IP Library Granted Patent US 11,650,197
Granted Patent B2
US 11,650,197 · App. 16/072,394 · Granted May 16, 2023

Methods and apparatus adapted to quantify a specimen from multiple lateral views

Inventors: Stefan Kluckner (Berlin, DE); Yao-Jen Chang (Princeton, NJ); Terrence Chen (Princeton, NJ); Benjamin S. Pollack (Jersey City, NJ)
Assignee: Siemens Healthcare Diagnostics Inc.
G01N21/31G01F23/00G01N21/90G01N33/49G01N33/491G01N35/00732G01N35/04G06K9/628G06K9/6269G06N7/08G06T7/0012G06T7/62G01N35/0099G01N35/02G01N2021/1772G01N2021/1776G01N2035/00495G01N2035/00752G01N2035/0406G01N2035/0439G06T2207/10016G06T2207/10024G06T2207/10144G06T2207/10152G06T2207/20081G06T2207/20084G06T2207/30024
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 11,650,197
App. No.
16/072,394
Granted
May 16, 2023
Kind
B2
Abstract

A model-based method for quantifying a specimen. The method includes providing a specimen, capturing images of the specimen while illuminated by multiple spectra at different nominal wavelengths, and exposures, and classifying the specimen into various class types comprising one or more of serum or plasma portion, settled blood portion, gel separator (if used), air, tube, label, or cap; and quantifying of the specimen. Quantifying includes determining one or more of: a location of a liquid-air interface, a location of a serum-blood interface, a location of a serum-gel interface, a location of a blood-gel interface, a volume and/or a depth of the serum or plasma portion, or a volume and/or a depth of the settled blood portion. Quality check modules and specimen testing apparatus adapted to carry out the method are described, as are other aspects.

Claims (68)

1. A method of quantifying a specimen contained within a specimen container, comprising:

providing a specimen;

capturing images of the specimen at multiple spectra having different nominal wavelengths, and at multiple different exposures;

selecting optimally-exposed pixels from the images at the multiple different exposures and at each of the multiple spectra to generate optimally-exposed image data for each of the multiple spectra, wherein the selected optimally-exposed pixels have an intensity value within a predetermined upper portion of a pixel intensity range;

classifying, using the optimally-exposed pixels, the specimen into various class types comprising one or more of serum or plasma portion, settled blood portion, gel separator, if the gel separator is used, air, tube, label, or cap; and

quantifying the specimen by determining one or more of:

a location of a liquid-air interface between the air and the serum or plasma portion,

a location of a serum-blood interface between the serum or plasma portion and the settled blood portion,

a location of a serum-gel interface between the serum or plasma portion and the gel separator, if the gel separator is used,

a location of a blood-gel interface between the settled blood portion and the gel separator, if the gel separator is used,

a volume or a depth of the serum or plasma portion, or

a volume or a depth of the settled blood portion.

2. The method of claim 1 , wherein the capturing images of the specimen at the multiple spectra and the multiple exposures times is conducted from multiple different viewpoints, with a camera provided at each viewpoint.

3. The method of claim 2 , wherein the multiple different viewpoints comprise three or more viewpoints.

4. The method of claim 1 , wherein the specimen is a centrifuged specimen including the settled blood portion and the serum or plasma portion.

5. The method of claim 1 , wherein the classifying the specimen is based upon a multi-class classifier.

6. The method of claim 5 , wherein the multi-class classifier is generated from multiple training sets.

7. The method of claim 5 , wherein the multi-class classifier further comprises a support vector machine.

8. The method of claim 5 , comprising identifying:

the serum or plasma portion,

the settled blood portion,

a liquid-air interface between the air and the serum or plasma portion, and

a serum-gel interface or a serum-settled blood interface, depending on if a gel separator is present.

9. The method of claim 1 , comprising identifying a location of a liquid-air interface between the air and the serum or plasma portion.

10. The method of claim 1 , comprising identifying a location of a serum-settled blood interface.

11. The method of claim 1 , comprising identifying a location of a serum-gel interface.

12. The method of claim 1 , comprising calculating a volume of the serum or plasma portion.

13. The method of claim 1 , comprising calculating a volume of the settled blood portion.

14. The method of claim 1 , comprising determining a physical dimensional characteristic of the specimen container.

15. A method of quantifying a specimen contained within a specimen container, comprising:

providing a specimen;

capturing images of the specimen at multiple spectra having different nominal wavelengths, and at multiple different exposures;

selecting optimally-exposed pixels from the images at the multiple different exposures and at each of the multiple spectra to generate optimally-exposed image data for each of the multiple spectra;

classifying the specimen into various class types comprising one or more of serum or plasma portion, settled blood portion, gel separator, if the gel separator is used, air, tube, label, or cap;

quantifying the specimen by determining one or more of:

a location of a liquid-air interface between the air and the serum or plasma portion,

a location of a serum-blood interface between the serum or plasma portion and the settled blood portion,

a location of a serum-gel interface between the serum or plasma portion and the gel separator, if the gel separator is used,

a location of a blood-gel interface between the settled blood portion and the gel separator, if the gel separator is used,

a volume or a depth of the serum or plasma portion, or

a volume or a depth of the settled blood portion; and

verifying segmentation of the specimen into various class types by a Monte Carlo simulation method.

16. A quality check module adapted to quantify a specimen, comprising:

a plurality of cameras configured to capture images of the specimen at multiple spectra having different nominal wavelengths, at multiple exposures, and from different viewpoints; and

a computer configured and operable to:

select optimally-exposed pixels from the images at the different exposures and at each of the multiple spectra to generate optimally-exposed image data for each of the multiple spectra, wherein the selected optimally-exposed pixels have an intensity value within a predetermined upper portion of a pixel intensity range,

classify, using the optimally-exposed pixels, the specimen into various class types comprising one or more of serum or plasma portion, settled blood portion, gel separator, if the gel separator is used, air, tube, label, or cap, and

quantify the specimen by determining one or more of:

a location of a liquid-air interface between the air and the serum or plasma portion,

a location of a serum-blood interface between the serum or plasma portion and the settled blood portion,

a location of a serum-gel interface between the serum or plasma portion and the gel separator, if used,

a location of a blood-gel interface between the settled blood portion and the gel separator, if used,

a volume or a depth of the serum or plasma portion, or

a volume or a depth of the settled blood portion.

17. A specimen testing apparatus, comprising:

a track; and

a quality check module on the track, the quality check module including:

a plurality of cameras configured to capture images of the specimen at multiple spectra having different nominal wavelengths, at multiple different exposures, and from different viewpoints, and

a computer configured and operable to:

select optimally-exposed pixels from the images at the multiple different exposures at each of the multiple spectra to generate optimally-exposed image data for each of the multiple spectra, wherein the selected optimally-exposed pixels have an intensity value within a predetermined upper portion of a pixel intensity range,

classify, using the optimally-exposed pixels, the specimen into various class types comprising one or more of serum or plasma portion, settled blood portion, gel separator, if the gel separator is used, air, tube, label, or cap, and

quantify the specimen by determining one or more of:

a location of a liquid-air interface between the air and the serum or plasma portion,

a location of a serum-blood interface between the serum or plasma portion and the settled blood portion,

a location of a serum-gel interface between the serum or plasma portion and the gel separator, if the gel separator is used,

a location of a blood-gel interface between the settled blood portion and the gel separator, if the gel separator is used,

a volume or a depth of the serum or plasma portion, or

a volume or a depth of the settled blood portion.

Assignments (3)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 14, 2022
From: SIEMENS CORPORATION
To: SIEMENS HEALTHCARE DIAGNOSTICS INC.
Reel/Frame 061420/0093 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 14, 2022
From: POLLACK, BENJAMIN S.
To: SIEMENS HEALTHCARE DIAGNOSTICS INC.
Reel/Frame 061420/0096 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 13, 2022
From: KLUCKNER, STEFAN; CHANG, YAO-JEN; CHEN, TERRENCE
To: SIEMENS CORPORATION
Reel/Frame 061420/0084 →
Continuity (2)
Provisional Application 62288362 · Jan 28, 2016
Related Publication 20190033209A1 · Jan 31, 2019