US-12626522-B2 - Instrument parameter determination based on sample tube identification

US12626522B2US 12626522 B2US12626522 B2US 12626522B2US-12626522-B2

Abstract

A system and method for reducing the responsibility of the user significantly by applying an optical system that can identify container like sample tubes with respect to their characteristics, e.g., shapes and inner dimensions, from their visual properties by capturing images from a rack comprising container and processing said images for reliably identifying a container tyle.

Inventors

Volker von Einem
Christopher Almy, JR.
Timo Ottenstein
Jaiganesh Srinivasan
Christian Luca
Andra Petrovai
Dan-Sebastian Bacea
Nicoleta-Ligia Novacean
Demetrio Sanchez-Martinez
Mark Wheeler

Assignees

STRATEC SE
INSTRUMENTATION LABORATORY COMPANY

Dates

Publication Date: 20260512
Application Date: 20230119
Priority Date: 20220119

Claims (20)

1 . A method for determining characteristics of a sample container in an automated testing system, the method comprising the steps of: identifying the presence of a rack within the automated testing system; capturing at least one image of the rack using a sensor of the automated testing system; processing the at least one image to determine that the rack comprises at least one container; processing the at least one image to determine one or more characteristics of the container selected from the group consisting of width, height, shape, and presence of a cap; processing the at least one image to determine presence or absence of a false bottom of the container; determining a type or class of the container based at least on the one or more characteristics of the container; and capturing at least a second image of the rack, measuring height, width, or both of the container at different heights in each image, and calculating mean values with standard deviation for determining the container's dimensions.
2 . The method according to claim 1 , wherein determining the type or class of the container based on the one or more characteristics of the container comprises identifying the type or class of the container using container data stored in a database, and wherein the database further comprises a set of instrument parameters assigned to a container type or container class.
3 . The method according to claim 1 , wherein presence of the container is determined by determining intersection points of a top of the rack and a background illumination by identifying a 2D pixel intensity matrix in different sections in the at least one image where the background illumination is present, followed by a first-order differentializing for identifying a slope in the intensity profile.
4 . The method according to claim 3 , wherein the 2D pixel intensity matrix is convolved to reduce noise in the image.
5 . The method of claim 4 , wherein the 2D pixel intensity matrix is converted to a 1D matrix by taking an average along each row and an intensity plot and variance of the 1D matrix is used for determining the presence of the container.
6 . The method of claim 1 , wherein the image is classified into one of two classes by a convolutional neural network (CNN).
7 . The method of claim 1 , wherein determining the type or class of the container comprises determining presence or absence of a false bottom of the container by comparing the position of the container's inner lower end with the position of a bottom end of the rack or the bottom end of a rack insert.
8 . The method of claim 1 , further comprising illuminating the container using a light source positioned to illuminate a first side of the rack opposite a second side of the rack, wherein the sensor is arranged to capture an image of the second side of the rack.
9 . The method according to claim 8 , wherein a width for illumination of the container is in a range between 15 to 35 mm.
10 . The method according to claim 8 , wherein the light source comprises LEDs arranged in two opposite arranged LED stripes.
11 . The method of claim 1 , further comprising: determining a region of interest (ROI) in the at least one image by identifying reference points; determining an upper end of the rack in the ROI; and determining edges of an upper end of the container within the ROI.
12 . The method of claim 1 , wherein determining presence or absence of the false bottom of the container is based on comparing a position of the container's inner lower end with the position of a bottom end of the rack or a bottom end of an insert of the rack.
13 . The method of claim 1 , wherein determining presence or absence of the false bottom of the container further comprises capturing a plurality of images of the container while rotating the container, and processing the plurality of images to determine presence or absence of the false bottom.
14 . A method for determining characteristics of a sample container in an automated testing system, the method comprising the steps of: identifying the presence of a rack within the automated testing system; capturing at least one image of the rack using a sensor of the automated testing system; determining that the rack comprises at least one container; determining, based on the at least one image, one or more characteristics of the container selected from the group consisting of width, height, shape, and presence of a cap; determining, based on the at least one image, presence or absence of a false bottom of the container; determining a type or class of the container based at least on the one or more characteristics of the container; determining boundaries of separated layers of a material located in the container; determining hematocrit based on one or more of layers, liquid levels, or liquid volumes percentage of a first layer and a second layer in the one container; and capturing multiple images of the container during rotation of the container in front of the sensor and forming a segmented picture from the multiple images.
15 . The method of claim 14 , wherein the first layer comprises red blood cells and the second layer comprises plasma.
16 . The method of claim 14 , further comprising the step of applying the segmented picture to a convolutional neural network (CNN) for determining an upper boundary and a lower boundary of a plasma layer in the segmented picture for generating a bounding box enclosing the plasma layer in all segments of the segmented picture.
17 . The method of claim 16 , comprising the step of rearranging the segments of the segmented picture prior to determining again the upper boundary and the lower boundary of the plasma layer in the newly arranged segmented picture for generating a bounding box enclosing the plasma layer in all segments of the segmented picture.
18 . A system for determining characteristics of a container in a rack for an automated testing system, the system comprising: a sensor configured to capture one or more images of a first side of the rack; a processor configured to receive the one or more images; to process the one or more images to determine one or more characteristics of the container selected from the group consisting of width, height, shape, and presence of a cap; and to process the one or more images to determine presence or absence of a false bottom of the container; a light source configured to provide back illumination by illuminating a second side of the rack opposite the first side of the rack; and comprising a second light source configured to provide front illumination by illuminating the first side of the rack, and wherein the first light source and the second light source each comprise an LED stripe.
19 . The system of claim 18 , further comprising a database comprising characteristics of a plurality of containers, and wherein the processor is further configured to determine a type or class of the container based on the one or more characteristics of the container and information of the characteristics of the plurality of containers from the database.
20 . The system of claim 18 , wherein the sensor is a camera selected from the group consisting of a monochrome CMOS sensor and a color sensor.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS The present application claims priority to Luxembourg Patent Application No. LU 102902 filed on Jan. 19, 2022, and claims the benefit of the filing of U.S. Provisional Application Ser. No. 63/304,809 filed on Jan. 31, 2022. The aforementioned applications are hereby incorporated by reference in their entirety. BACKGROUND OF THE INVENTION Field of the Invention The invention relates to a method for determining the type or class of a container in automated analyser and for determining boundaries of separated layers in a material located in such a container. Brief Description of the Related Art Automated analyser systems for use in clinical diagnostics and life sciences are produced by several companies. Such systems perform analytical assays like in vitro diagnostic assays on substantially liquid patient samples comprising body liquids like whole blood samples. The samples are comprised in consumables which will be transported in the automated analyzer systems in racks. The term liquid refers, in the context of the present disclosure, to patient samples (including blood and plasma), buffers, reagents or solutions which may also comprise solids like particles. The liquids are handled by probes or pipettes. The handling of appropriate liquid volumes is related to the volume of a container like a tube as the volume of a tube depends on its diameter and height. It is a common task in laboratory instrumentation to aspirate liquids from containers of different kind, like sample tubes, with differing volumes. A liquid's upper surface level depends on a total volume of the liquid in a container, and the container's geometry which depends in turn from height, width, shape, inner diameter and/or bottom height and other differing properties. Additionally, the required liquid filling height has an important impact on the instrument performance within the meaning that a too high liquid level might lead to contaminations, whereas a too low liquid level might lead to insufficient sample aspiration due to a probe that fails to immerge into the liquid. A consumable sample comprising a sample tube is usually placed into a rack for allowing the movement of the consumable and to keep it in an upright position. The consumable typically projects the upper end of the rack whereas the height of the consumable determines the amount of projection. If different circular containers with an identical height have different diameters, the upper liquid level of a defined volume will differ. This dependency between diameter and height is important with respect to a required liquid level tracking, i.e., the required velocity of a probe following a liquid's upper surface while aspirating. When placed on a rack, the inner tube bottom is higher than outer tube bottom. Calculating a liquid's upper level using the geometric properties of a wrong tube bottom may result in a too high or too low stop position for the probe. Thus, the knowledge of the tube bottom geometry is important for avoiding a crash of the probe when moving the probe downwards. Knowing the upper surface level of a liquid in a tube allows to quickly move the probe close to the surface before liquid level detection (LLD) is activated which requires a slower Z move (up and down) velocity hence resulting in lower throughput. Knowing the hematocrit of a blood sample prevents an instrument to move a probe too far downwards so that red blood cells (RBC) will be aspirated when only plasma is intended to be suctioned. The aspiration of RBC might lead to wrong results of an assay. Hematocrit (HCT) or Packed cell volume (PCV) is defined by CLSI H07-A3 (Vol 20 N. 18; October 2000) as the measure of the ratio of the volume occupied by the red blood cells (RBC) to the volume of the whole blood, expressed as a fraction. HCT can be also expressed as a percentage. Existing instruments handle these variations by requiring the user to manually sort tube types of common properties in one specific rack type that is identified by a rack barcode which contains a rack type. An alternative but technically similar approach is to dedicate certain positions within a known rack to specific tube types. In both cases, it is up the user to load a tube into the right rack and or position according to its type which might lead to error conditions due to human mistakes. Health care statistics show that human failure is one of the main reasons for harm on patients related to medical devices. Published International patent application WO 2020/219869 A1 relates to systems and methods for automatically tailoring treatment of samples in sample containers carried in a rack. The systems and methods may identify sample containers in the rack and/or detect various characteristics associated with the containers and/or the rack. This information may then be used to tailor their treatment, such as by aspirating and dispensing fluid from the sample containers in a way that accounts for