Systems, methods, and computer readable media for using descriptors to identify when a subject is likely to have a dysmorphic feature

Inventors

Gelbman, Dekel • Gurovich, Yaron

Assignees

FDNA Inc

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 computer-implemented systems for analyzing image pixels of soft tissue, in particular cranio-facial external soft tissue images, to determine whether a subject is likely to have a genetic variant. Populational electronic information reflective of populational sets of values corresponding to pixels in a plurality of cranio-facial external soft tissue images is received from a plurality of geographically dispersed individuals, and electronic characterizations of the populational images are generated using the populational sets of values.

Electronic characterizations of the populational images are associated in an electronic database with genetic variant(s), and the electronic characterizations are analyzed to identify at least one populational predictor location associated with an external soft tissue attribute predictive of the genetic variant. Subject-related electronic information reflective of subject-related sets of values corresponding to pixels of a cranio-facial external soft tissue image of a subject is received, and the subject-related information is analyzed to identify a subject predictor location corresponding to the populational predictor location.

Information associated with pixels corresponding to the populational predictor location is compared with information associated with pixels corresponding to the subject predictor location, and it is determined whether a common dysmorphology exists between the subject predictor location and the populational predictor location. Based on the determining, the system predicts whether the subject has the genetic variant.

Claims Coverage

The independent claims explicitly cover three form factors for the same core approach: a computer-implemented method, an electronic device, and a non-transitory computer-readable medium. Across these independent claims, the key inventive features are the population-derived predictor location framework, the pixel-relationship-based characterization of cranio-facial external soft tissue images, and the common dysmorphology comparison used to predict whether the subject has a genetic variant.

Across the independent claims, the inventive coverage centers on generating population-derived electronic characterizations from pixel relationships in cranio-facial external soft tissue images, using those characterizations to identify populational predictor locations tied to dysmorphic features predictive of a genetic variant, mapping subject predictor locations to those populational locations, determining whether a common dysmorphology exists, and predicting genetic-variant presence from that comparison.

Stated Advantages

Documented Applications