Granted Patent B2

US 12,217,837 · App. 18/603,051 · Granted Feb 4, 2025

Inventors: Jithin Prems (Dooravani Nagar, IN); Manish Shiralkar (Pune, IN); Prasanth Perugupalli (Cary, NC); Shilpa G. Krishna (Kerala, IN); Durgaprasad Dodle (Telangana, IN); Raghubansh Bahadur Gupta (Bangalore, IN); Jaya Jain (Shahpura, IN); Prateek Jain (Karnataka, IN); Priyanka Golchha (Rajasthan, IN)

Assignee: Pramana, Inc.

G16H10/40

Abstract

Claims (49)

1. A system for digitization of tissue slides based on associations among serial sections, wherein the system is comprised of:

at least a computing device, wherein the computing device is comprised of:

a memory, wherein the memory stores instructions; and

a processor, communicatively connected to the memory, wherein the processor is configured to:

retrieve, from the memory, a candidate tissue map associated with a candidate tissue section, wherein the candidate tissue map is digital and comprises a digitized and then scanned slide at a high magnification wherein the scanned slide is restricted to content within an identified enclosing bounding box;

retrieve a reference tissue map associated with a reference tissue section;

align the candidate tissue map to the reference tissue map;

compare the aligned candidate tissue map to the reference tissue map; and

generate a regenerated candidate tissue map as a function of the reference tissue map, wherein the regenerated candidate tissue map is digital and

generating the regenerated candidate tissue map comprises instantiating a machine learning module which further comprises:

receiving training data, wherein the training data correlates a plurality of reference tissue map data to a plurality of regenerated candidate tissue map data;

training, iteratively, the machine learning module using the training data, wherein training the machine learning module includes retraining the machine learning module with feedback from previous iterations of the machine learning module; and

generating the regenerated candidate tissue map using the trained machine learning module; and

a scanner, configured to scan a slide and send a digitized image of the slide to the computing device.

2. The system of claim 1 , wherein the memory further includes instructions configuring the processor to:

identify a candidate serial section from at least one stain type, wherein the candidate serial section is associated with a case identification number and a block identification number;

identify a reference serial section based on the cane identification number and the block identification number;

generate the reference tissue map in response to scanning the reference serial section; and

generate the candidate tissue map in response to scanning the candidate serial section.

3. The system of claim 1 , wherein the candidate serial section is on a first slide and the reference serial section is on a second slide.

4. The system of claim 1 wherein the candidate serial section and the reference serial section are both on a first slide.

5. The system of claim 1 , wherein the system is further comprised of at least a storage device.

6. The system of claim 1 , wherein the system is further comprised of a scanned slides data repository.

7. The system of claim 1 , wherein the system is further comprised of a regenerated slides data repository.

8. The system of claim 1 , wherein the system is further comprised of both a scanned slides data repository and a regenerated slides data repository.

9. The system of claim 1 , wherein the system instantiates a machine learning module.

10. The system of claim 1 , wherein the system instantiates a neural network.

11. A method for digitization of tissue slides based on associations among serial sections, wherein the method is comprised of:

receiving, from a memory, a candidate tissue map associated with a candidate tissue section, wherein the candidate tissue map is digital and comprises a digitized and then scanned slide at a high magnification wherein the scanned slide is restricted to content within an identified enclosing bounding box;

receiving a reference tissue map associated with a reference tissue section, the reference tissue section having a predetermined association with the candidate tissue section;

aligning the candidate tissue map to the reference tissue map;

comparing the aligned candidate tissue map to the reference tissue map; and

generating a regenerated candidate tissue map as a function of the reference tissue map, wherein the regenerated candidate tissue map is digital and generating the regenerated candidate tissue map comprises instantiating a machine learning module which further comprises:

receiving training data, wherein the training data correlates a plurality of reference tissue map data to a plurality of regenerated candidate tissue map data;

training, iteratively, the machine learning module using the training data, wherein training the machine learning module includes retraining the machine learning module with feedback from previous iterations of the machine learning module; and

generating the regenerated candidate tissue map using the trained machine learning module.

12. The method of claim 11 , wherein the method further comprises:

identifying a candidate serial section from at least one stain type, wherein the candidate serial section is associated with a case identification number and a block identification number;

identifying a reference serial section based on the case identification number and the block identification number;

generating the reference tissue map in response to scanning the reference serial section; and

generating the candidate tissue map in response to scanning the candidate serial section.

13. The method of claim 11 , wherein the candidate serial section is on a first slide and the reference serial section is on a second slide.

14. The method of claim 11 , wherein the candidate serial section and the reference serial section are both on a first slide.

15. The method of claim 11 , wherein the method further includes storage and retrieval of slides data from at least a storage device.

16. The method of claim 11 , wherein the method further includes storage and retrieval of slides data from a scanned slides data repository.

17. The method of claim 11 , wherein the method further includes storage and retrieval of slides data from a regenerated slides data repository.

18. The method of claim 11 , wherein the method further includes storage and retrieval of slides data from both a scanned slides data repository and a regenerated slides data repository.

19. The method of claim 11 , wherein the method instantiates a machine learning module.

20. The method of claim 11 , wherein the method instantiates a neural network.

Assignments (1)

Continuity (2)

References Cited (14)