Patents by Inventor Marco Loog
Marco Loog 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: 8315446Abstract: Mammogram images are processed by computer to derive automatically a value for a parameter useful in detecting differences in breast tissue in subsequent images of the same breast or relative to a control group of such images, said derived parameter being a parameter that changes alongside changes in breast density and is hence useful in assessing cancer risk. The method comprises the steps of processing each image of at least part of a breast by: computing for pixels of the image a quotient value representative of the aspect ratio of tissue structures depicted in the image; using a trained classifier to classify said pixels according to their respective said quotient values and assigning a score to the respective pixels representing their classification with respect to at least two classes; deriving said parameter that changes alongside changes in breast density based on the aggregate pixel membership scores of said classes.Type: GrantFiled: February 9, 2007Date of Patent: November 20, 2012Assignee: Synarc Inc.Inventors: Jakob Raundahl, Marco Loog, Mads Nielsen
-
Patent number: 8285019Abstract: A method of processing a mammogram image to derive a value for a parameter useful in detecting differences in breast tissue in subsequent images of the same breast or relative to a control group of such images, said derived parameter being an aggregate probability score reflecting the probability of the image being a member of a predefined class of mammogram images, comprises computing for each of a multitude of pixels within a large region of interest within the image a pixel probability score assigned by a trained statistical classifier according to the probability of said pixel belonging to an image belonging to said class, said pixel probability being calculated on the basis of a selected plurality of features of said pixels, and computing said parameter by aggregating the pixel probability scores over said region of interest. Saud features may include the 3-jet of said pixels.Type: GrantFiled: May 26, 2010Date of Patent: October 9, 2012Assignee: SYNARC Inc.Inventors: Jakob Raundahl, Marco Loog, Mads Nielsen, Sami Sebastian Brandt, Gopal Raghunath Karemore
-
Patent number: 8218850Abstract: A method of processing a mammogram image to derive a value for a parameter useful in detecting differences in breast tissue in subsequent images of the same breast or relative to a control group of such images, said derived parameter being an aggregate probability score reflecting the probability of the image being a member of a predefined class of mammogram images, comprises computing for each of a multitude of pixels within a large region of interest within the image a pixel probability score assigned by a trained statistical classifier according to the probability of said pixel belonging to an image belonging to said class, said pixel probability being calculated on the basis of a selected plurality of features of said pixels, and computing said parameter by aggregating the pixel probability scores over said region of interest. Said features may include the 3-jet of said pixels.Type: GrantFiled: December 23, 2008Date of Patent: July 10, 2012Assignee: Synarc Inc.Inventors: Jakob Raundahl, Marco Loog, Mads Nielsen
-
Publication number: 20110013819Abstract: A method of processing a mammogram image to derive a value for a parameter useful in detecting differences in breast tissue in subsequent images of the same breast or relative to a control group of such images, said derived parameter being an aggregate probability score reflecting the probability of the image being a member of a predefined class of mammogram images, comprises computing for each of a multitude of pixels within a large region of interest within the image a pixel probability score assigned by a trained statistical classifier according to the probability of said pixel belonging to an image belonging to said class, said pixel probability being calculated on the basis of a selected plurality of features of said pixels, and computing said parameter by aggregating the pixel probability scores over said region of interest. Saud features may include the 3-jet of said pixels.Type: ApplicationFiled: May 26, 2010Publication date: January 20, 2011Applicant: NORDIC BIOSCIENCE IMAGING A/SInventors: Jakob Raundahl, Marco Loog, Mads Nielsen, Sami S. Brandt, Gopal R. Karemore
-
Publication number: 20090296999Abstract: Mammogram images are processed by computer to derive automatically a value for a parameter useful in detecting differences in breast tissue in subsequent images of the same breast or relative to a control group of such images, said derived parameter being a parameter that changes alongside changes in breast density and is hence useful in assessing cancer risk. The method comprises the steps of processing each image of at least part of a breast by: computing for pixels of the image a quotient value representative of the aspect ratio of tissue structures depicted in the image; using a trained classifier to classify said pixels according to their respective said quotient values and assigning a score to the respective pixels representing their classification with respect to at least two classes; deriving said parameter that changes alongside changes in breast density based on the aggregate pixel membership scores of said classes.Type: ApplicationFiled: February 9, 2007Publication date: December 3, 2009Inventors: Jakob Raundahl, Marco Loog, Mads Nielsen
-
Publication number: 20090299769Abstract: A computer based calculation of a prognostic index I of osteoarthritis based on biochemical and imaging based biomarkers a mathematical combination of said values, wherein a first imaging based biomarker is a measure of the quantity of a cartilage in a joint compartment, a second imaging based biomarker relating to the quality of said cartilage in said joint compartment, and wherein a value of said first biomarker indicative of a larger quantity of cartilage affects the index to make it predictive of more disease progression, and a value of said second biochemical marker indicative of a greater departure from the quality of disease free cartilage affects the index to make it predictive of more risk of disease progression, exemplified by I = yHom + zVol + ? n = 1 N ? a n ? Other n where y and z are numerical coefficients, Hom is the measured homogeneity, Vol is the measured cartilage volume, and where Othern represents N further biomarkers each having a respective numerical coefficient anType: ApplicationFiled: May 29, 2009Publication date: December 3, 2009Applicant: Nordic Bioscience Imaging A/SInventors: Erik B. Dam, Marco Loog, Morten Karsdal, Mads Nielsen, Claus Christiansen
-
Publication number: 20090232376Abstract: A method of processing a mammogram image to derive a value for a parameter useful in detecting differences in breast tissue in subsequent images of the same breast or relative to a control group of such images, said derived parameter being an aggregate probability score reflecting the probability of the image being a member of a predefined class of mammogram images, comprises computing for each of a multitude of pixels within a large region of interest within the image a pixel probability score assigned by a trained statistical classifier according to the probability of said pixel belonging to an image belonging to said class, said pixel probability being calculated on the basis of a selected plurality of features of said pixels, and computing said parameter by aggregating the pixel probability scores over said region of interest. Saud features may include the 3-jet of said pixels.Type: ApplicationFiled: December 23, 2008Publication date: September 17, 2009Inventors: Jakob Raundahl, Marco Loog, Mads Nielsen