Systems, methods, and computer-readable media for time lapse image comparison in genetic disorder analysis
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-10016167-B2
Publication Date
2018-07-10
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 determines, from a series of pixels in an image of external cranio-facial soft tissue, whether a subject is likely to be affected by a medical condition. The system receives electronic information reflective of first values corresponding to pixels in the external soft tissue image, where the first values correspond to relationships between at least one group of pixels in the cranio-facial soft tissue image. The invention analyzes the first electronic information using at least one of an anchored cells analysis, a shifting patches analysis, and a relative measurements analysis.
Based on the analysis, the invention determines an indication that a dysmorphic feature exists and assigns a severity score to the dysmorphic feature. Using the analysis and the severity score, the invention predicts whether the dysmorphic feature is indicative of the medical condition.
The invention also provides additional scoring and prediction outputs tied to dysmorphic features and medical conditions. It can determine probability and relative magnitude definitions for the severity score, incorporate contextual scoring based on surrounding features, and extend the framework to additional dysmorphic or non-dysmorphic features.
Claims Coverage
The provided claim set includes four independent claims covering an electronic system, a computer-implemented method, a non-transitory computer-readable medium, and additional output-focused system/method variants. The independent claims share a common core pipeline: pixel relationship input, analysis using anchored cells, shifting patches, and/or relative measurements, dysmorphic-feature indication, severity score assignment where required, and prediction of medical-condition indication, with certain independent claims further requiring outputting a plurality of medical conditions and optionally prioritization.
Pixel relationship-based analysis of external cranio-facial soft-tissue image
Receive electronic information reflective of first values corresponding to pixels of an external soft tissue image of the subject, wherein the first values correspond to relationships between at least one group of pixels in the cranio-facial soft tissue image of the subject.
Anchored cells, shifting patches, and relative measurements analysis
Analyze the first electronic information using at least one of an anchored cells analysis, a shifting patches analysis, and a relative measurements analysis.
Dysmorphic feature existence indication
Determine, based on the analysis, an indication that a dysmorphic feature exists.
Severity scoring of dysmorphic feature and condition-indicative prediction
Assign a severity score to the dysmorphic feature; and predict, based at least in part on the analysis, and based, at least in part, on the severity score, whether the dysmorphic feature is indicative of the medical condition.
Prediction-based output of plurality of medical conditions
Predict, based at least in part on the analysis, whether the dysmorphic feature is indicative of the medical condition; and output a plurality of medical conditions associated with the dysmorphic feature.
Across the independent claims, the inventive core is grounded in receiving pixel relationship-based electronic information from an external cranio-facial soft-tissue image, analyzing it using anchored cells analysis, shifting patches analysis, and/or relative measurements analysis, determining an indication of a dysmorphic feature, and using analysis and a severity score where required to predict whether the dysmorphic feature is indicative of the medical condition. The additional independent claims further require outputting a plurality of medical conditions associated with the dysmorphic feature.
Stated Advantages
Not explicitly described in patent.
Documented Applications
Not explicitly described in patent.
Interested in licensing this patent?