公开(公告)号：US11238318B2

公开(公告)日：2022-02-01

申请号：US16604125

申请日：2018-04-10

Applicant: Siemens Healthcare Diagnostics Inc.

Inventor： Shanhui Sun ,  Stefan Kluckner ,  Yao-Jen Chang ,  Terrence Chen ,  Benjamin S. Pollack

IPC: G06K9/00 ,  A61B5/00 ,  G06K9/62 ,  G06K9/20 ,  G06N3/04 ,  G06N3/08 ,  G06T7/00

Abstract: A method of characterizing a serum and plasma portion of a specimen in regions occluded by one or more labels. The characterization may be used for determining Hemolysis (H), Icterus (I), and/or Lipemia (L), or Normal (N) of a serum or plasma portion of a specimen. The method includes capturing one or more images of a labeled specimen container including a serum or plasma portion, processing the one or more images with a convolutional neural network to provide a determination of Hemolysis (H), Icterus (I), and/or Lipemia (L), or Normal (N). In further embodiments, the convolutional neural network can provide N′-Class segmentation information. Quality check modules and testing apparatus adapted to carry out the method are described, as are other aspects.

公开(公告)号：US11022620B2

公开(公告)日：2021-06-01

申请号：US16349075

申请日：2017-11-13

Applicant: Siemens Healthcare Diagnostics Inc.

Inventor： Stefan Kluckner ,  Shanhui Sun ,  Yao-Jen Chang ,  Terrence Chen ,  Benjamin S. Pollack

IPC: G01N35/00 ,  G06T7/11 ,  B01L9/00 ,  G01N21/27 ,  G06T7/00 ,  G01J3/10 ,  G01N21/25 ,  G01J3/28 ,  G06T5/50 ,  G01B11/00 ,  G01B11/06

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.

公开(公告)号：US20190277870A1

公开(公告)日：2019-09-12

申请号：US16349075

申请日：2017-11-13

Applicant: Siemens Healthcare Diagnostics Inc.

Inventor： Stefan Kluckner ,  Shanhui Sun ,  Yao-Jen Chang ,  Terrence Chen ,  Benjamin S. Pollack

IPC: G01N35/00 ,  G01N21/27 ,  G06T7/11 ,  G06T7/00 ,  B01L9/00

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.

公开(公告)号：US20180239936A1

公开(公告)日：2018-08-23

申请号：US15551565

申请日：2016-02-16

Applicant: Siemens Healthcare Diagnostics Inc.

Inventor： Stefan Kluckner ,  Yao-Jen Chang ,  Wen Wu ,  Benjamin Pollack ,  Terrence Chen

IPC: G06K7/10 ,  G06K7/14

CPC classification number: G06K7/10722 ,  B01L3/5453 ,  G01N35/00732 ,  G01N2035/00752 ,  G06K7/1413 ,  G06K7/1439 ,  G06K7/1491 ,  G06K9/629 ,  G06K2209/19

Abstract: Barcode tag conditions on sample tubes are detected utilizing side view images of sample tubes for streamlining handling in clinical laboratory automation systems. The condition of the tags may be classified into classes, each divided into a list of additional subcategories that cover individual characteristics of the tag quality. According to an embodiment, a tube characterization station (TCS) is utilized to obtain the side view images. The TCS enables the simultaneous or near-simultaneous collection of three images for each tube, resulting in a 360 degree side view for each tube. The method is based on a supervised scene understanding concept, resulting in an explanation of each pixel into its semantic meaning. Two parallel low-level cues for condition recognition, in combination with a tube model extraction cue, may be utilized. The semantic scene information is then integrated into a mid-level representation for final decision making into one of the condition classes.

公开(公告)号：US20180046883A1

公开(公告)日：2018-02-15

申请号：US15551566

申请日：2016-02-16

Applicant: Siemens Healthcare Diagnostics Inc.

Inventor： Khurram Soomro ,  Yao-Jen Chang ,  Stefan Kluckner ,  Wen Wu ,  Benjamin Pollack ,  Terrence Chen

IPC: G06K9/62 ,  G06K9/20 ,  G06K9/46 ,  B01L9/06 ,  G06T7/11 ,  G06K7/14 ,  G01N35/00 ,  B01L3/00 ,  G06T7/00 ,  G06K9/78

CPC classification number: G06K9/6269 ,  B01L3/5453 ,  B01L9/06 ,  B01L2200/143 ,  B01L2300/021 ,  B01L2300/0809 ,  G01N35/00613 ,  G01N35/00732 ,  G01N2035/00752 ,  G06K7/1413 ,  G06K9/2063 ,  G06K9/3233 ,  G06K9/46 ,  G06K9/6256 ,  G06K9/6277 ,  G06K9/78 ,  G06K2209/057 ,  G06T7/0012 ,  G06T7/11 ,  G06T2207/30204

Abstract: Embodiments are directed to classifying barcode tag conditions on sample tubes from top view images to streamline sample tube handling in advanced clinical laboratory automation systems. The classification of barcode tag conditions leads to the automatic detection of problematic barcode tags, allowing for a user to take necessary steps to fix the problematic barcode tags. A vision system is utilized to perform the automatic classification of barcode tag conditions on sample tubes from top view images. The classification of barcode tag conditions on sample tubes from top view images is based on the following factors: (1) a region-of-interest (ROI) extraction and rectification method based on sample tube detection; (2) a barcode tag condition classification method based on holistic features uniformly sampled from the rectified ROI; and (3) a problematic barcode tag area localization method based on pixel-based feature extraction.

公开(公告)号：US12254694B2

公开(公告)日：2025-03-18

申请号：US16630286

申请日：2018-06-25

Applicant: Siemens Healthcare Diagnostics Inc.

Inventor： Yao-Jen Chang ,  Stefan Kluckner ,  Benjamin S. Pollack ,  Terrence Chen

IPC: G01N21/25 ,  G01N35/00 ,  G01N35/04 ,  G06V20/52

Abstract: Embodiments provide a method of using image-based tube top circle detection based on multiple candidate selection to localize the tube top circle region in input images. According to embodiments provided herein, the multi-candidate selection enhances the robustness of tube circle detection by making use of multiple views of the same tube to improve the robustness of tube top circle detection. With multiple candidates extracted from images under different viewpoints of the same tube, the multi-candidate selection algorithm selects an optimal combination among the candidates and provides more precise measurement of tube characteristics. This information is invaluable in an IVD environment in which a sample handler is processing the tubes and moving the tubes to analyzers for testing and analysis.

公开(公告)号：US11927736B2

公开(公告)日：2024-03-12

申请号：US17251744

申请日：2019-06-10

Applicant: Siemens Healthcare Diagnostics Inc.

Inventor： Kai Ma ,  Yao-Jen Chang ,  Terrence Chen ,  Benjamin S. Pollack

IPC: G02B21/34 ,  G01N35/00 ,  G06F18/214 ,  G06F18/241 ,  G06F18/2431 ,  G06T7/00 ,  G06V10/10 ,  G06V10/25 ,  G06V10/764 ,  G06V10/82

CPC classification number: G02B21/34 ,  G01N35/00732 ,  G06F18/241 ,  G06F18/2431 ,  G06T7/0012 ,  G06V10/25 ,  G06V10/764 ,  G06V10/82 ,  G01N2035/00752 ,  G06F18/214 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30024 ,  G06V10/16

Abstract: A method of characterizing a serum or plasma portion of a specimen in a specimen container provides a fine-grained HILN index (hemolysis, icterus, lipemia, normal) of the serum or plasma portion of the specimen, wherein the H, I, and L classes may each have five to seven sub-classes. The HILN index may also have one un-centrifuged class. Pixel data of an input image of the specimen container may be processed by a deep semantic segmentation network having, in some embodiments, more than 100 layers. A small front-end container segmentation network may be used to determine a container type and boundary, which may additionally be input to the deep semantic segmentation network. A discriminative network may be used to train the deep semantic segmentation network to generate a homogeneously structured output. Quality check modules and testing apparatus configured to carry out the method are also described, as are other aspects.

公开(公告)号：US11650197B2

公开(公告)日：2023-05-16

申请号：US16072394

申请日：2017-01-24

Applicant: Siemens Healthcare Diagnostics Inc.

Inventor： Stefan Kluckner ,  Yao-Jen Chang ,  Terrence Chen ,  Benjamin S. Pollack

IPC: G01N21/31 ,  G06T7/00 ,  G06T7/62 ,  G01F23/00 ,  G01N33/49 ,  G01N21/90 ,  G01N35/00 ,  G01N35/04 ,  G06K9/62 ,  G06N7/08 ,  G01N35/02 ,  G01N21/17

CPC classification number: G01N21/31 ,  G01F23/00 ,  G01N21/90 ,  G01N33/49 ,  G01N33/491 ,  G01N35/00732 ,  G01N35/04 ,  G06K9/628 ,  G06K9/6269 ,  G06N7/08 ,  G06T7/0012 ,  G06T7/62 ,  G01N35/0099 ,  G01N35/02 ,  G01N2021/1772 ,  G01N2021/1776 ,  G01N2035/00495 ,  G01N2035/00752 ,  G01N2035/0406 ,  G01N2035/0439 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/10144 ,  G06T2207/10152 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30024

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.

公开(公告)号：US11035870B2

公开(公告)日：2021-06-15

申请号：US16320198

申请日：2017-07-07

Applicant: Siemens Healthcare Diagnostics Inc.

Inventor： Stefan Kluckner ,  Yao-Jen Chang ,  Terrence Chen ,  Benjamin S. Pollack

IPC: G06K9/00 ,  G01N35/02 ,  G01N21/25 ,  G01N21/55 ,  G01N21/63 ,  G06K9/62 ,  G06K9/20 ,  G06T7/586 ,  G01N35/00 ,  G01N35/04 ,  B01L3/00

Abstract: A model-based method of determining characteristics of a specimen container cap to identify the container cap. The method includes providing a specimen container including a container cap; capturing backlit images of the container cap taken at different exposures lengths and using a plurality of different nominal wavelengths; selecting optimally-exposed pixels from the images at different exposure lengths at each nominal wavelength to generate optimally-exposed image data for each nominal wavelength; classifying the optimally-exposed pixels as at least being one of a tube, a label or a cap; and identifying a shape of the container cap based upon the optimally-exposed pixels classified as being the cap and the image data for each nominal wavelength. Quality check modules and specimen testing apparatus adapted to carry out the method are described, as are numerous other aspects.

公开(公告)号：US11009467B2

公开(公告)日：2021-05-18

申请号：US15551562

申请日：2016-02-16

Applicant: Siemens Healthcare Diagnostics Inc.

Inventor： JinHyeong Park ,  Yao-Jen Chang ,  Wen Wu ,  Terrence Chen ,  Benjamin Pollack

IPC: G01N21/94 ,  G06T7/00 ,  G01J3/46 ,  G01J3/50 ,  G01N21/25 ,  G01N21/03 ,  G01N21/27 ,  G01N35/00 ,  G06K9/00 ,  G06K9/62 ,  G01N21/59

Abstract: A model-based method of inspecting a specimen for presence of one or more interferent, such as Hemolysis, Icterus, and/or Lipemia (HI L) is provided. The method includes generating a pixelated image of the specimen in a first color space, determining color components (e.g., an a-value and a b-value) for pixels in the pixelated image, classifying of the pixels as being either liquid or non-liquid, defining one or more liquid regions based upon the pixels classified as liquid, and determining a presence of one or more interferent within the one or more liquid regions. The liquid classification is based upon a liquid classification model. Pixel classification may be based on a trained multiclass classifier. Interference level for the one or more interferent may be provided. Testing apparatus adapted to carry out the method are described, as are other aspects.