APPARATUS AND METHOD FOR TRAINING OF MACHINE LEARNING MODELS USING ANNOTATED IMAGE DATA FOR PATHOLOGY IMAGING

    公开(公告)号:US20230411014A1

    公开(公告)日:2023-12-21

    申请号:US18459679

    申请日:2023-09-01

    发明人: Allen H. OLSON

    IPC分类号: G16H50/20 G16H30/40

    CPC分类号: G16H50/20 G16H30/40

    摘要: Features are disclosed for training a machine learning model to identify objects in histological images. A system may obtain an image and determine a number of objects in the image. For example, the system may determine a percentage of objects in the image with a particular object type. Further, the system may determine a weight. The weight may specify a percentage of the image occupied by objects with the particular object type. The system can generate training set data that includes the image, data identifying the number of objects in the image, and the weight. The system can use the training set data to train a machine learning model to predict a number of objects in a different image and a weight. The system can implement the machine learning model based on training the machine learning model.

    SYSTEM AND METHOD FOR MATCHING OF BLOCK AND SLICE HISTOLOGICAL SAMPLES

    公开(公告)号:US20230326025A1

    公开(公告)日:2023-10-12

    申请号:US18210261

    申请日:2023-06-15

    IPC分类号: G06T7/00

    摘要: Features are disclosed for imaging block and slice samples using an imaging system. The imaging system can link the images by identifiers associated with the block and slice samples. The imaging system can train a machine learning algorithm based on correctly linked images. In some embodiments, the trained machine learning algorithm may include an image analysis module or a convolutional neural network. The imaging system can use the trained machine learning algorithm in order to determine a confidence score of a match between the block and the slice samples. The trained machine learning algorithm can use features of the block and the slice samples such as shape and tissue morphology to determine whether the samples match. In some embodiments, when the confidence score is below a certain threshold, the imaging system can alert a user that the samples may not match.

    HIGH AND LOW FREQUENCY FEATURE MAP GENERATION FOR H&E PATHOLOGY IMAGES

    公开(公告)号:US20230298320A1

    公开(公告)日:2023-09-21

    申请号:US18115082

    申请日:2023-02-28

    发明人: Ji Wang Chad Salinas

    摘要: An apparatus and methods for determining features in an image of a Hematoxylin and Eosin (H&E) stained tissue sample. An apparatus can be configured to apply a machine learning model to the H&E stained tissue sample image to determine features in the image. Applying the machine learning model can include performing convolution operations on the H&E stained tissue sample image to generate a plurality of initial feature maps, applying octave-convolution-first-layer operations on the initial feature maps to generate initial high-frequency feature maps and low-frequency feature maps, applying octave-convolution operations on the high-frequency initial feature maps to generate refined high-frequency feature maps, applying octave-convolution operations on the low-frequency initial feature maps to generate refined low-frequency feature maps, and applying octave-convolution last layer operations on the refined high-frequency feature maps and the refined low-frequency feature maps to produce combined feature maps.

    Power off delay system and method

    公开(公告)号:US11604200B2

    公开(公告)日:2023-03-14

    申请号:US17813877

    申请日:2022-07-20

    摘要: A power off delay system and method is configured to delay termination of electrical power to a digital pathology device in a power off condition. If the apparatus includes a UPS, the power off delay system and method delays termination of electrical power when a power switch is turned off and when a catastrophic power failure occurs. During the delay of the termination of electrical power, the digital pathology device is configured to control the scanning stage system and the glass slide conveyor system and the slide rack conveyor system to place each of these systems into a known state and position all glass slides into a known position prior to the termination of electrical power to the digital pathology device. This allows the digital pathology device to resume normal operation upon power up.

    Real-time autofocus focusing algorithm

    公开(公告)号:US11454781B2

    公开(公告)日:2022-09-27

    申请号:US17085962

    申请日:2020-10-30

    摘要: A digital scanning apparatus is provided that includes imaging and focusing sensors and a processor to analyze the image data captured by the imaging and focusing sensors and adjust the focus of the scanning apparatus in real time during a scanning operation. The individual pixels of the imaging sensor are all in the same image plane with respect to the optical path of the digital scanning apparatus. The individual pixels of the focusing sensor are each in a different image plane with respect to the optical path, and one pixel of the focusing sensor is on the same image plane as the image sensor. The processor analyzes image data from the imaging sensor and the focusing sensor and determines a distance and direction to adjust the relative position of an objective lens and a stage of the digital scanning apparatus to achieve optimal focus during the scanning operation.

    USER-ASSISTED ITERATION OF CELL IMAGE SEGMENTATION

    公开(公告)号:US20220277440A1

    公开(公告)日:2022-09-01

    申请号:US17634212

    申请日:2020-09-02

    IPC分类号: G06T7/00 G06T7/11

    摘要: A segmentation of cell image data obtains cell segmentation data for the nuclei, cytoplasm and cell membranes, which are displayed on an image pane. A data pane is also displayed which contains a table with rows specific to cells and columns specific to cell attributes. In an editing session, a user can select cells for deletion either from the data pane or the image pane. Responsive to a selection via the data pane, the image pane is updated and responsive to a selection via the image pane, the data pane is updated. At any time, the user can command a re-segmentation taking account of the edits, which starts from a version of the previous nuclear segmentation data which has been edited to remove data relating to cells selected for deletion and then from that determines the cytoplasm and cell membrane segmentation data.

    COMPUTER SUPPORTED REVIEW OF TUMORS IN HISTOLOGY IMAGES AND POST OPERATIVE TUMOR MARGIN ASSESSMENT

    公开(公告)号:US20220076410A1

    公开(公告)日:2022-03-10

    申请号:US17415396

    申请日:2020-05-29

    发明人: Walter Georgescu

    摘要: A computer apparatus and method for identifying and visualizing tumors in a histological image and measuring a tumor margin are provided. A CNN is used to classify pixels in the image according to whether they are determined to relate to non-tumorous tissue, or one or more classes for tumorous tissue. Segmentation is carried out based on the CNN results to generate a mask that marks areas occupied by individual tumors. Summary statistics for each tumor are computed and supplied to a filter which edits the segmentation mask by filtering out tumors deemed to be insignificant. Optionally, the tumors that pass the filter may be ranked according to the summary statistics, for example in order of clinical relevance or by a sensible order of review for a pathologist. A visualization application can then display the histological image having regard to the segmentation mask, summary statistics and/or ranking. Tumor masses extracted by resection are painted with an ink to highlight its surface region. The CNN is trained to distinguish ink and no-ink tissue as well as tumor and no-tumor tissue. The CNN is applied to the histological image to generate an output image whose pixels are assigned to the tissue classes. Tumor margin status of the tissue section is determined by the presence or absence of tumor-and-ink classified pixels. Tumor margin involvement and tumor margin distance are determined by computing additional parameters based on classification-specified inter-pixel distance parameters.