Granted Patent B2

US 12,591,126 · App. 18/588,030 · Granted Mar 31, 2026

Inventors: Ganesh Ramamoorthy (Andover, MA); Prasanth Perugupalli (Cary, NC)

Assignee: Pramana, Inc.

G02B21/361G02B21/26G02B21/32G02B21/34G02B21/365G02B21/368

Abstract

Claims (57)

1 . An apparatus for real time image generation, the apparatus comprising:

at least an optical system;

a slide port configured to hold a slide;

an actuator mechanism mechanically connected to a mobile element;

a user interface comprising an input interface and an output interface, wherein the input interface is configured to receive a parameter set from a user;

at least a processor; and

a memory communicatively connected to the at least a processor, the memory containing instructions configuring the at least a processor to:

using the at least an optical system, capture a first image of the slide at a first position;

modify the first image;

using the output interface, display the modified first image to the user; and

using the actuator mechanism, move the mobile element into a second position, wherein the second position is determined based on the parameter set.

2 . The apparatus of claim 1 , wherein moving the mobile element into the second position comprises:

positioning, using the actuator mechanism, the slide relative to the at least an optical system such that a region of interest defined by the parameter set is within a frame of at least an optical sensor of the at least an optical system; and

setting a zoom of the at least an optical system based on a level of zoom specified by the parameter set.

3 . The apparatus of claim 1 , wherein the input from the user comprises an audio input, and wherein the audio input is interpreted using an automatic speech recognition function.

4 . The apparatus of claim 1 , wherein the parameter set comprises an image capture parameter, and wherein the first image is captured using the image capture parameter.

5 . The apparatus of claim 1 , wherein memory contains instructions configuring the at least processor to transmit the first image to an image processing module, wherein the image processing module is configured to determine a region of interest is by isolating a feature of interest from the first image and segmenting the region of interest depicting a feature of interest into a plurality of sub-regions.

6 . The apparatus of claim 5 , wherein memory contains instructions configuring the at least processor to determine a degree of quality of depiction of the region of interest of the first image.

7 . The apparatus of claim 1 , wherein modifying the first image comprises:

receiving, using the user interface, an annotation instruction from the user; and

adding an annotation to the first image based on the annotation instruction.

8 . The apparatus of claim 7 , wherein the memory contains instructions configuring the at least a processor to:

train an annotation machine learning model using a training dataset including image data associated with a feature depicted by the image;

input into the annotation machine learning model an image selected from a list consisting of the first image, the second image, and a hybrid image;

receive from the annotation machine learning model a datum identifying a feature depicted by the image selected from the list consisting of the first image, the second image, and the hybrid image; and

add an annotation to the first image, as a function of the image feature.

9 . The apparatus of claim 1 , wherein modifying the first image comprises:

removing a first artifact from the first image, wherein removing the first artifact comprises:

inputting the first image into an artifact removal machine learning model; and

receiving, from the artifact removal machine learning model, a version of first image lacking the artifact.

10 . The apparatus of claim 1 , wherein modifying the first image comprises isolating a feature of interest from an image and determining a feature of interest using an edge detection technique.

11 . A method of real time image generation, the method comprising:

using at least a processor and at least an optical system, capturing a first image of a slide at a first position;

using the at least a processor, modifying the first image;

using the at least a processor and an input interface, receiving a parameter set from a user;

using the at least a processor and an actuator mechanism, moving a mobile element into a second position, wherein the second position is determined based on the parameter set; and

using an output interface, displaying the modified first image to the user.

12 . The method of claim 11 , wherein moving the mobile element into the second position comprises:

positioning, using the actuator mechanism, the slide relative to the at least an optical system such that a region of interest defined by the parameter set is within a frame of at least an optical sensor of the at least an optical system; and

setting a zoom of the at least an optical system based on a level of zoom specified by the parameter set.

13 . The method of claim 11 , wherein the input from the user comprises an audio input, and wherein the audio input is interpreted using an automatic speech recognition function.

14 . The method of claim 11 , wherein the parameter set comprises an image capture parameter, and wherein the first image is captured using the image capture parameter.

15 . The method of claim 11 , using the at least a processor, transmitting the first image to an image processing module, wherein the image processing module is configured to determine a region of interest is by isolating a feature of interest from the first image and segmenting the region of interest depicting a feature of interest into a plurality of sub-regions.

16 . The method of claim 15 , using the at least a processor, determining a degree of quality of depiction of the region of interest of the first image.

17 . The method of claim 11 , wherein modifying the first image comprises:

receiving, using the user interface, an annotation instruction from the user; and

adding an annotation to an image selected from to the first image, based on the annotation instruction.

18 . The method of claim 17 , wherein modifying the first image comprises:

training an annotation machine learning model using a training dataset including image data associated with a feature depicted by the image;

inputting into the annotation machine learning model an image selected from a list consisting of the first image, the second image, and a hybrid second image;

receiving from the annotation machine learning model a datum identifying a feature depicted by the image selected from the list consisting of the first image, the second image, and the hybrid second image; and

adding an annotation to the first image, as a function of the image feature.

19 . The method of claim 11 , wherein modifying the first image comprises:

removing a first artifact from the first image, wherein removing the first artifact comprises:

inputting the first image into an artifact removal machine learning model; and

receiving, from the artifact removal machine learning model, a version of first image lacking the artifact.

20 . The method of claim 11 , wherein modifying the first image comprises isolating a feature of interest from an image and determining a feature of interest using an edge detection technique.

Continuity (2)

References Cited (14)