Systems, methods, and computer-readable media for determining when a subject is likely to be affected by a genetic disorder
Inventors
Gelbman, Dekel • Gurovich, Yaron
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-9597037-B2
Publication Date
2017-03-21
Expiration Date
Abstract
Systems, methods, and computer-readable media are disclosed for identifying when a subject is likely to be affected by a medical condition. For example, at least one processor may be configured to receive information reflective of an external soft tissue image of the subject. The processor may also be configured to perform an evaluation of the external soft tissue image information and to generate evaluation result information based, at least in part, on the evaluation. The processor may also be configured to predict a likelihood that the subject is affected by the medical condition based, at least in part, on the evaluation result information.
Core Innovation
The invention provides a computer-implemented method that determines from a series of pixels in an image of external cranio-facial soft tissue whether a subject is likely to be affected by each of two or more genetic disorders. The method uses a plurality of cranio-facial images of positive and negative individuals, where positive individuals have a first genetic disorder and a second genetic disorder, and negative individuals lack at least one of those genetic disorders. Descriptors are calculated from features in each cell within a grid imposed on each cranio-facial image and aggregated into vectors.
For an image of the subject, descriptors are calculated from features in each of a plurality of cells within a grid imposed on the subject image, and one or more vectors are produced by aggregating the subject cell descriptors. A cranio-facial comparison is implemented by computing a distance metric between each vector of the positive and negative individuals and each vector of the subject. Based on the comparison, a subset of the plurality of vectors that are more similar to the subject vectors than a remainder is determined.
The method then determines a first probability score indicating a likelihood that the subject has the first genetic disorder and a second probability score indicating a likelihood that the subject has the second genetic disorder, by analyzing whether vectors in the determined subset are derived from the first set of first positive individuals and the second set of second positive individuals. The described electronic system and non-transitory computer-readable medium implement the same comparison and probability-score determination using externally captured cranio-facial soft tissue images.
Claims Coverage
The independent claims are clm-00001, clm-00009, and clm-00016. Across these independent claims, the main inventive features are the grid-cell descriptor aggregation into vectors, cranio-facial vector comparison using distance metrics, selection of a more-similar subset, and disorder-specific probability scoring based on which positive individual sets the similar vectors are derived from.
Grid-cell descriptor aggregation into vectors for positive and negative individuals
Using a plurality of cranio-facial images of positive and negative individuals, calculating descriptors derived from features in each of a plurality of cells within a grid imposed on each of the plurality of cranio-facial images; producing vectors by aggregating the descriptors of the plurality of cells in the cranio-facial images of the positive individuals and the negative individuals.
Subject descriptor aggregation within an imposed grid
Using an image of the subject, calculating descriptors derived from features in each of a plurality of cells within a grid imposed on the image of the subject; producing one or more vectors by aggregating the descriptors of the plurality of cells in the cranio-facial image of the subject.
Cranio-facial vector comparison using distance metrics
Implementing a cranio-facial comparison of the plurality of vectors of the images of the positive and negative individuals with the one or more vectors of the image of the subject by computing a distance metric between each of the plurality of vectors and each of the one or more vectors.
Selecting a more-similar subset of vectors
Determining, based on the comparison, a subset of the plurality of vectors more similar to the one or more vectors than a remainder of the plurality of vectors.
Disorder-specific probability scoring based on derived positive sets
Determining a first probability score indicating a likelihood that the subject has the first genetic disorder and a second probability score indicating a likelihood that the subject has the second genetic disorder by analyzing whether vectors in the determined subset of the plurality of vectors are derived from the first set of first positive individuals and the second set of second positive individuals.
Across the independent claims, the inventive approach is to map externally obtained cranio-facial soft tissue images into grid-cell descriptors aggregated into vectors, compare those vectors to subject vectors using distance metrics, select a subset of most similar vectors, and compute disorder likelihoods by analyzing the positive-disorder origin of the similar vectors.
Stated Advantages
Documented Applications
No documented applications found
Interested in licensing this patent?