16, 2014
    Date of Patent: January 9, 2018
    Assignee: Howard University
    Inventors: John M. M. Anderson, Mandoye Ndoye, Oludotun Ode, Henry C. Ogworonjo
  • Patent number: 9865042
    Abstract: In implementations of the subject matter described herein, the feature maps are obtained by convoluting an input image using a plurality of layers of convolution filters. The feature maps record semantic information for respective regions on the image and only need to be computed once. Segment features of the image are extracted from the convolutional feature maps. Particularly, the binary masks may be obtained from a set of candidate segments of the image. The binary masks are used to mask the feature maps instead of the raw image. The masked feature maps define the segment features. The semantic segmentation of the image is done by determining a semantic category for each pixel in the image at least in part based on the resulting segment features.
    Type: Grant
    Filed: July 17, 2015
    Date of Patent: January 9, 2018
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Jifeng Dai, Kaiming He, Jian Sun
  • Patent number: 9865049
    Abstract: A method for improving image quality is provided. The method includes receiving image data of a substrate, wherein the image data is generated by imaging the substrate, and an image is generated from the image data. The method further includes generating a background representation from a background noise portion of the image, wherein the background portion includes signal information undesired for further processing and generating a background subtracted image by subtracting the background representation from the image. In this way, a separate background image is not needed to subtract the background from the image including the regions-of-interest to improve image quality.
    Type: Grant
    Filed: September 28, 2012
    Date of Patent: January 9, 2018
    Assignee: LIFE TECHNOLOGIES CORPORATION
    Inventors: Francis T. Cheng, Thomas Wessel
  • Patent number: 9864184
    Abstract: Certain aspects pertain to Fourier ptychographic imaging systems, devices, and methods that implement an embedded pupil function recovery.
    Type: Grant
    Filed: December 16, 2014
    Date of Patent: January 9, 2018
    Assignee: California Institute of Technology
    Inventors: Xiaoze Ou, Jaebum Chung, Roarke Horstmeyer, Guoan Zheng, Changhuei Yang
  • Patent number: 9865052
    Abstract: What is disclosed is a system and method for contour-based determination of malignant tissue in a thermal image of a patient for cancer screening. In one embodiment, the method involves receiving a thermal image for cancer screening. Pixels in the thermal image with a higher temperature value are displayed in a first color and pixels with a lower temperature value are displayed in a second color. Pixels with temperature values between the lower and higher temperature values are displayed in gradations of color between the first and second colors. The thermal image is then analyzed to identify a patch of pixels with an elevated temperature relative to a temperature of pixels associated with surrounding tissue. Thereafter, tissue associated with the identified patch is determined to be malignant or non-malignant based a measure of irregularity calculated for boundary contour encompassing that patch of pixels.
    Type: Grant
    Filed: March 18, 2016
    Date of Patent: January 9, 2018
    Inventors: Krithika Venkataramani, Susmija Jabbireddy, Himanshu J. Madhu, Siva Teja Kakileti
  • Patent number: 9855024
    Abstract: A medical diagnostic imaging apparatus includes identification-information-changing circuitry and comparison-result-calculating circuitry. The identification-information-changing circuitry changes identification information given to a plurality of points corresponding to contours of tissue in first medical-image-data in a first medical-image-data group each including a plurality of pieces of medical-image-data of different time phases.
    Type: Grant
    Filed: August 12, 2015
    Date of Patent: January 2, 2018
    Assignee: Toshiba Medical Systems Corporation
    Inventors: Hiroyuki Ohuchi, Yasuhiko Abe
  • Patent number: 9858494
    Abstract: Systems, methods, and non-transitory computer-readable media can obtain data corresponding to a first content item. The first content item can be rendered for display. The first content item can be presented through a display interface. A screenshot image of the display interface can be captured while the first content item is being presented. A determination is made whether the first content item was incompletely rendered based at least in part on the screenshot image.
    Type: Grant
    Filed: December 28, 2015
    Date of Patent: January 2, 2018
    Assignee: Facebook, Inc.
    Inventors: Chih-Tang Chen, Xiaojun Liang, Maher Afif Saba
  • Patent number: 9857446
    Abstract: A method for providing at least one motion corrected magnetic resonance imaging (MRI) image of an object in an MRI system with an array of a plurality of receiving coils is provided. At least one motion navigator signal of the object is provided. Individual navigator data are collected from each of the plurality of receiving coils. Motion estimates are generated for each of the plurality of receiving coils from the collected individual navigator data. A subset of the plurality of coils is found that detects a dominant motion by clustering the generated motion estimates. Only motion estimates from coils in the found subset are used to create a determined motion estimate. At least one MRI image is reconstructed using the determined motion estimate.
    Type: Grant
    Filed: January 14, 2015
    Date of Patent: January 2, 2018
    Assignee: The Board of Trustees of the Leland Stanford Junior University
    Inventors: Tao Zhang, John M. Pauly, Yuxin Chen, Joseph Y. Cheng, Shreyas S. Vasanawala
  • Patent number: 9858668
    Abstract: This invention relates generally to methods and systems for removing an artifact within an image. Typically, the artifact is a guidewire artifact. In one aspect, at least two images of an imaging surface are acquired. Each acquired image comprises a set of data. A guidewire artifact is detected in one of the at least two images. The guidewire artifact is replaced with data representing the imaging surface obtained from another one of the at least two images. In certain embodiments, the at least two images are of the same imaging surface having a guidewire or object causing the artifact moved to a different position.
    Type: Grant
    Filed: October 3, 2013
    Date of Patent: January 2, 2018
    Assignee: VOLCANO CORPORATION
    Inventors: Jesse Jones, Elizabeth Begin, Anuja Nair, Jason Sproul
  • Patent number: 9858666
    Abstract: A medical skin examination device configured to diagnose a skin lesion includes: a first storage unit configured to store an original first skin image related to a dermoscopy structure imaged via a dermoscope; an image conversion unit configured to apply High Dynamic Range (HDR) conversion processing to the first skin image and obtain a second skin image in which the dermoscopy structure is made clear and salient; a second storage unit configured to store the second skin image; and a display control unit configured execute control so as to display at least one of the first skin image and the second skin image.
    Type: Grant
    Filed: February 1, 2017
    Date of Patent: January 2, 2018
    Assignee: CASIO COMPUTER CO., LTD.
    Inventors: Yoshiharu Houjou, Nobuhiro Aoki
  • Patent number: 9858387
    Abstract: A method for vascular assessment is disclosed. The method comprises receiving a plurality of 2D angiographic images of a portion of a vasculature of a subject, and processing the images to produce a stenotic model over the vasculature, the stenotic model having measurements of the vasculature at one or more locations along vessels of the vasculature. The method further comprises obtaining a flow characteristic of the stenotic model, and calculating an index indicative of vascular function, based, at least in part, on the flow characteristic in the stenotic model.
    Type: Grant
    Filed: September 29, 2013
    Date of Patent: January 2, 2018
    Assignee: CathWorks, LTD.
    Inventors: Ifat Lavi, Ran Kornowski, Idit Avrahami, Nessi Benishti, Guy Lavi
  • Patent number: 9858469
    Abstract: The present disclosure relates to characterization of biological samples via modular image analysis. By way of example, the analysis may include extracting plurality of regions of interest from the biological sample from a plurality of image data sets. Each region of interest may include a combination of one or more subsets of an image data set. In one example, an image data set may be generated by image segmentation. After each region of interest is extracted, at least one metric of the region of interest may be determined.
    Type: Grant
    Filed: December 18, 2014
    Date of Patent: January 2, 2018
    Assignee: GE Healthcare Bio-Sciences Corp.
    Inventors: Yousef Al-Kofahi, Brion Daryl Sarachan
  • Patent number: 9858663
    Abstract: An image generation method is described, comprising obtaining a plurality of 2D images through an object to be imaged, obtaining a 3D image data set of the object to be imaged, and registering the 2D images with the 3D image data set. The method then further includes defining an image reconstruction plane internal to the object, being the plane of an image to be reconstructed from the plurality of 2D images. Then, for a pixel in the image reconstruction plane, corresponding pixel values from the plurality of 2D images are mapped thereto, and the mapped pixel values are combined into a single value to give a value for the pixel in the image reconstruction plane. Another aspect of the method provides for clutter removal from the image. In a medical imaging context this can provide for “de-boned” images, allowing soft tissue to be more clearly seen.
    Type: Grant
    Filed: August 1, 2014
    Date of Patent: January 2, 2018
    Assignee: Cydar Limited
    Inventors: Graeme Penney, Tom Carrell, Mazen Alhrishy
  • Patent number: 9858674
    Abstract: A data processing method for determining an enhancing structure of interest within an anatomical body part, wherein the structure of interest exhibits an enhanced signal in an image of the anatomical body part generated by a medical imaging method using a contrast agent, said method being designed to be performed by a computer and comprising a region growing algorithm.
    Type: Grant
    Filed: November 5, 2013
    Date of Patent: January 2, 2018
    Assignee: Brainlab AG
    Inventors: Rainer Lachner, Rowena Thomson, Christina Sladky
  • Patent number: 9852354
    Abstract: Methods and apparatuses for analyzing digital pathology images are provided. The methods and apparatuses may provide estimates of staining intensity and proportion score in regions of interest within an image. Digital pathology images may be scored according to these metrics. The methods and apparatuses disclosed herein utilize various predetermined thresholds, parameters, and models to increase efficiency and permit accurate estimation of characteristics of a stained tissue sample.
    Type: Grant
    Filed: May 1, 2015
    Date of Patent: December 26, 2017
    Assignee: DAKO Denmark A/S
    Inventors: Rohit Jain, Kapil Dhingra, Edward Hartford
  • Patent number: 9844356
    Abstract: A medical image processing apparatus includes a processing circuitry. The processing circuitry obtains volume data including a tubular organ. The processing circuitry extracts the tubular organ from the volume data. The processing circuitry calculates each of a plurality of feature quantities at a plurality of positions in the tubular organ. The processing circuitry calculates a graph indicating a distribution of the plurality of feature quantities at the plurality of positions. The processing circuitry displays the graph and the tubular organ on a display, the displayed graph being aligned with the displayed tubular organ.
    Type: Grant
    Filed: August 20, 2015
    Date of Patent: December 19, 2017
    Assignee: TOSHIBA MEDICAL SYSTEMS CORPORATION
    Inventor: Satoshi Wakai