LABORATORY SAMPLE CONTAINER HANDLING APPARATUS, LABORATORY AUTOMATION SYSTEM, AND USE

    公开(公告)号:US20230184796A1

    公开(公告)日:2023-06-15

    申请号:US18061717

    申请日:2022-12-05

    CPC classification number: G01N35/025

    Abstract: A laboratory sample container carrier handling apparatus is provided comprising a revolving device, a guiding surface, and a force-applying device, wherein the force-applying device is adapted to apply a force to a laboratory sample container carrier supplied to the revolving device to such an extent that the laboratory sample container carrier is forced against the guiding surface to such an extent that the laboratory sample container carrier rolls off at the guiding surface pushed by the revolving device. A laboratory automation system is also provided comprising such a laboratory sample container carrier handling apparatus and to a use of such a laboratory sample container carrier handling apparatus for handling a laboratory sample container carrier in, in particular such, a laboratory automation system.

    SEPSIS MANAGEMENT
    59.
    发明申请

    公开(公告)号:US20230030564A1

    公开(公告)日:2023-02-02

    申请号:US17772959

    申请日:2020-10-27

    Abstract: The present invention concerns methods for aiding in the risk assessment of a patient with suspected sepsis. For example, the risk of poor outcome (such as of a complicated clinical course and/or of mortality) can be assessed. The methods of the present invention may comprise the steps of (a) determining the amount of the biomarker Presepsin in a sample from a patient with suspected sepsis who has a known qSOFA (quick Sequential Organ Failure-Assessment) score of 0, 1, 2 or 3, (b) determining the amount of the biomarker Pro-calcitonin (PCT) in a sample from the patient, comparing the amounts determined in steps (b) and (c) to reference amounts, and (d) aiding in the risk assessment of a patient with suspected sepsis. The methods of the present invention may be computer-implemented.

    PROCESSING OF IMAGES CONTAINING OVERLAPPING PARTICLES

    公开(公告)号:US20230028525A1

    公开(公告)日:2023-01-26

    申请号:US17813194

    申请日:2022-07-18

    Abstract: A computer-implemented method of generating training data to be used to train a machine learning model for generating a segmentation mask of an image containing overlapping particles. Training data is generated from sparse particle images which contain no overlaps. Generating masks for non-overlapping particles is generally not a problem if the particles can be identified clearly; in many cases simple methods such as thresholding already yield usable masks. The sparse images can then be combined to images which contain artificial overlaps. The same can be done for the masks as well which yields a large amount of training data, because of the many combinations which can be created from just a small set of images. The method is simple yet effective and can be adapted to many domains for example by adding style-transfer to the generated images or by including additional augmentation steps.

Patent Agency Ranking