Method and apparatus for identifying and quantifying abnormality

Inventors

Zebaze, Roger • Peng, Yu

Assignees

Straxcorp Pty Ltd • Curvebeam AI Ltd

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

The invention provides a computer-implemented method of building an abnormality quantifier by imagizing at least one first dataset comprising measurements of a normal population or sample and at least one second dataset comprising measurements of an abnormal population or sample into an image or map. The method identifies a normality zone within the image or map using the at least one first dataset and identifies an abnormality zone within the image or map using the at least one second dataset. A definition of normality is determined based on the normality zone, and a definition of abnormality is determined based on a comparison of the definition of normality and the abnormality zone.

The abnormality is disease, fracture-vulnerability of bone, or obesity, and the measurements comprise co-measurements that relate to respective characteristics of the normal population or sample and the abnormal population or sample. The co-measurements comprise two-or more dimensional ordered pairs of either co-dependent or non co-dependent parameters. The approach uses the normality definition and abnormality zone to determine which of the one or more measurements correspond to abnormality.

A software device and an apparatus are also disclosed for defining and quantifying abnormality using the same abnormality-definition workflow based on imagizing normal and abnormal datasets into an image or map, identifying normality and abnormality zones, and comparing definitions of normality and abnormality. The document further includes abnormality quantification that adapts to define and quantify the extent of abnormality of measurements, where the abnormality is disease, fracture-vulnerability of bone, or obesity and the normal and abnormal datasets are represented using co-measurements as two-or more dimensional ordered pairs of (co-)dependent parameters.

Claims Coverage

The independent claims define a common core workflow for building and applying an abnormality-definition mechanism based on imagizing normal and abnormal datasets into an image/map, segmenting normality and abnormality zones, and deriving definitions of normality and abnormality by comparison. The coverage includes four independent claims directed to a method of building an abnormality quantifier, identifying abnormality in measurements, generating a software device for defining and quantifying abnormality, and an apparatus implementing the same concepts.

Across the independent claims, abnormality is defined by constructing an image or map from normal and abnormal datasets via imagizing, segmenting normality and abnormality zones, determining a definition of normality from the normality zone, and determining a definition of abnormality by comparison. The independent claim set also anchors the abnormality types to disease, fracture-vulnerability of bone, or obesity and requires co-measurements expressed as two-or-more dimensional ordered pairs of co-dependent or non co-dependent parameters, with apparatus and software-device versions outputting abnormality results.

Stated Advantages

Documented Applications