公开(公告)号：US11748981B2

公开(公告)日：2023-09-05

申请号：US17731228

申请日：2022-04-27

Applicant: AstraZeneca Computational Pathology GmbH

Inventor： Guenter Schmidt ,  Nicolas Brieu ,  Ansh Kapil ,  Jan Martin Lesniak

IPC: G06V10/82 ,  G06T7/00 ,  G06V20/69 ,  G06V10/764 ,  G06T7/136 ,  G06T7/33 ,  G06T7/35 ,  G01N1/30 ,  G06F18/2413

CPC classification number: G06V10/82 ,  G01N1/30 ,  G06F18/2414 ,  G06T7/0012 ,  G06T7/136 ,  G06T7/337 ,  G06T7/35 ,  G06V10/764 ,  G06V20/695 ,  G06V20/698 ,  G01N2800/52 ,  G01N2800/7028 ,  G06T2207/20084 ,  G06T2207/30024 ,  G06T2207/30242

Abstract: A method for indicating how a cancer patient will respond to a predetermined therapy relies on spatial statistical analysis of classes of cell centers in a digital image of tissue of the cancer patient. The cell centers are detected in the image of stained tissue of the cancer patient. For each cell center, an image patch that includes the cell center is extracted from the image. A feature vector is generated based on each image patch using a convolutional neural network. A class is assigned to each cell center based on the feature vector associated with each cell center. A score is computed for the image of tissue by performing spatial statistical analysis based on classes of the cell centers. The score indicates how the cancer patient will respond to the predetermined therapy. The predetermined therapy is recommended to the patient if the score is larger than a predetermined threshold.

公开(公告)号：US20220254020A1

公开(公告)日：2022-08-11

申请号：US17731228

申请日：2022-04-27

Applicant: AstraZeneca Computational Pathology GmbH

Inventor： Guenter Schmidt ,  Nicolas Brieu ,  Ansh Kapil ,  Jan Martin Lesniak

IPC: G06T7/00 ,  G06T7/136 ,  G06T7/33 ,  G06T7/35 ,  G01N1/30 ,  G06V10/82 ,  G06V20/69 ,  G06K9/62

Abstract: A method for indicating how a cancer patient will respond to a predetermined therapy relies on spatial statistical analysis of classes of cell centers in a digital image of tissue of the cancer patient. The cell centers are detected in the image of stained tissue of the cancer patient. For each cell center, an image patch that includes the cell center is extracted from the image. A feature vector is generated based on each image patch using a convolutional neural network. A class is assigned to each cell center based on the feature vector associated with each cell center. A score is computed for the image of tissue by performing spatial statistical analysis based on classes of the cell centers. The score indicates how the cancer patient will respond to the predetermined therapy. The predetermined therapy is recommended to the patient if the score is larger than a predetermined threshold.