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 relates to a computer-based image analysis system and method that determine, from a series of pixels in an image of external cranio-facial soft tissue, whether a subject is likely to have a dysmorphic feature. The method receives first electronic information reflective of first sets of values corresponding to pixels of the subject image, where the first sets of values correspond to relationships between at least one group of pixels in the cranio-facial external soft tissue image. The method also accesses second electronic information reflective of second sets of values corresponding to pixels of cranio-facial external soft tissue images of a plurality of geographically disbursed individuals.

The invention processes the first electronic information with respect to the second electronic information, using processing that includes one or more of an anchored cells analysis, shifting patches analysis, and relative measurements analysis. Based on at least one of the anchored cells analysis, the shifting patches analysis, and the relative measurements analysis, the processing determines at least one dysmorphic feature included in the first electronic information. The dysmorphic feature determination is grounded in comparisons between subject-derived pixel relationships and pixel-derived data from the geographically disbursed individuals.

After determining the dysmorphic feature(s), the invention accesses a database of descriptors of dysmorphic features and selects, based on the determining, at least one descriptor associated with the at least one determined dysmorphic feature. The described approach supports selecting descriptors linked to the identified dysmorphic features, including descriptor database content such as medical ontology-based descriptors and textual descriptions associated with synonyms, and can include representing selected descriptors with a location indication on a cranio-facial image.

Claims Coverage

The partial content identifies three independent claims (clm-00001, clm-00013, clm-00019). Across these independent claims, each includes a shared core inventive sequence: pixel-derived relationships from a cranio-facial external soft tissue image are compared against pixel-derived values from geographically disbursed individuals using anchored cells analysis, shifting patches analysis, and relative measurements analysis; at least one dysmorphic feature is determined; and at least one associated descriptor is selected from a database of descriptors of dysmorphic features.

Across clm-00001, clm-00013, and clm-00019, the claim coverage centers on comparing pixel-derived relationship values from a subject’s external cranio-facial soft tissue image to pixel-derived values from geographically disbursed individuals, using anchored cells analysis, shifting patches analysis, and relative measurements analysis to determine at least one dysmorphic feature, and selecting at least one descriptor associated with the determined dysmorphic feature from a database of descriptors.

Stated Advantages

Documented Applications

No documented applications found