Patents by Inventor Kilian Koepsell

Kilian Koepsell has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Publication number: 20210106285
    Abstract: A method for clip selection includes receiving through an interface to a medical imaging device, a selection of a diagnostic procedure and a target portion of a mammalian body. Thereafter, the device acquires video clip imagery of the target portion and stores the video clip imagery in an image store. Each video clip of the video clip imagery is then image processed to determine a view and a quality of each video clip and a rule is retrieved from a rules base corresponding to the selected diagnostic procedure and target portion. In this regard, the rule specifies a requisite view and quality of the video clip imagery. Finally, the retrieved rule is applied to the video clip imagery as a filter to produce a subset of video clip imagery satisfying the specified requisite view and quality and the subset of video clip imagery is stored in the image store.
    Type: Application
    Filed: October 20, 2020
    Publication date: April 15, 2021
    Inventors: Charles Cadieu, Ha Hong, Kilian Koepsell, Johan Mathe, Nicolas Poilvert, Michael Cannon, Nathanael Romano, Natalia Bilenko, Charles Chen, Nina Miolane
  • Publication number: 20210106284
    Abstract: A method for clip selection includes receiving through an interface to a medical imaging device, a selection of a diagnostic procedure and a target portion of a mammalian body. Thereafter, the device acquires video clip imagery of the target portion and stores the video clip imagery in an image store. Each video clip of the video clip imagery is then image processed to determine a view and a quality of each video clip and a rule is retrieved from a rules base corresponding to the selected diagnostic procedure and target portion. In this regard, the rule specifies a requisite view and quality of the video clip imagery. Finally, the retrieved rule is applied to the video clip imagery as a filter to produce a subset of video clip imagery satisfying the specified requisite view and quality and the subset of video clip imagery is stored in the image store.
    Type: Application
    Filed: October 20, 2020
    Publication date: April 15, 2021
    Inventors: Charles Cadieu, Ha Hong, Kilian Koepsell, Johan Mathe, Nicolas Poilvert, Michael Cannon, Nathanael Romano, Natalia Bilenko, Charles Chen, Nina Miolane
  • Publication number: 20210052253
    Abstract: An ultrasound guidance dynamic progression method includes selecting a predetermined ultrasound diagnostic workflow in memory of an ultrasound diagnostic computing system, the workflow including a sequence of views of a target organ. The method further includes selecting a first view in the sequence and presenting guidance in a display of the computing system for the first view, for instance visual, audible or haptic feedback. The method yet further includes acquiring imagery in the computing system in association with the first view, and detecting an anomalous feature of the acquired imagery. Finally, the method includes selecting a different view in the sequence as a substitute for a next one of the views in the sequence in response to having detected the anomalous feature, and further presenting different guidance in the display for the different view in lieu of guidance for the next one of the views.
    Type: Application
    Filed: August 19, 2019
    Publication date: February 25, 2021
    Inventors: Charles Cadieu, Michael G. Cannon, Ali Chaudhry, Ha Hong, Kilian Koepsell, Nripesh Parajuli, Nicolas Poilvert
  • Publication number: 20210052255
    Abstract: An ultrasound guidance dynamic mode switching method includes selecting a predetermined ultrasound diagnostic procedure in memory of an ultrasound diagnostic computing system and identifying an operating mode of the system for a first sequence of views stored in the memory as a workflow in correspondence to the selected procedure. The method additionally includes placing the system in the identified operating mode and acquiring imagery of a target organ in association with the views of the first sequence of the workflow. Finally, the method includes detecting in the acquired imagery, a feature of the target organ mapped to a different operating mode, and in response to the detection, displaying a recommendation in a display to change operating modes, placing the system into the different operating mode, and acquiring additional imagery of the target organ utilizing the system in association with a different sequence of additional views of a different workflow.
    Type: Application
    Filed: August 19, 2019
    Publication date: February 25, 2021
    Inventors: Charles Cadieu, Michael G. Cannon, Ali Chaudhry, Ha Hong, Kilian Koepsell, Nripesh Parajuli, Nicolas Poilvert
  • Publication number: 20200336751
    Abstract: An image processing method includes selecting an image in fixed storage of a computer and loading the selected image into memory of the computer. The method further includes representing the loaded image by a processor of the computer in the memory as an initial two-dimensional array of pixel values. Thereafter, the initial two-dimensional array of pixel values may be transformed into a hierarchy of progressively axially decremented two-dimensional arrays of signs and a pair of one-dimensional values for each 2×2 array of signs amongst the decremented two-dimensional arrays of signs. Finally, each of the two-dimensional arrays of signs and each pair of one-dimensional values may be stored in the fixed storage as a compressed form of the selected image.
    Type: Application
    Filed: June 30, 2020
    Publication date: October 22, 2020
    Inventors: Christopher J. Hillar, Ram Mehta, Kilian Koepsell, Charles Garfinkle
  • Patent number: 10806402
    Abstract: A method for clip selection includes receiving through an interface to a medical imaging device, a selection of a diagnostic procedure and a target portion of a mammalian body. Thereafter, the device acquires video clip imagery of the target portion and stores the video clip imagery in an image store. Each video clip of the video clip imagery is then image processed to determine a view and a quality of each video clip and a rule is retrieved from a rules base corresponding to the selected diagnostic procedure and target portion. In this regard, the rule specifies a requisite view and quality of the video clip imagery. Finally, the retrieved rule is applied to the video clip imagery as a filter to produce a subset of video clip imagery satisfying the specified requisite view and quality and the subset of video clip imagery is stored in the image store.
    Type: Grant
    Filed: April 2, 2020
    Date of Patent: October 20, 2020
    Assignee: CAPTION HEALTH, INC.
    Inventors: Charles Cadieu, Ha Hong, Kilian Koepsell, Johan Mathe, Nicolas Poilvert, Michael Cannon, Nathanael Romano
  • Publication number: 20200281535
    Abstract: A method for clip selection includes receiving through an interface to a medical imaging device, a selection of a diagnostic procedure and a target portion of a mammalian body. Thereafter, the device acquires video clip imagery of the target portion and stores the video clip imagery in an image store. Each video clip of the video clip imagery is then image processed to determine a view and a quality of each video clip and a rule is retrieved from a rules base corresponding to the selected diagnostic procedure and target portion. In this regard, the rule specifies a requisite view and quality of the video clip imagery. Finally, the retrieved rule is applied to the video clip imagery as a filter to produce a subset of video clip imagery satisfying the specified requisite view and quality and the subset of video clip imagery is stored in the image store.
    Type: Application
    Filed: April 2, 2020
    Publication date: September 10, 2020
    Inventors: Charles Cadieu, Ha Hong, Kilian Koepsell, Johan Mathe, Nicolas Poilvert, Michael Cannon, Nathanael Romano
  • Publication number: 20200245976
    Abstract: In a method, system and computer program product for retrospective image clip saving for ultrasound imagery, the method includes first repeatedly acquiring different ultrasound image clips of a single view of a target feature through an ultrasound imaging probe of an ultrasound imaging system. Thereafter, each of the acquired different ultrasound image clips may be stored in a buffer of the ultrasound imaging system and a value assigned to each of the image clips according to a measured characteristic. A save-best-clip mode of the ultrasound imaging system is then activated and, in response to the activation, each of the acquired different ultrasound image clips are compared in the buffer based upon respective measured characteristics, at least one of the clips demonstrating an optimal value for the measured characteristic is identified and the identified clip or clips saved in memory of the ultrasound imaging system in correspondence with the single view.
    Type: Application
    Filed: January 31, 2019
    Publication date: August 6, 2020
    Inventors: Charles Cadieu, Charles Chen, Ha Hong, Ching Hsieh, Kilian Koepsell
  • Publication number: 20200245970
    Abstract: A method for prescriptively guiding an operator of an ultrasound imaging probe includes acquiring a sequence of image clips of a target organ utilizing an ultrasound imaging probe, determining a particular view of the target organ expressed by the acquired image clips and assessing a quality of each of the acquired image clips in respect to the particular view. On condition that the assessed quality falls below a pre-determined satisfactory quality for the particular view, a prescriptive movement of the probe is computed that has been pre-determined to produce quality improvement of a subsequently acquired image clip of the target organ for the particular view. Then, responsive to determining that the prescriptive movement has been computed a threshold number of times in connection with the sequence, the prescriptive movement is displayed concurrently with a display of subsequently acquired image clips of the target organ.
    Type: Application
    Filed: January 31, 2019
    Publication date: August 6, 2020
    Inventors: Charles Cadieu, Ali Chaudhry, Sara Guttas, Ha Hong, Ching Hsieh, Kilian Koepsell, Nripesh Parajuli, Nicolas Poilvert
  • Patent number: 10726548
    Abstract: Embodiments of the present invention provide a method, system and computer program product for video clip quality determination in medical device imaging and diagnosis. In an embodiment of the invention, a method for video clip quality determination in medical imaging includes first retrieving from a data store into memory of a host computer, video clip imagery of a target organ. Then, a quality value assigned to the video clip imagery may be identified in connection with the retrieved video clip imagery. A measurement of the target organ is computed based upon the retrieved video clip imagery. Finally, a confidence in respect to the computed measurement is determined based upon the identified quality value and the confidence determination displayed in a user interface provided by the host computer.
    Type: Grant
    Filed: June 25, 2018
    Date of Patent: July 28, 2020
    Assignee: BAY LABS, INC.
    Inventors: Charles Cadieu, Ha Hong, Kilian Koepsell, Nicolas Poilvert, Michael G. Cannon, Nathanael Romano, Ching Hsieh, Samuel Surette, Natalia Bilenko
  • Patent number: 10701376
    Abstract: An image processing method includes selecting an image in fixed storage of a computer and loading the selected image into memory of the computer. The method further includes representing the loaded image by a processor of the computer in the memory as an initial two-dimensional array of pixel values. Thereafter, the initial two-dimensional array of pixel values may be transformed into a hierarchy of progressively axially decremented two-dimensional arrays of signs and a pair of one-dimensional values for each 2×2 array of signs amongst the decremented two-dimensional arrays of signs. Finally, each of the two-dimensional arrays of signs and each pair of one-dimensional values may be stored in the fixed storage as a compressed form of the selected image.
    Type: Grant
    Filed: July 5, 2018
    Date of Patent: June 30, 2020
    Assignee: AWECOM, INC.
    Inventors: Christopher J. Hillar, Ram Mehta, Kilian Koepsell, Charles Garfinkle
  • Patent number: 10631791
    Abstract: A method for clip selection includes receiving through an interface to a medical imaging device, a selection of a diagnostic procedure and a target portion of a mammalian body. Thereafter, the device acquires video clip imagery of the target portion and stores the video clip imagery in an image store. Each video clip of the video clip imagery is then image processed to determine a view and a quality of each video clip and a rule is retrieved from a rules base corresponding to the selected diagnostic procedure and target portion. In this regard, the rule specifies a requisite view and quality of the video clip imagery. Finally, the retrieved rule is applied to the video clip imagery as a filter to produce a subset of video clip imagery satisfying the specified requisite view and quality and the subset of video clip imagery is stored in the image store.
    Type: Grant
    Filed: June 25, 2018
    Date of Patent: April 28, 2020
    Assignee: Caption Health, Inc.
    Inventors: Charles Cadieu, Ha Hong, Kilian Koepsell, Johan Mathe, Nicolas Poilvert, Michael Cannon, Nathanael Romano, Natalia Bilenko, Charles Chen, Nina Miolane
  • Publication number: 20200014942
    Abstract: An image processing method includes selecting an image in fixed storage of a computer and loading the selected image into memory of the computer. The method further includes representing the loaded image by a processor of the computer in the memory as an initial two-dimensional array of pixel values. Thereafter, the initial two-dimensional array of pixel values may be transformed into a hierarchy of progressively axially decremented two-dimensional arrays of signs and a pair of one-dimensional values for each 2×2 array of signs amongst the decremented two-dimensional arrays of signs. Finally, each of the two-dimensional arrays of signs and each pair of one-dimensional values may be stored in the fixed storage as a compressed form of the selected image.
    Type: Application
    Filed: July 5, 2018
    Publication date: January 9, 2020
    Inventors: Christopher J. Hillar, Ram Mehta, Kilian Koepsell, Charles Garfinkle
  • Publication number: 20190392577
    Abstract: Embodiments of the present invention provide a method, system and computer program product for video clip quality determination in medical device imaging and diagnosis. In an embodiment of the invention, a method for video clip quality determination in medical imaging includes first retrieving from a data store into memory of a host computer, video clip imagery of a target organ. Then, a quality value assigned to the video clip imagery may be identified in connection with the retrieved video clip imagery. A measurement of the target organ is computed based upon the retrieved video clip imagery. Finally, a confidence in respect to the computed measurement is determined based upon the identified quality value and the confidence determination displayed in a user interface provided by the host computer.
    Type: Application
    Filed: June 25, 2018
    Publication date: December 26, 2019
    Inventors: Charles Cadieu, Ha Hong, Kilian Koepsell, Nicolas Poilvert, Michael G. Cannon, Nathanael Romano, Ching Hsieh, Samuel Surette, Natalia Bilenko
  • Publication number: 20190392581
    Abstract: A method for clip selection includes receiving through an interface to a medical imaging device, a selection of a diagnostic procedure and a target portion of a mammalian body. Thereafter, the device acquires video clip imagery of the target portion and stores the video clip imagery in an image store. Each video clip of the video clip imagery is then image processed to determine a view and a quality of each video clip and a rule is retrieved from a rules base corresponding to the selected diagnostic procedure and target portion. In this regard, the rule specifies a requisite view and quality of the video clip imagery. Finally, the retrieved rule is applied to the video clip imagery as a filter to produce a subset of video clip imagery satisfying the specified requisite view and quality and the subset of video clip imagery is stored in the image store.
    Type: Application
    Filed: June 25, 2018
    Publication date: December 26, 2019
    Inventors: Charles Cadieu, Ha Hong, Kilian Koepsell, Johan Mathe, Nicolas Poilvert, Michael Cannon, Nathanael Romano, Natalia Bilenko, Charles Chen, Nina Miolane
  • Patent number: 10470677
    Abstract: Embodiments of the invention provide a method, system and computer program product for artificially intelligent ejection fraction determination. In a method for artificially intelligent ejection fraction determination, a neural network is loaded into memory of a computer, that has been trained with different sets of cardiac imaging data acquired during imaging of a ventricle for different hearts and a known ejection fraction for each of the sets. Then, a contemporaneous set of imaging data is acquired of a ventricle of a heart and the contemporaneous set of imaging data is provided to the neural network. Finally, an ejection fraction determination output by the neural network is displayed in a display of the computer without tracing a ventricle boundary of the heart.
    Type: Grant
    Filed: October 11, 2017
    Date of Patent: November 12, 2019
    Assignee: BAY LABS, INC.
    Inventors: Charles Cadieu, Michael G. Cannon, Ha Hong, Kilian Koepsell, Johan Mathe, Nicolas Poilvert
  • Publication number: 20190104949
    Abstract: Embodiments of the invention provide a method, system and computer program product for artificially intelligent ejection fraction determination. In a method for artificially intelligent ejection fraction determination, a neural network is loaded into memory of a computer, that has been trained with different sets of cardiac imaging data acquired during imaging of a ventricle for different hearts and a known ejection fraction for each of the sets. Then, a contemporaneous set of imaging data is acquired of a ventricle of a heart and the contemporaneous set of imaging data is provided to the neural network. Finally, an ejection fraction determination output by the neural network is displayed in a display of the computer without tracing a ventricle boundary of the heart.
    Type: Application
    Filed: October 11, 2017
    Publication date: April 11, 2019
    Inventors: Charles Cadieu, Michael G. Cannon, Ha Hong, Kilian Koepsell, Johan Mathe, Nicolas Poilvert
  • Patent number: 10204286
    Abstract: An invention based on learning a discrete recurrent neural network for a given signal domain is described. In one implementation to the domain of visual images, the method can be used to efficiently compress digital photographs and to devise a new perceptual distortion measure between images that well-matches data collected from a human psychophysics experiment. Other applications of the invention include unsupervised detection of recurrent patterns in high-dimensional data and Shannon-optimal error-correcting coding from few training examples.
    Type: Grant
    Filed: February 29, 2016
    Date of Patent: February 12, 2019
    Assignee: EMERSYS, INC.
    Inventors: Christopher J. Hillar, Kilian Koepsell, Ram Mehta, Jascha Sohl-Dickstein
  • Publication number: 20180153505
    Abstract: Embodiments of the invention provide for the guided navigation of an ultrasound probe. In an embodiment of the invention, an ultrasound navigation assistance method includes acquiring an image by an ultrasound probe of a target organ of a body. The method also includes processing the image in connection with an estimator such as a neural network. The processing in turn determines a deviation of a contemporaneous pose evident from the acquired image from an optimal pose of the ultrasound probe for imaging the target organ. Finally, the method includes presenting the computed deviation to an end user operator of the ultrasound probe.
    Type: Application
    Filed: December 4, 2017
    Publication date: June 7, 2018
    Inventors: Charles Cadieu, Ha Hong, Kilian Koepsell, Johan Mathe, Martin Wojtczyk
  • Publication number: 20170249536
    Abstract: An invention based on learning a discrete recurrent neural network for a given signal domain is described. In one implementation to the domain of visual images, the method can be used to efficiently compress digital photographs and to devise a new perceptual distortion measure between images that well-matches data collected from a human psychophysics experiment. Other applications of the invention include unsupervised detection of recurrent patterns in high-dimensional data and Shannon-optimal error-correcting coding from few training examples.
    Type: Application
    Filed: February 29, 2016
    Publication date: August 31, 2017
    Inventors: Christopher J. Hillar, Kilian Koepsell, Ram Mehta, Jascha Sol-Dickstein