Search

EP-4052046-B1 - APPARATUS AND METHODS OF IDENTIFYING TUBE ASSEMBLY TYPE

EP4052046B1EP 4052046 B1EP4052046 B1EP 4052046B1EP-4052046-B1

Inventors

  • NALAM VENKAT, Rayal Raj Prasad
  • POLLACK, BENJAMIN S.
  • CHANG, YAO-JEN
  • NARASIMHAMURTHY, Venkatesh
  • SINGH, VIVEK
  • KAPOOR, Ankur

Dates

Publication Date
20260513
Application Date
20201022

Claims (13)

  1. A method (900) of identifying a tube type, comprising: capturing (902) one or more images of a cap (102A, 102B) affixed to a tube (104A, 104B), the capturing generating a pixelated image of the cap (102A, 102B), the pixelated image including a plurality of pixels; identifying (904) a color of one or more pixels of the pixelated image of the cap (102A, 102B); identifying (906) one or more gradients of a dimension of the cap (102A, 102B); and identifying (908) the tube type based at least on: the color of the one or more pixels, and the one or more gradients of a dimension of the cap (102A, 102B); characterized in that the identifying the tube type is based on a discriminative model, and in that an input to the discriminative model comprises a combination of color components of color feature spaces of the one or more pixels of the pixelated image of the cap and discriminative feature space comprising the one or more gradients of a dimension of the cap (102A, 102B).
  2. The method (900) of claim 1, wherein one or more inputs to the discriminative model comprise a width and/or height of the tube (104A, 104B).
  3. The method (900) of claim 1, wherein an input to the discriminative model comprises - cap weight, or - capturing images of tube assembly (100A, 100B) comprising the cap (102A, 102B) attached atop the tube (104A, 104B) when illuminated using non-visible light comprising IR or near IR, or - a 7-dimensional discriminative feature space of the cap (102A, 102B) comprising hue (H), saturation (S), value (V), maximum value of row gradient (RG-max), R-mean, G-mean, and B-mean, wherein the row gradient is Equation (1): δu i , j δy = u i , j + 1 − u i , j − 1 2 Δ y wherein: u i,j is the two-dimensional value of u at location index i,j i is the x-axis location index, j is the y-axis location index, δu i,j / δy is the numerical derivative of u at location i,j with reference to the y-axis, and Δy is the change in dimension in the vertical dimension.
  4. The method (900) of claim 1, wherein the discriminative model is a linear support vector machine.
  5. The method (900) of claim 1, wherein identifying a color of one or more pixels of the pixelated image of the cap (102A, 102B) comprises utilizing cap opacity or translucence using one or more back-illuminated images of the cap.
  6. The method (900) of claim 1, wherein identifying the color of the one or more pixels comprises calculating a mean color of a plurality of pixels in the pixelated image of the cap (102A, 102B).
  7. The method (900) of claim 1, wherein identifying the color of the one or more pixels is determined by a color space model in a multi-element color space selected from one or more of the group of: HSV, HSL, RGB, Adobe RGB, YIQ, YUV, CIELCAB, CIELUV, ProPhoto, sRGB, Luma plus Chroma, CMYK.
  8. The method (900) of claim 1, wherein identifying the color of the one or more pixels comprises calculating a mean color of a plurality of pixels of the cap (102A, 102B) in the pixelated image and identifying hue, saturation, and value components of the mean color in HSV color space.
  9. The method (900) of claim 1, wherein the one or more gradients of the dimension of the cap (102A, 102B) comprise one or more row gradients, wherein the one or more row gradients preferably comprises a maximum value (RG-max1, RG-max2) of the row gradients as defined in Equation (1).
  10. The method (900) of claim 1, wherein the one or more gradients of the dimension of the cap (102A, 102B) comprise one or more gradients of cap width or cap height.
  11. The method (900) of claim 1, comprising identifying a mismatch between a test ordered and the tube type.
  12. The method of identifying a tube type according to claim 1 comprises: identifying (910) a match between a test ordered and the tube type.
  13. A diagnostic apparatus (800), comprising: an imaging device (807) configured to capture one or more images of a tube assembly (100A, 100B) comprising a cap (102A, 102B) affixed to a tube (104A, 104B), wherein the one or more images comprise one or more pixelated images of the cap (102A, 102B); and a controller (809) communicatively coupled to the imaging device (807), the controller (809) comprising a processor (810) coupled to a memory (812), the memory (812) storing executable program instructions in the form of a discriminative model that are executable to: determine a color of one or more pixels of the one or more pixelated images of the cap (102A, 102B); determine one or more gradients of a dimension of the cap (102A, 102B); and identify a tube type based at least on: the color of the one or more pixels, and the one or more gradients of the dimension of the cap (102A, 102B), wherein an input to the discriminative model comprises a combination of color feature spaces of one or more pixels of the pixelated image of the cap and discriminative feature space comprising the one or more gradients of a dimension of the cap (102A, 102B).

Description

FIELD Embodiments of the present disclosure relate to apparatus and methods of identifying tube assemblies. BACKGROUND Automated testing systems may conduct clinical chemistry or assays using one or more reagents to identify an analyte or other constituent in a biological sample (sample) such as blood serum, blood plasma, urine, interstitial liquid, cerebrospinal liquids, and the like. For convenience and safety reasons, these samples are almost always contained in sample tubes (e.g., blood collection tubes). The sample tubes may be capped and in some cases, and the caps may include a color and/or shape that provides information concerning the type of test to be conducted, type of additive contained in the tube (e.g., serum separator, coagulant such as thrombin, or anticoagulant and specific type thereof, like EDTA or sodium citrate, or anti-glycosis additive), and whether the tube is provided with vacuum capability, and the like. In certain automated testing systems, the sample container and sample are digitally imaged and processed, such as with a computer-aided digital imaging system, so that type and color of the cap can be discerned. During imaging, one or more images of the sample tube (including cap) and sample can be captured. However, such automated testing systems may, under certain conditions, provide variations in performance and can improperly characterize a tube and/or cap type. Thus, improved methods and apparatus of digitally imaging and processing sample containers and caps are sought. US2016/018427A1, WO2018/022280A1 and US2015/064740A1 disclose known apparatuses and methods of identifying tube assembly types. SUMMARY The invention is defined in the independent claims. Preferred embodiments are defined in the dependent claims. BRIEF DESCRIPTION OF THE DRAWINGS The drawings, described below, are for illustrative purposes and are not necessarily drawn to scale. Accordingly, the drawings and descriptions are to be regarded as illustrative in nature, and not as restrictive. The drawings are not intended to limit the scope of the disclosure in any way. Like numerals are used throughout to denote the same or similar elements. FIG. 1A illustrates a side elevation view of a first tube assembly including a cap attached to a tube and a box indicating a location of a mask image shown in FIG. 2A according to one or more embodiments of the disclosure.FIG. 1B illustrates a side elevation view of a second tube assembly including a cap attached to a tube and a box indicating a location of a mask image shown in FIG. 2B according to one or more embodiments of the disclosure.FIG. 2A is a schematic diagram of a mask image of a first cap of a first tube assembly including a box indicating the location of where the mask image aligns with the first tube assembly of FIG. 1A according to one or more embodiments of the disclosure.FIG. 2B is a schematic diagram of a mask image of a second cap of a second tube assembly including a box indicating the location of where the mask image aligns with the second tube assembly of FIG. 1B according to one or more embodiments of the disclosure.FIG. 3A illustrates a side elevation view of portions of a first tube assembly that may be analyzed to determine multiple row gradients according to one or more embodiments of the disclosure.FIG. 3B graphically illustrates a profile of the width of an upper portion of the first tube assembly of FIG. 3A according to one or more embodiments of the disclosure.FIG. 3C graphically illustrates the first order derivative of the graph of FIG. 3B according to one or more embodiments of the disclosure.FIG. 4A illustrates a side elevation view of portions of a second tube assembly that may be analyzed to determine multiple row gradients according to one or more embodiments of the disclosure.FIG. 4B graphically illustrates a profile of the width of an upper portion of the second tube assembly of FIG. 4A according to one or more embodiments of the disclosure.FIG. 4C graphically illustrates the first order derivative of the graph of FIG. 4B according to one or more embodiments of the disclosure.FIG. 5A graphically illustrates a bar chart plot of a spectrum of light (wavelength vs. mean intensity) that passes through a first tube assembly according to one or more embodiments of the disclosure.FIG. 5B graphically illustrates a bar chart plot of a spectrum of light (wavelength vs. mean intensity) that passes through a second tube assembly according to one or more embodiments of the disclosure.FIG. 5C illustrates photographic images of a portion of a back-illuminated, first tube assembly that yielded the graph of FIG. 5A according to one or more embodiments of the disclosure.FIG. 5D illustrates photographic images of a portion of a back-illuminated, second tube assembly that yielded the graph of FIG. 5B according to one or more embodiments of the disclosure.FIG. 6 illustrates a table of examples of different tube assemblies having different cap colors and