Granted Patent B1

US 11,997,240 · App. 18/227,155 · Granted May 28, 2024

Inventors: Prasanth Perugupalli (Cary, NC); Jaya Jain (Bhopal, IN); Prateek Jain (Karnataka, IN); Durgaprasad Dodle (Telangana, IN); Tasin Ahmed (Scarborough, CA); Deepak Anand (Karnataka, IN); Raghubansh Bahadur Gupta (Bangalore, IN); Himansh Mulchandani (Karnataka, IN); Vaibhav Singh (Karnataka, IN); Asa Rubin (Silver Springs, MD)

Assignee: Pramana, Inc.

H04N1/04H04N1/00005H04N1/00336H04N1/2166H04N1/3876H04N1/409H04N1/00331

Abstract

Claims (53)

1. An apparatus for inline image enrichment, wherein the apparatus comprises:

circuitry configured to:

receive a plurality of subject data corresponding to a subject;

generate a model candidate set using the plurality of subject data;

instantiate at least a model of the model candidate set;

digitally capture an image of the subject, wherein digitally capturing the image comprises:

identifying at least a focal point using the at least a model; and

capturing the image as a function of the at least a focal point;

capturing a plurality of individual stack views of the image comprising a stack of scans which enable a user to toggle the viewing depth by rotating a digital version of the stack of scans;

saving each individual stack view; and

executing a continuum diffusion process to fuse individual stack views together; and

store the captured image in a repository.

2. The apparatus of claim 1 , wherein the circuitry includes a configurable hardware circuit.

3. The apparatus of claim 1 , wherein generating the model candidate set further comprises classifying the plurality of subject data to at least a candidate model of a plurality of potential candidate models.

4. The apparatus of claim 1 , wherein:

the plurality of subject data includes at least an element of subject metadata; and

generating the model candidate set further comprises generating the model candidate set using the subject metadata.

5. The apparatus of claim 1 , wherein instantiating the at least a model further comprises instantiating a locally cached model.

6. The apparatus of claim 1 , wherein instantiating the at least a model further comprises:

receiving a remotely cached model; and

instantiating the remotely cached model.

7. The apparatus of claim 1 , wherein capturing the image further comprises:

reviewing an initial scan;

comparing the initial scan to a confidence threshold; and

performing a subsequent scan based on the comparison.

8. The apparatus of claim 1 , wherein the plurality of individual stack views correspond to a plurality of distinct focal points.

9. The apparatus of claim 1 further configured to enhance at least a viewability characteristic of the image using a machine-learning process.

10. A method for inline image enrichment, wherein the method comprises:

receiving, by a configured circuitry, a plurality of subject data corresponding to a subject;

generating, by the configured circuitry, a model candidate set using the plurality of subject data;

instantiating, by the configured circuitry, at least a model of the model candidate set;

digitally capturing, by the configured circuitry, an image of the subject, wherein digitally capturing the image comprises;

identifying, by the configured circuitry, at least a focal point using the at least a model;

capturing, by the configured circuitry, the image as a function of the at least a focal point;

capturing a plurality of individual stack views of the image comprising a stack of scan which enable a user to toggle the viewing depth by rotating a digital version of the stack of scan;

saving each individual stack view; and

executing a continuum diffusion process to fuse individual stack views together; and

storing, by the configured circuitry, the captured image in a repository.

11. The method of claim 10 , wherein the configured circuitry includes a configurable hardware circuit.

12. The method of claim 10 , wherein generating the model candidate set further comprises classifying, by the configured circuitry, the plurality of subject data to at least a candidate model of a plurality of potential candidate models.

13. The method of claim 10 , wherein:

the plurality of subject data includes at least an element of subject metadata; and

generating the model candidate set further comprises generating, by the configured circuitry, the model candidate set using the subject metadata.

14. The method of claim 10 , wherein instantiating the at least a model further comprises instantiating, by the configured circuitry, a locally cached model.

15. The method of claim 10 , wherein instantiating the at least a model further comprises:

receiving, by the configured circuitry, a remotely cached model; and

instantiating the remotely cached model.

16. The method of claim 10 , wherein capturing the image further comprises:

reviewing, by the configured circuitry, an initial scan;

comparing, by the configured circuitry, the initial scan to a confidence threshold; and

performing a subsequent scan based on the comparison.

17. The method of claim 10 , wherein the plurality of individual stack views correspond to a plurality of distinct focal points.

18. The method of claim 10 further comprising enhancing, by the configured circuitry, at least a viewability characteristic of the image using a machine-learning process.

Assignments (12)

Cited By (2)

US 12,288,621 US 12,634,577