Back to results
US 12,586,671 B1Granted
Systems and methods for anatomical and injury modeling
AssigneeSports Rehab LA
InventorPatrick Khaziran
Life of this patent
Estimating the term…
Abstract
The present disclosure relates to systems and methods for anatomical and injury modeling. A system can process multimedia and sensor data collected during various anatomical tests, such as mobility tests and muscle, ligament, or tendon assessments, performed by a user. By applying this data to neural network models, the system can generate anatomy scores and subscores for specific body regions, identifying potential vulnerabilities in the anatomy of the user. The system can further generate a personalized conditioning protocol to address these vulnerabilities and reducing the likelihood of injury.
Claims16
A method, comprising:
- receiving, by one or more processing circuits, a request comprising anatomy information of a user and an objective of an anatomy of the user;
- determining or identifying, by the one or more processing circuits, a plurality of anatomical tests to perform by the user;
- collecting, by the one or more processing circuits from at least one camera or at least one first sensor, a set of images or videos of a performance of at least one mobility test of the plurality of anatomical tests performed by the user;
- applying, by the one or more processing circuits, the set of images or videos as input to at least one first neural network to cause the at least one first neural network to generate at least one first result of the at least one mobility test, wherein the at least one first neural network comprises a vision model, the set of multimedia or the first sensor data images or videos is applied to an input layer of the vision model to model the performance of the user to generate, in an output layer, the at least one first result of the plurality of anatomical tests based at least on detecting and mapping one or more anatomical landmarks of the user in the set of images or videos to one or more predefined mobility thresholds, wherein the vision model tracks the one or more anatomical landmarks of the user in the set of images and videos;
- collecting, by the one or more processing circuits from at least one second sensor, second sensor data during performance of at least one muscle, ligament, or tendon test of the plurality of anatomical tests performed by the user;
- determining, by the one or more processing circuits, at least one second result of the at least one muscle, ligament, or tendon test based at least on a predetermined threshold;
- applying, by the one or more processing circuits, the at least one first result of the performance of the at least one mobility test, the at least one second result of the performance of the at least one muscle, ligament, or tendon test, the anatomy information, and objective of the anatomy of the user as input to at least one second neural network to cause the at least one second neural network to generate (i) at least one anatomy score corresponding with the anatomy of the user and a plurality of anatomy subscores corresponding to one or more regions or portions of the anatomy of the user, and (ii) an anatomical conditioning protocol comprising at least a plurality of anatomy exercises based at least on the objective of the anatomy of the user and the plurality of anatomy subscores corresponding to the one or more regions or portions of the anatomy of the user, wherein the at least one second neural network is configured based on at least one physical profile of a plurality of different users;
- providing, by the one or more processing circuits, the at least one anatomy score and the anatomical conditioning protocol;
- monitoring, by the one or more processing circuits, a progress of the anatomical conditioning protocol based at least on receiving an indication of a performance by the user, the indication comprising at least one of:
- receiving application data of a user device of the user or a third-party;
- receiving, via an interface, an input from the user or the third-party;
- or
- receiving an input from a sensor device positioned to monitor the user or coupled to the user;
- and
- updating, by the one or more processing circuits, the at least one anatomy score and at least one of the plurality of anatomy subscores based on the progress.
12 more elements
A system, comprising:
- one or more processing circuits configured to:
- receive a request comprising anatomy information of a user and an objective of an anatomy of the user;
- determine or identify a plurality of anatomical tests to perform by the user;
- collect, from at least one camera or at least one first sensor, a set of images or videos of a performance of at least one mobility test of the plurality of anatomical tests performed by the user;
- generate, using a vision model, at least one first result of the at least one mobility test based on the set of images or videos, wherein the set of images or videos is applied to an input layer of the vision model to model the performance of the user to generate, in an output layer, the at least one first result of the plurality of anatomical tests based at least on detecting and mapping one or more anatomical landmarks of the user in the set of images or videos to one or more predefined mobility thresholds, wherein the vision model tracks the one or more anatomical landmarks of the user in the set of images and videos;
- collect, from at least one second sensor, second sensor data during performance of at least one muscle, ligament, or tendon test of the plurality of anatomical tests performed by the user;
- determine at least one second result of the at least one muscle, ligament, or tendon test based at least on a predetermined threshold;
- apply the at least one first result of the performance of the at least one mobility test, the at least one second result of the performance of the at least one muscle, ligament, or tendon test, the anatomy information, and objective of the anatomy of the user as input to at least one neural network to cause the at least one neural network to generate (i) at least one anatomy score corresponding with the anatomy of the user and a plurality of anatomy subscores corresponding to one or more regions or portions of the anatomy of the user, and (ii) an anatomical conditioning protocol comprising at least a plurality of anatomy exercises based at least on the objective of the anatomy of the user and the plurality of anatomy subscores corresponding to the one or more regions or portions of the anatomy of the user, wherein the at least one neural network is configured based on at least one physical profile of a plurality of different users;
- provide the at least one anatomy score and the anatomical conditioning protocol;
- monitor a progress of the anatomical conditioning protocol based at least on receiving an indication of a performance by the user, the indication comprising at least one of:
- receiving application data of a user device of the user or a third-party;
- receiving, via an interface, an input from the user or the third-party;
- or
- receiving an input from a sensor device positioned to monitor the user or coupled to the user;
- and
- update the at least one anatomy score and at least one of the plurality of anatomy subscores based on the progress.
13 more elements
A non-transitory computer readable medium including one or more instructions stored thereon, and when the one or more instructions are executed by at least one processor causes the at least one processor to execute operations of:
- applying a set of images or videos as input to at least one first neural network to cause the at least one first neural network to generate at least one first result of at least one mobility test, wherein the at least one first neural network comprises a vision model, the set of images or videos is applied to an input layer of the vision model to model a performance of a user to generate, in an output layer, the at least one first result of a plurality of anatomical tests based at least on detecting and mapping one or more anatomical landmarks of the user in the set of images or videos to one or more predefined mobility thresholds, wherein the vision model tracks the one or more anatomical landmarks of the user in the set of images and videos;
- applying the at least one first result of the performance of the at least one mobility test, anatomy information, and objective of an anatomy of the user as input to at least one second neural network to cause the at least one second neural network to generate (i) at least one anatomy score corresponding with the anatomy of the user and a plurality of anatomy subscores corresponding to one or more regions or portions of the anatomy of the user, and (ii) an anatomical conditioning protocol comprising at least a plurality of anatomy exercises based at least on then objective of the anatomy of the user and the plurality of anatomy subscores corresponding to the one or more regions or portions of the anatomy of the user, wherein the at least one second neural network is configured based on at least one physical profile of a plurality of different users;
- providing the at least one anatomy score and the anatomical conditioning protocol;
- monitoring a progress of the anatomical conditioning protocol based at least on receiving an indication of a performance by the user, the indication comprising at least one of:
- receiving application data of a user device of the user or a third-party;
- receiving, via an interface, an input from the user or the third-party;
- or
- receiving an input from a sensor device positioned to monitor the user or coupled to the user;
- and
- updating the at least one anatomy score and at least one of the plurality of anatomy subscores based on the progress.
7 more elements
Dependencies are inferred from the claim text.