Method and apparatus for identifying and quantifying abnormality
Inventors
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-11462302-B2
Publication Date
2022-10-04
Expiration Date
Abstract
A method of building an abnormality quantifier comprising: generating at least one selected first dataset comprising measurements of a normal population or sample and at least one second selected dataset comprising measurements of an abnormal population or sample; generating an image or map by imagizing the datasets; identifying a normality zone within the image or map using the first dataset; identifying an abnormality zone within the image or map using the second dataset; determining a definition of abnormality based on a comparison of the normality zone and the abnormality zone; receiving or accessing at least one third dataset comprising measurements of a both known normal and abnormal population or sample; testing the performance of the initially defined abnormality against one or more preset performance criteria; and outputting an abnormality quantifier when optimal performance has been reached.
Core Innovation
A method of building an abnormality quantifier generates an image or map by imagizing at least one first selected dataset comprising measurements of a normal population or sample and at least one second selected dataset comprising measurements of an abnormal population or sample. The method identifies a normality zone within the image or map using the first dataset and identifies an abnormality zone within the image or map using the second dataset. A definition of normality is determined based on the normality zone.
A definition of abnormality is determined based on a comparison of the definition of normality and the abnormality zone. The method receives or accesses at least one third dataset comprising measurements of a both known normal and known abnormal population or sample and tests a performance of the determined definition of abnormality against one or more preset performance criteria. The performance is improved by modifying one or more of the definition of normality and the definition of abnormality.
When a preset performance threshold has been reached, the method outputs the abnormality quantifier. The abnormality is disease, fracture-vulnerability of bone or obesity, with the measurements comprising co-measurements related to respective characteristics. The documented applications include bone, where the abnormality quantifier quantifies fracture-vulnerability due to reduced bone amount and/or brittleness, including uses such as predicting fracture risk/timeframe, recategorization after threshold adjustment, and treatment selection or monitoring based on abnormality type.
Claims Coverage
Independent claims cover methods and an apparatus that build and use an abnormality quantifier by creating an image/map from normal and abnormal datasets, defining normality and abnormality zones, and iteratively testing and improving a definition using preset performance criteria until a preset performance threshold is reached. Across the independent claims, the inventive features repeat around zone-based definition and performance-driven modification, with further refinements for identifying abnormality correspondences and for bone/fracture-vulnerability use cases.
Zone-based normality and abnormality definitions from imagized normal/abnormal datasets
Generating an image or map by imagizing at least one first selected dataset comprising measurements of a normal population or sample and at least one second selected dataset comprising measurements of an abnormal population or sample; identifying a normality zone within the image or map using the at least one first dataset; identifying an abnormality zone within the image or map using the at least one second dataset; determining a definition of normality based on the normality zone; and determining a definition of abnormality based on a comparison of the definition of normality and the abnormality zone.
Performance-tested and improved abnormality definition using a third dataset and preset criteria
Receiving or accessing at least one third dataset comprising measurements of a both known normal and known abnormal population or sample; testing a performance of the determined definition of abnormality against one or more preset performance criteria; improving the performance by modifying one or more of the definition of normality and the definition of abnormality; and outputting the abnormality quantifier when a preset performance threshold has been reached.
Abnormality identification by mapping the definition of abnormality to measurements
Determining from the definition of abnormality which of the one or more measurements of the population sample correspond to abnormality, wherein the method is a computer-implemented method for identifying abnormality in one or more measurements of a population or sample and wherein the abnormality is disease, fracture-vulnerability of bone or obesity.
Computer-implemented system configured to generate zones, define normality/abnormality, test, and output results
An apparatus comprising a processor, a memory, and an outputter, wherein the processor is configured to generate an image or map by imagizing at least a first and a second dataset, the first dataset comprising measurements of a normal population or sample and the second dataset comprising measurements of an abnormal population or sample; identify a normality zone within the image or map using the first dataset and identify an abnormality zone within the image or map using the second dataset; determine a definition of normality based on the normality zone; determine a definition of abnormality based on a comparison of the definition of normality and the abnormality zone, to test a performance of the determined definition of abnormality against one or more preset performance criteria using at least one third dataset comprising measurements of a both known normal and known abnormal population or sample, and to improve the performance by modifying one or more of the definition of normality and the definition of abnormality; and the outputter is configured to output at least one result.
The independent claim set focuses on creating an image/map from normal and abnormal datasets, identifying normality and abnormality zones, defining abnormality by comparing the zones to a normality definition, and validating and improving the definition using a third dataset with known normal and known abnormal measurements against preset performance criteria until a preset performance threshold is reached. Additional independent-claim coverage includes identifying which measurements correspond to abnormality and supporting a computer-implemented apparatus with a processor, memory, and outputter configured to perform the zone-and-performance workflow.
Stated Advantages
Outputs an abnormality quantifier when a preset performance threshold has been reached.
Improves the performance of the determined definition of abnormality by modifying one or more of the definition of normality and the definition of abnormality.
Documented Applications
Bone imaging applications to quantify fracture-vulnerability, including fracture-vulnerability due to structural abnormality with reduced amount of bone.
Predicting a timeframe in which a fracture may occur from an amount of bone reduction.
Recategorization after threshold adjustment of abnormality definitions.
Treatment selection/monitoring based on an abnormality type.
Interested in licensing this patent?