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 is an image-analysis system that screens a subject by receiving an external cranio-facial soft tissue image and determining whether the subject is likely to have a dysmorphic feature. The method processes the external cranio-facial soft tissue image with respect to cranio-facial external soft tissue images of a plurality of individuals, including one or more of an anchored cells analysis, a shifting patches analysis, and a relative measurements analysis to identify at least one dysmorphic feature included in the image of the subject.

After determining the dysmorphic feature(s), the system accesses a database of descriptors of dysmorphic features and selects at least one descriptor associated with the determined dysmorphic feature(s). The descriptor database includes descriptor components such as medical ontology sources and synonyms, and the output can include probability and severity scores for dysmorphic features and medical condition likelihood.

The system compares the subject image to a database of other individuals and can optionally filter comparisons by age, gender, ethnicity, or race group. The system also supports multiple evaluations and/or time-lapse or longitudinal comparison, can discount features using unaffected relatives, and can output dysmorphology visualization and localization on the image with superimposed indicators such as a heat map.

Claims Coverage

The partial content includes three independent claims, a computer-implemented method, a system, and a non-transitory computer-readable medium, each centered on using cranio-facial external soft tissue images to determine dysmorphic feature(s) via specified comparative analyses and then selecting descriptors from a dysmorphic-feature descriptor database. Across the independent claims, the inventive features are focused on the comparative image processing and descriptor selection tied to the determined dysmorphic feature(s).

Across the independent claims, the core claim coverage is the combination of comparing an external cranio-facial soft tissue image to images of a plurality of individuals using anchored cells analysis, shifting patches analysis, and/or relative measurements analysis to determine dysmorphic feature(s), and selecting descriptors from a descriptors database that are associated with the determined dysmorphic feature(s).

Stated Advantages

Documented Applications