Patents by Inventor Gwenole Quellec
Gwenole Quellec 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).
-
Patent number: 11935235Abstract: A method of identifying an object of interest can comprise obtaining first samples of an intensity distribution of one or more object of interest, obtaining second samples of an intensity distribution of confounder objects, transforming the first and second samples into an appropriate first space, performing dimension reduction on the transformed first and second samples, whereby the dimension reduction of the transformed first and second samples generates an object detector, transforming one or more of the digital images into the first space, performing dimension reduction on the transformed digital images, whereby the dimension reduction of the transformed digital images generates one or more reduced images, classifying one or more pixels of the one or more reduced images based on a comparison with the object detector, and identifying one or more objects of interest from the classified pixels.Type: GrantFiled: September 1, 2022Date of Patent: March 19, 2024Assignees: UNIVERSITY OF IOWA RESEARCH FOUNDATION, UNITED STATES GOVERNMENT AS REPRESENTED BY THE DEPARTMENT OF VETERANS AFFAIRSInventors: Michael Abramoff, Gwenole Quellec
-
Publication number: 20230306731Abstract: Method for the prediction of labels associated with a digital image, comprising a prediction phase consisting of: supplying the image to a segmentation neural network configured to predict a classification of the pixels of the image into a first set of classes; and supplying at least part of this classification to a classification neural network configured to predict a set of labels for said image, based on the classification P of the pixels; said segmentation and classification neural networks being determined by a learning phase comprising, for each image of a training set, the first and second steps; and determining a location of the background of said image, based on the classification of the pixels, and optimizing the weights of the neural networks according to a set of cost functions configured, by iteration, to maximize the quality of the set of labels as a function of labels previously established and associated with the image, and to maximize the probability of not predicting any label for the bacType: ApplicationFiled: July 21, 2021Publication date: September 28, 2023Applicants: UNIVERSITE BRESTBRETAGNE OCCIDENTALE, INSTITUT NATIONAL DE LA SANTÉ ET DE LA RECHERCHE MÉDICALE (INSERM)Inventor: Gwenolé QUELLEC
-
Publication number: 20230076762Abstract: A method of identifying an object of interest can comprise obtaining first samples of an intensity distribution of one or more object of interest, obtaining second samples of an intensity distribution of confounder objects, transforming the first and second samples into an appropriate first space, performing dimension reduction on the transformed first and second samples, whereby the dimension reduction of the transformed first and second samples generates an object detector, transforming one or more of the digital images into the first space, performing dimension reduction on the transformed digital images, whereby the dimension reduction of the transformed digital images generates one or more reduced images, classifying one or more pixels of the one or more reduced images based on a comparison with the object detector, and identifying one or more objects of interest from the classified pixels.Type: ApplicationFiled: September 1, 2022Publication date: March 9, 2023Inventors: MICHAEL ABRAMOFF, GWENOLE QUELLEC
-
Patent number: 11468558Abstract: A method of identifying an object of interest can comprise obtaining first samples of an intensity distribution of one or more object of interest, obtaining second samples of an intensity distribution of confounder objects, transforming the first and second samples into an appropriate first space, performing dimension reduction on the transformed first and second samples, whereby the dimension reduction of the transformed first and second samples generates an object detector, transforming one or more of the digital images into the first space, performing dimension reduction on the transformed digital images, whereby the dimension reduction of the transformed digital images generates one or more reduced images, classifying one or more pixels of the one or more reduced images based on a comparison with the object detector, and identifying one or more objects of interest from the classified pixels.Type: GrantFiled: October 11, 2018Date of Patent: October 11, 2022Assignees: UNITED STATES GOVERNMENT AS REPRESENTED BY THE DEPARTMENT OF VETERANS AFFAIRS, UNIVERSITY OF IOWA RESEARCH FOUNDATIONInventors: Michael Abramoff, Gwenole Quellec
-
Publication number: 20220237900Abstract: Disclosed is an automatic image analysis method that can be used to automatically recognise at least one rare characteristic in an image to be analysed. The method comprises a learning phase during which at least one convolutional neural network is trained to recognise characteristics, a parameter space of dimension n, in which n?2, is constructed from at least one intermediate layer of the network, a presence probability function is determined for each characteristic in the parameter space from a projection of reference images in the parameter space. During a phase of analysing the image to be analysed, the method comprises a step of recognising the at least one rare characteristic in the image to be analysed on the basis of the presence probability function determined for the at least one rare characteristic.Type: ApplicationFiled: May 7, 2020Publication date: July 28, 2022Inventor: Gwenolé QUELLEC
-
Publication number: 20220181007Abstract: An electronic device is disclosed. The device receives retinal images and patient data corresponding to the retinal images. The device can train a first machine learning model (“model”) based on a first group of the retinal images and patient data corresponding to the first group and a second model based on a second group of the retinal images and patient data corresponding to the second group. The electronic device can generate a first prediction based on the first subset of a third group of the retinal images and a second prediction based on the second subset of the third group. After training the first model and the second model, the device can train a third model to predict a geographic atrophy progression in an eye of a patient based on the first and second predictions, the first and second subsets, and patient data corresponding to the first and second subset.Type: ApplicationFiled: March 5, 2020Publication date: June 9, 2022Inventors: Guillaume MEYERS-NORMAND, Ronan DANNO, Bruno LAY, Gwenolé QUELLEC, Georges WEISSGERBER
-
Publication number: 20190164278Abstract: A method of identifying an object of interest can comprise obtaining first samples of an intensity distribution of one or more object of interest, obtaining second samples of an intensity distribution of confounder objects, transforming the first and second samples into an appropriate first space, performing dimension reduction on the transformed first and second samples, whereby the dimension reduction of the transformed first and second samples generates an object detector, transforming one or more of the digital images into the first space, performing dimension reduction on the transformed digital images, whereby the dimension reduction of the transformed digital images generates one or more reduced images, classifying one or more pixels of the one or more reduced images based on a comparison with the object detector, and identifying one or more objects of interest from the classified pixels.Type: ApplicationFiled: October 11, 2018Publication date: May 30, 2019Inventors: MICHAEL ABRAMOFF, GWENOLE QUELLEC
-
Patent number: 10258229Abstract: In a method for the acquisition of optical coherence tomography image data of retina tissue of an eye (99) of a human subject using an acquisition device comprising an imaging optics (2), a first image associated with a baseline relative positioning of the eye (99) of the human subject with respect to the imaging optics (2) is acquired at a first point in time. The baseline relative positioning is stored. At a second point in time being different from the first point in time, the baseline relative positioning of the same eye (99) of the same human subject with respect to the imaging optics (2) is re-established and a second image is acquired. For re-establishing the positioning, a present relative positioning of the eye (99) of the human subject with respect to the imaging optics is determined based on a video image of an iris region of the eye.Type: GrantFiled: April 30, 2015Date of Patent: April 16, 2019Assignee: MIMO AGInventors: Jens Kowal, Gwenolé Quellec, Peter Maloca
-
Patent number: 10219691Abstract: In a method for the acquisition of optical coherence tomography image data of retina tissue of an eye (99) of a human subject using an acquisition device comprising an imaging optics (2), a first image associated with a baseline relative positioning of the eye (99) of the human subject with respect to the imaging optics (2) is acquired at a first point in time. The baseline relative positioning is stored. At a second point in time being different from the first point in time, the baseline relative positioning of the same eye (99) of the same human subject with respect to the imaging optics (2) is re-established and a second image is acquired. For re-establishing the positioning, a present relative positioning of the eye (99) of the human subject with respect to the imaging optics is determined based on a video image of an iris region of the eye.Type: GrantFiled: April 30, 2015Date of Patent: March 5, 2019Assignee: MIMO AGInventors: Jens Kowal, Gwenolé Quellec, Peter Maloca
-
Patent number: 10140699Abstract: A method of identifying an object of interest can comprise obtaining first samples of an intensity distribution of one or more object of interest, obtaining second samples of an intensity distribution of confounder objects, transforming the first and second samples into an appropriate first space, performing dimension reduction on the transformed first and second samples, whereby the dimension reduction of the transformed first and second samples generates an object detector, transforming one or more of the digital images into the first space, performing dimension reduction on the transformed digital images, whereby the dimension reduction of the transformed digital images generates one or more reduced images, classifying one or more pixels of the one or more reduced images based on a comparison with the object detector, and identifying one ore more objects of interest from the classified pixels.Type: GrantFiled: December 6, 2011Date of Patent: November 27, 2018Assignee: University of Iowa Research FoundationInventors: Michael Abramoff, Gwenole Quellec
-
Patent number: 10083507Abstract: In the context of a method for the analysis of image data representing a three-dimensional volume of biological tissue, the image data comprises a first image representing the volume at a first point in time and a second image representing the volume at a second point in time being different from the first point in time.Type: GrantFiled: March 30, 2015Date of Patent: September 25, 2018Assignee: MIMO AGInventors: Gwenolé Quellec, Jens Kowal, Peter Maloca
-
Patent number: 10062164Abstract: In the context of a method for the analysis of image data representing a three-dimensional volume (10, 20) of biological tissue, for each of a number of subvolumes at least two error probability values (41, 42, 43, 44) are generated, each of the values (41, 42, 43, 44) indicating a probability of a type of imaging error, the totality of subvolumes constituting the three-dimensional volume (10, 20). A single consolidated error probability value (51) is determined for each of the number of subvolumes, based on the at least two error probability values (41, 42, 43, 44). Subsequently, the image data is analyzed to obtain a physiologically relevant conclusion applying to a plurality of subvolumes, weighting in the analysis the image data of a given subvolume of the plurality of subvolumes according to the consolidated error probability (51) of the subvolume.Type: GrantFiled: March 30, 2015Date of Patent: August 28, 2018Assignee: MIMO AGInventors: Gwenolé Quellec, Jens Kowal, Peter Maloca
-
Publication number: 20170071466Abstract: In a method for the acquisition of optical coherence tomography image data of retina tissue of an eye (99) of a human subject using an acquisition device comprising an imaging optics (2), a first image associated with a baseline relative positioning of the eye (99) of the human subject with respect to the imaging optics (2) is acquired at a first point in time. The baseline relative positioning is stored. At a second point in time being different from the first point in time, the baseline relative positioning of the same eye (99) of the same human subject with respect to the imaging optics (2) is re-established and a second image is acquired. For re-establishing the positioning, a present relative positioning of the eye (99) of the human subject with respect to the imaging optics is determined based on a video image of an iris region of the eye.Type: ApplicationFiled: April 30, 2015Publication date: March 16, 2017Applicant: MIMO AGInventors: Jens KOWAL, Gwenolé QUELLEC, Peter MALOCA
-
Publication number: 20170032525Abstract: In the context of a method for the analysis of image data representing a three-dimensional volume of biological tissue, the image data comprises a first image representing the volume at a first point in time and a second image representing the volume at a second point in time being different from the first point in time.Type: ApplicationFiled: March 30, 2015Publication date: February 2, 2017Applicant: MIMO AGInventors: Gwenolé QUELLEC, Jens KOWAL, Peter MALOCA
-
Publication number: 20170032522Abstract: In the context of a method for the analysis of image data representing a three-dimensional volume (10, 20) of biological tissue, for each of a number of subvolumes at least two error probability values (41, 42, 43, 44) are generated, each of the values (41, 42, 43, 44) indicating a probability of a type of imaging error, the totality of subvolumes constituting the three-dimensional volume (10, 20). A single consolidated error probability value (51) is determined for each of the number of subvolumes, based on the at least two error probability values (41, 42, 43, 44). Subsequently, the image data is analyzed to obtain a physiologically relevant conclusion applying to a plurality of subvolumes, weighting in the analysis the image data of a given subvolume of the plurality of sub-volumes according to the consolidated error probability (51) of the subvolume.Type: ApplicationFiled: March 30, 2015Publication date: February 2, 2017Applicant: MIMO AGInventors: Gwenolé QUELLEC, Jens KOWAL, Peter MALOCA
-
Publication number: 20150379708Abstract: Provided are systems and methods for analyzing images. An exemplary method can comprise receiving at least one image having one or more annotations indicating a feature. The method can comprise generating training images from the at least one image. Each training image can be based on a respective section of the at least one image. The training images can comprise positive images having the feature and negative images without the feature. The method can comprise generating a feature space based on the positive images and the negative images. The method can further comprise identifying the feature in one or more unclassified images based upon the feature space.Type: ApplicationFiled: January 31, 2014Publication date: December 31, 2015Inventors: Michael ABRAMOFF, Gwenole QUELLEC
-
Publication number: 20130301889Abstract: A method of identifying an object of interest can comprise obtaining first samples of an intensity distribution of one or more object of interest, obtaining second samples of an intensity distribution of confounder objects, transforming the first and second samples into an appropriate first space, performing dimension reduction on the transformed first and second samples, whereby the dimension reduction of the transformed first and second samples generates an object detector, transforming one or more of the digital images into the first space, performing dimension reduction on the transformed digital images, whereby the dimension reduction of the transformed digital images generates one or more reduced images, classifying one or more pixels of the one or more reduced images based on a comparison with the object detector, and identifying one ore more objects of interest from the classified pixels.Type: ApplicationFiled: December 6, 2011Publication date: November 14, 2013Applicant: UNIVERSITY OF IOWA RESEARCH FOUNDATIONInventors: Michael Abramoff, Gwenole Quellec