Abstract: A method of retrieving an image file from a first database, where the image file includes a link to an associated report stored in a second database. The method includes: de-identifying the report; applying a search query to the second database; returning the report in response to the applied query; applying the link to the first database; and returning the image file in response to the applied link.
Type:
Grant
Filed:
August 23, 2017
Date of Patent:
June 14, 2022
Assignee:
IMAGING ENDPOINTS II LLC
Inventors:
Doug Dean Burkett, David Jose Marichal, Andre A Burkett
Abstract: Methods and apparatus for predicting responsiveness to immune therapy in lung cancer. The method includes the steps of: identifying a first population of known responders and a second population of known non-responders; processing imaging data for the first and second populations using quantitative textural analysis (QTA); generating, for each member of both populations, quantitative metrics using the QTA; performing logistic regression on the quantitative metrics for both populations to yield a predictive signature expressed in the form of Y=Mx+B where x comprises mean pixel density; performing QTA on a lung cancer scan for a subsequent patient; comparing the predictive signature to one or more relevant metrics associated with the subsequent patient; and predicting responsiveness to immune therapy for the subsequent patient based on the comparison.
Abstract: Biomarker signatures for predicting breast cancer tumor aggressiveness. The signatures are derived from QTA-based parameters from a first population of low risk scores and a second population of high risk scores. The signatures may be expressed in the form log (RS)=Mx+B for linear modeling, or for logistic modeling the signatures may be expressed as either p=ex/[1+ex] where x=Ay+B, or in the form log it(p)=C(PR)+Ay+B, where y is a QTA based parameter.
Abstract: Methods and apparatus for using a biomarker signature to determine whether a breast tumor is malignant by comparing imaging data for the breast tumor to the signature, the signature derived using Quantitative Textural Analysis (QTA) and expressed in the form: Y=XCx+B; where: Y is a predictive indicator ranging from 0 to 1; B is a constant; Cx is a coefficient; and X is the mean positive pixel (MPP) value associated with the breast tumor under inspection.
Abstract: A method of retrieving an image file from a first database, where the image file includes a link to an associated report stored in a second database. The method includes: de-identifying the report; applying a search query to the second database; returning the report in response to the applied query; applying the link to the first database; and returning the image file in response to the applied link.
Type:
Application
Filed:
August 23, 2017
Publication date:
September 27, 2018
Applicant:
Imaging Endpoints II, LLC
Inventors:
Doug Dean Burkett, David Jose Marichal, Andre A. Burkett