PROCESSING OF HISTOLOGY IMAGES WITH A CONVOLUTIONAL NEURAL NETWORK TO IDENTIFY TUMORS

    公开(公告)号:WO2019133538A3

    公开(公告)日:2019-07-04

    申请号:PCT/US2018/067349

    申请日:2018-12-21

    Abstract: A convolutional neural network CNN is applied to identifying tumors in a histological image. The CNN has one channel assigned to each of a plurality of tissue classes that are to be identified, there being at least one class for each of non-tumorous and tumorous tissue types. Multi-stage convolution is performed on image patches extracted from the histological image followed by multi-stage transpose convolution to recover a layer matched in size to the input image patch. The output image patch thus has a one-to-one pixel-to-pixel correspondence with the input image patch such that each pixel in the output image patch has assigned to it one of the multiple available classes. The output image patches are then assembled into a probability map that can be co-rendered with the histological image either alongside it or over it as an overlay. The probability map can then be stored linked to the histological image.

    SLIDE RACK GRIPPER APPARATUS
    2.
    发明申请

    公开(公告)号:WO2019109028A1

    公开(公告)日:2019-06-06

    申请号:PCT/US2018/063461

    申请日:2018-11-30

    Abstract: A slide rack gripper apparatus is provided that simultaneously conveys a plurality of glass slides in the protection of a slide rack within a digital slide scanning apparatus. The slide rack gripper apparatus conveys the plurality of glass slides from a slide rack carousel to a scanning stage for processing. The slide rack gripper includes a first motor attached to a base configured to drive a finger mount attached to the base along a first linear axis. The slide rack gripper apparatus also includes a second motor attached to the finger mount and configured to drive opposing gripper fingers attached to the finger mount along a second linear axis. The second motor is also configured to drive individual gripper fingers along a third linear axis to move the gripper fingers toward each other and away from each other to grasp or release a slide rack.

    COLOR MONITOR SETTINGS REFRESH
    3.
    发明申请

    公开(公告)号:WO2019109024A1

    公开(公告)日:2019-06-06

    申请号:PCT/US2018/063456

    申请日:2018-11-30

    Abstract: Described herein are systems and methods that place a known color monitor (known by unique serial number or SKU) into a desired state for displaying digital pathology image data. Using an application programming interface, any color monitor that implements MCCS can be calibrated and characterized immediately before each display of digital pathology image data and can also be periodically reset (if needed) during display of digital pathology image data.

    SAFETY LIGHT CURTAIN TO DISABLE CAROUSEL ROTATION

    公开(公告)号:WO2019109020A1

    公开(公告)日:2019-06-06

    申请号:PCT/US2018/063450

    申请日:2018-11-30

    Abstract: A digital slide scanning apparatus includes a safety light curtain that operates to disable the motor that rotates the carousel when the presence of an object (e.g., the fingers of an operator) is detected within a predetermined area of the carousel. The light curtain also operates to disable the motor that rotates the carousel when an improperly positioned glass slide or slide rack is detected. The digital slide scanning apparatus also includes a multi-color status indicator for each rack slot that indicates the rack slot location of an improperly positioned glass slide or slide rack.

    SLIDE RACK DETERMINATION SYSTEM
    5.
    发明申请

    公开(公告)号:WO2019104342A1

    公开(公告)日:2019-05-31

    申请号:PCT/US2018/062659

    申请日:2018-11-27

    Abstract: A slide rack determination system for a digital slide scanning apparatus. In an embodiment, a motor drives a slide rack at a known rate toward an engagement surface. The elapsed time until engagement may be used to detect the presence or absence of the slide rack and/or the height of the slide rack. In addition, one or more sensors may detect one or more features of the slide rack, and these feature(s) may be used to determine the presence or absence of a slide rack, whether usage of the slide rack is supported or unsupported by the digital slide scanning apparatus, the orientation of the slide rack, and/or the manufacturer and/or model of the slide rack.

    TWO-DIMENSIONAL AND THREE-DIMENSIONAL FIXED Z SCANNING

    公开(公告)号:WO2019068045A1

    公开(公告)日:2019-04-04

    申请号:PCT/US2018/053639

    申请日:2018-09-28

    Abstract: Apparatus and methods for scanning a 2D or 3D image of a specimen without relative Z-axis motion between the specimen and the objective lens. In an embodiment, the apparatus includes a tilted camera having individual lines of pixels. Each line of pixels can be separately processed and is at a different image plane with respect to the stage. The depth of field of each line of pixels abuts, slightly overlaps, or is slightly spaced apart from the adjacent lines of pixels in the tilted camera. The angle of the tilt determines the relationship (abut, overlapping, or spaced) of the adjacent lines of pixels. The individual image lines produced by each line of pixels can be combined into a 3D volume image of a sample. Also, the highest-contrast line at each X-Y location can be combined into an in-focus 2D image of the sample.

    AUTOMATIC NUCLEAR SEGMENTATION
    7.
    发明申请
    AUTOMATIC NUCLEAR SEGMENTATION 审中-公开
    自动核分割

    公开(公告)号:WO2017106106A1

    公开(公告)日:2017-06-22

    申请号:PCT/US2016/066200

    申请日:2016-12-12

    Abstract: Automatic nuclear segmentation. In an embodiment, a plurality of superpixels are determined in a digital image. For each of the superpixels, any superpixels located within a search radius from the superpixel are identified, and, for each unique local combination between the superpixel and any identified superpixels located within the search radius from the superpixel, a local score for the local combination is determined. One of a plurality of global sets of local combinations with an optimum global score is identified based on the determined local scores.

    Abstract translation:

    自动核分割。 在一个实施例中,在数字图像中确定多个超像素。 对于每个超像素,标识位于超像素的搜索半径内的任何超像素,并且对于超像素和位于来自超像素的搜索半径内的任何标识的超像素之间的每个唯一局部组合,局部组合的局部分数是 决心。 基于确定的局部分数来识别具有最佳总体分数的多个局部组合的全局集合之一。

    REAL-TIME FOCUSING IN LINE SCAN IMAGING
    8.
    发明申请
    REAL-TIME FOCUSING IN LINE SCAN IMAGING 审中-公开
    实时聚焦在线扫描成像

    公开(公告)号:WO2017053891A1

    公开(公告)日:2017-03-30

    申请号:PCT/US2016/053581

    申请日:2016-09-23

    CPC classification number: G02B27/40 G02B7/28 G02B21/02 G02B21/06 G03B13/36

    Abstract: System for acquiring a digital image of a sample on a microscope slide. In an embodiment, the system comprises a stage configured to support a sample, an objective lens having a single optical axis that is orthogonal to the stage, an imaging sensor, and a focusing sensor. The system further comprises at least one beam splitter optically coupled to the objective lens and configured to receive a field of view corresponding to the optical axis of the objective lens, and simultaneously provide at least a first portion of the field of view to the imaging sensor and at least a second portion of the field of view to the focusing sensor. The focusing sensor may simultaneously acquire image(s) at a plurality of different focal distances and/or simultaneously acquire a pair of mirrored images, each comprising pixels acquired at a plurality of different focal distances.

    Abstract translation: 用于在显微镜载玻片上获取样品的数字图像的系统。 在一个实施例中,系统包括被配置为支撑样本的台,具有与舞台正交的单个光轴的物镜,成像传感器和聚焦传感器。 该系统还包括光学耦合到物镜并被配置为接收与物镜的光轴相对应的视场的至少一个分束器,并且同时向成像传感器提供视野的至少第一部分 以及视场的至少第二部分到聚焦传感器。 聚焦传感器可以同时获取多个不同焦距的图像和/或同时获取一对镜像图像,每个镜像图像包括以多个不同焦距获取的像素。

    AUTOMATED STAIN FINDING IN PATHOLOGY BRIGHT-FIELD IMAGES
    9.
    发明申请
    AUTOMATED STAIN FINDING IN PATHOLOGY BRIGHT-FIELD IMAGES 审中-公开
    自动化的斑块在病理学领域中的发现

    公开(公告)号:WO2017049226A1

    公开(公告)日:2017-03-23

    申请号:PCT/US2016/052331

    申请日:2016-09-16

    CPC classification number: G06K9/00127 G06K9/00147

    Abstract: Automated stain finding. In an embodiment, an image of a sample comprising one or more stains is received. For each of a plurality of pixels in the image, an optical density vector for the pixel is determined. The optical density vector comprises a value for each of the one or more stains, and represents a point in an optical density space that has a number of dimensions equal to a number of the one or more stains. The optical density vectors are transformed from the optical density space into a representation in a lower dimensional space. The lower dimensional space has a number of dimensions equal to one less than the number of dimensions of the optical density space. An optical density vector corresponding to each of the one or more stains is identified based on the representation.

    Abstract translation: 自动染色。 在一个实施例中,接收包含一个或多个污渍的样品的图像。 对于图像中的多个像素中的每一个,确定像素的光密度矢量。 光密度矢量包括一个或多个污渍中的每一个的值,并且表示光密度空间中具有等于一个或多个污渍数量的维数的点。 光密度矢量从光密度空间变换为较低维空间中的表示。 较低的维数空间具有等于光密度空间的维数的一个维数的数量。 基于该表示来识别对应于一个或多个污渍中的每一个的光密度矢量。

Patent Agency Ranking