IP Library Granted Patent US 12,511,752
Granted Patent B1
US 12,511,752 · App. 18/975,926 · Granted Dec 30, 2025

Apparatus and method for automatically validating quality data associated with at least a slide

Inventors: Raghubansh Bahadur Gupta (Bangalore, IN); Jithin Prems (Dooravani Nagar, IN); Rohan Prateek (Uttar Pradesh, IN); Pavani Pallavi Pelluru (Pocharam, IN); Prasanth Perugupalli (Cary, NC)
Assignee: Pramana, Inc.
G06T7/0014A61B10/0041G06T7/337G06V10/24G06V10/25G16H10/40G06T2207/10056G06T2207/10064G06T2207/30024G06T2207/30168G06V2201/03G06V2201/10
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,511,752
App. No.
18/975,926
Granted
Dec 30, 2025
Kind
B1
Abstract

An apparatus and method for automatically validating quality data associated with at least a slide. The apparatus includes at least a processor and a memory communicatively connected to the at least a processor. The memory instructs the processor to receive, from the at least an optical device, at least a digital slide corresponding to the at least a slide, determine, using metadata, a slide identification, localize, using at least an object detection technique, the at least a digital slide, wherein localizing the at least a digital slide comprises identifying a stained core of interest and aligning the stained core of interest into a standard form, and, evaluate, using a predefined threshold, the stained core of interest, wherein evaluating comprises comparing the stained core of interest to a control core, generating a validation output, and transmitting the validation output to a downstream device.

Claims (72)

1 . An apparatus for automatically validating quality data associated with at least a slide, wherein the apparatus comprises:

at least an optical device comprising at least a camera configured to scan at least a slide, wherein the at least a slide comprises two or more stained cores, wherein scanning the at least a slide creates at least a digital slide corresponding to the at least a slide;

at least a computing device communicatively connected to the at least an optical device, wherein the computing device comprises:

a memory; and

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

receive, from the at least an optical device, at least a digital slide corresponding to the at least a slide;

determine, using metadata, a slide identification;

localize, using at least an object detection technique, the at least a digital slide, wherein localizing the at least a digital slide comprises:

identifying a stained core of interest from the two or more stained cores; and

aligning the stained core of interest into a standard form, wherein the standard form comprises at least data entry rules; and

evaluate, using a predefined threshold, the stained core of interest, wherein evaluating comprises:

comparing the stained core of interest to a control core;

generating a validation output as a function of a comparison of the stained core of interest and the control core and wherein generating the validation output comprises utilizing a stain statistical model configured to compute at least a predefined value, wherein the at least a predefined value is configured to validate the at least a digital slide;

transmitting the validation output to a display device;

cross-validating a positive control core of the validation output to confirm a reliability of the validation output, wherein cross-validation comprises:

configuring one or more optical device parameters comprising at least a magnification level and scanning speed of the optical device as a function of the stained core of interest and the positive control core, wherein the optical device parameters are adjusted to ensure accurate specific attributes of the stained core;

scanning, using the at least an optical device, the stained core of interest at a magnified resolution;

comparing the stained core of interest against the control core; and

generating a cross-validation output; and

transmitting the cross-validation output to a display device for further action.

2 . The apparatus of claim 1 , wherein the at least a slide comprises an immunohistology chemistry slide, wherein the two or more stained cores of the immunohistology chemistry slide comprises a tissue sample.

3 . The apparatus of claim 1 , wherein determining the slide identification comprises extracting the metadata from a slide label using an image processing algorithm.

4 . The apparatus of claim 1 , wherein determining the slide identification, using the metadata, comprises extracting the slide identification from an electronic health record database.

5 . The apparatus of claim 1 , wherein aligning the stained core of interest comprises one or more of rotating the at least a digital slide, translating the at least a digital slide, and reflecting the at least a digital slide.

6 . The apparatus of claim 1 , wherein the apparatus is further configured to align the stained core of interest comprising a mirrored configuration into the standard form by:

identifying, using metadata, the stained core of interest;

using at least a handling mirror; and

overlaying a validation control on the stained core of interest.

7 . The apparatus of claim 6 , wherein aligning the two or more stained cores comprising the mirrored configuration into the standard form comprises using a texture of the two or more stained cores, a deconvolved channel, and at least a stain.

8 . The apparatus of claim 1 , wherein a temporal datum associated with the at least a slide is used to determine which of a plurality of pre-processing steps generated a fault associated with the at least a slide by:

chronologically organizing temporal data associated with the at least a slide;

chronologically organizing the plurality of pre-processing steps corresponding to the temporal data; and

identifying, using the temporal datum, a pre-processing step, of the plurality of pre-processing steps, corresponding to the fault.

9 . The apparatus of claim 1 , further configured to cross-validate a positive control core of the validation output, wherein cross-validation comprises:

configuring one or more optical device parameters of the optical device as a function of the stained core of interest and the positive control core;

scanning, using the at least an optical device, the stained core of interest at a magnified resolution;

comparing the stained core of interest against the control core; and

generating a cross-validation output.

10 . A method for automatically validating quality data associated with at least a slide, wherein the method comprises:

receiving, from at least an optical device, at least a digital slide corresponding to at least a slide wherein the at least a slide comprises two or more stained cores;

determining, using metadata, a slide identification;

localizing, using at least an object detection technique, the at least a digital slide, wherein localizing the at least a digital slide comprises:

identifying a stained core of interest from the two or more stained cores; and

aligning the stained core of interest into a standard form; and

evaluating, using a predefined threshold, the stained core of interest, wherein evaluating comprises:

comparing the stained core of interest to a control core;

generating a validation output as a function of a comparison of the stained core of interest and the control core and wherein generating the validation output comprises utilizing a stain statistical model configured to compute at least a predefined value, wherein the at least a predefined value is configured to validate the at least a digital slide;

transmitting the validation output to a downstream device;

cross-validating a positive control core of the validation output to confirm a reliability of the validation output, wherein cross-validation comprises:

configuring one or more optical device parameters comprising at least a magnification level and scanning speed of the optical device as a function of the stained core of interest and the positive control core, wherein the optical device parameters are adjusted to ensure accurate specific attributes of the stained core;

scanning, using the at least an optical device, the stained core of interest at a magnified resolution;

comparing the stained core of interest against the control core; and

generating a cross-validation output; and

transmitting the cross-validation output to a display device for further action.

11 . The method of claim 10 , wherein the at least a slide comprises an immunohistology chemistry slide, wherein the two or more stained cores of the immunohistology chemistry slide comprises a tissue sample.

12 . The method of claim 10 , wherein determining the slide identification comprises extracting the metadata from a slide label using an image processing algorithm.

13 . The method of claim 10 , wherein determining the slide identification, using the metadata, comprises extracting the slide identification from an electronic health record database.

14 . The method of claim 10 , wherein aligning the stained core of interest comprises one or more of rotating the at least a digital slide, translating the at least a digital slide, and reflecting the at least a digital slide.

15 . The method of claim 10 , further configured to align the stained core of interest comprising a mirrored configuration into the standard form by:

identifying, using metadata, the stained core of interest;

using at least a handling mirror; and

overlaying a validation control on the stained core of interest.

16 . The method of claim 15 , wherein aligning the two or more stained cores comprising the mirrored configuration into the standard form comprises using a texture of the two or more stained cores, a deconvolved channel, and at least a stain.

17 . The method of claim 10 , wherein a temporal datum associated with the at least a slide is used to determine which of a plurality of pre-processing steps generated a fault associated with the at least a slide by:

chronologically organizing temporal data associated with the at least a slide;

chronologically organizing the plurality of pre-processing steps corresponding to the temporal data; and

identifying, using the temporal datum, a pre-processing step, of the plurality of pre-processing steps, corresponding to the fault.

18 . The method of claim 10 , further configured to cross-validate a positive control core of the validation output, wherein cross-validation comprises:

configuring one or more optical device parameters of the optical device as a function of the stained core of interest and the positive control core;

scanning, using the at least an optical device, the stained core of interest at a magnified resolution;

comparing the stained core of interest against the control core; and

generating a cross-validation output.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 6, 2025
From: GUPTA, RAGHUBANSH BAHADUR; PREMS, JITHIN; PRATEEK, ROHAN; PELLURU, PAVANI PALLAVI; PERUGUPALLI, PRASANTH
To: PRAMANA, INC.
Reel/Frame 069750/0503 →
References Cited (12)
US 8160348B2 · Pinard et al. · 2012 [cited by applicant]
US 8565503B2 · Eichhorn et al. · 2013 [cited by applicant]
US 20230206416A1 · Maier et al. · 2023 [cited by applicant]
WO 2013090567A2 · 2013 [cited by applicant]
WO 2014181347A2 · 2014 [cited by applicant]
WO WO2021133847A1 · 2021 [cited by examiner]
WO WO2022251556A1 · 2022 [cited by examiner]
WO WO2023049471A1 · 2023 [cited by examiner]
Komura et al. in Computational and Structural Biotechnology Journal (2018) vol. 16:34-42. [cited by examiner]
Niazi et al. “Digital Pathology and Artificial Intelligence” Lancet Oncol. (2019) vol. 20, May: e253-61. [cited by examiner]
M. I. Samuelson et al Rapid Validation of Whole-Slide Imaging for Primary Histopathology Diagnosis Am J Clin Pathol. Jan. 29, 2021, p. 1-11. [cited by applicant]
Adela Saco et al Validation of Whole-Slide Imaging for Histolopathogical Diagnosis: Current State Pathobiology (2016) 83 (2-3): 89-98. [cited by applicant]