Methods, apparatus, and quality check modules for detecting hemolysis, icterus, lipemia, or normality of a specimen

Patent metadata

Field	Value
Publication number	US-11022620-B2
Application number	US-201716349075-A
Country	US
Kind code	B2
Filing date	Nov 13, 2017
Priority date	Nov 14, 2016
Publication date	Jun 1, 2021
Grant date	Jun 1, 2021

Abstract

A method of characterizing a specimen for HILN (H, I, and/or L, or N). The method includes capturing images of the specimen at multiple different viewpoints, processing the images to provide segmentation information for each viewpoint, generating a semantic map from the segmentation information, selecting a synthetic viewpoint, identifying front view semantic data and back view semantic data for the synthetic viewpoint, and determining HILN of the serum or plasma portion based on the front view semantic data with an HILN classifier, while taking into account back view semantic data. Testing apparatus and quality check modules adapted to carry out the method are described, as are other aspects.

First claim

What is claimed is:

1. A method of characterizing a specimen for HILN, comprising:
capturing one or more images from multiple viewpoints of a specimen container including a serum or plasma portion, wherein the specimen container is held in a holder and some portion of the specimen container includes a label;
processing the one or more images from the multiple viewpoints to provide segmentation information for each of the multiple viewpoints by determining classifications of regions for each of the multiple viewpoints;
generating a semantic map from the segmentation information from each of the multiple viewpoints;
selecting a synthetic viewpoint that has visibility of the serum or plasma portion;
identifying front view semantic data and back view semantic data for the synthetic viewpoint; and
determining HILN of the serum or plasma portion based on the front view semantic data with an HILN classifier, while taking into account the back view semantic data.

2. The method of claim 1 , wherein the back view semantic data includes information on regions that are classified as being label.

3. The method of claim 1 , wherein the back view semantic data includes information on regions that are classified as being holder.

4. The method of claim 1 , wherein the back view semantic data includes information on regions that are classified as label and holder.

5. The method of claim 1 , comprising not using corresponding regions in the front view semantic data on regions that are classified as being label in the back view semantic data.

6. The method of claim 1 , wherein the taking into account the back view semantic data comprises not using regions in the front view semantic data corresponding to regions that are classified as being holder in the back view semantic data.

7. The method of claim 1 , wherein the semantic map includes information on at least the serum or plasma portion and the label.

8. The method of claim 1 , wherein the semantic map includes information on at least the serum or plasma portion and holder.

9. The method of claim 8 , wherein the semantic map includes information on one or more of holder, separator, air, tube, and cap.

10. The method of claim 1 , wherein the synthetic viewpoint comprises one of the multiple viewpoints.

11. The method of claim 1 , wherein the synthetic viewpoint comprises other than one of the multiple viewpoints.

12. The method of claim 1 , wherein the synthetic viewpoint comprises a viewpoint other than one of the multiple viewpoints, and the front view semantic data of the synthetic viewpoint includes a most number of pixels that are designated as serum or plasma portion.

13. The method of claim 1 , wherein the capturing the one or more images from the multiple viewpoints comprises backlighting with light sources comprising one or more spectra of R, G, B, white light, IR, and near IR.

14. The method of claim 1 , wherein the capturing the one or more images from the multiple viewpoints comprises exposure at different exposure times for each spectral illumination.

15. The method of claim 1 , comprising illumination during the capturing the one or more images at multiple different spectra comprising red light, green light, and blue light, white light, and IR light.

16. The method of claim 1 , wherein the taking into account the back view semantic data comprises providing additional feature descriptors to the HILN classifier taking into account back view data before determining the HILN.

17. The method of claim 16 , wherein the additional feature descriptors are encoded as 1=label or 0=no label.

18. The method of claim 16 , wherein the additional feature descriptors are encoded as 1=holder or 0=no holder.

19. A quality check module adapted to determine presence of an interferent in a specimen contained within a specimen container, comprising:
a plurality of image capture devices arranged around the specimen container and configured to capture multiple images of the specimen from multiple viewpoints; and
a computer coupled to the plurality of image capture devices and adapted to process image data of the multiple images, the computer configured and capable of being operated to:
generate a semantic map,
select a synthetic viewpoint of the semantic map,
identify front view semantic data and back view semantic data for the synthetic viewpoint, and
classify whether an interferent is present within a serum or plasma portion of the specimen based on the front view semantic data, while taking into account the back view semantic data.

20. A specimen testing apparatus adapted to determine presence of an interferent in a specimen contained within a specimen container, comprising:
a track;
a carrier moveable on the track and configured to contain the specimen container;
a plurality of image capture devices arranged around the track and configured to capture multiple images of the specimen from multiple viewpoints; and
a computer coupled to the plurality of image capture devices and configured to process image data from the multiple images, the computer configured and capable of being operated to:
generate a semantic map,
select a synthetic viewpoint of the semantic map,
identify front view semantic data and back view semantic data for the synthetic viewpoint, and
classify whether an interferent is present within a serum or plasma portion of the specimen based on the front view semantic data, while taking into account the back view semantic data.

Assignees

• Siemens Healthcare Diagnostics Inc

Inventors

• Kluckner Stefan
• Sun Shanhui
• Chang Yao-Jen
• Chen Terrence
• Pollack Benjamin S

Classifications

• G01N35/00732 Primary

  Identification of carriers, materials or components in automatic analysers · CPC title

• G01N2035/00752

  bar codes · CPC title

• G01N35/00584

  Control arrangements for automatic analysers · CPC title

• G01B11/06

  for measuring thickness {; e.g. of sheet material (thickness measurement by thermal means G01B21/085)} · CPC title

• B01L2300/021

  Identification, e.g. bar codes · CPC title