公开(公告)号：US11783603B2

公开(公告)日：2023-10-10

申请号：US16958555

申请日：2018-03-07

Applicant: VERILY LIFE SCIENCES LLC.

Inventor： Martin Stumpe ,  Philip Nelson ,  Lily Peng

IPC: G06K9/62 ,  G06V20/69 ,  G16H30/40 ,  G01N1/30 ,  G06N3/08 ,  G06T7/00 ,  G06T11/00 ,  G06F18/214 ,  G06V10/82

CPC classification number: G06V20/69 ,  G01N1/30 ,  G06F18/214 ,  G06N3/08 ,  G06T7/0012 ,  G06T11/001 ,  G06V10/82 ,  G06V20/695 ,  G16H30/40 ,  G01N2001/302 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30024 ,  G06T2210/41 ,  G06V2201/03

Abstract: A machine learning predictor model is trained to generate a prediction of the appearance of a tissue sample stained with a special stain such as an IHC stain from an input image that is either unstained or stained with H&E. Training data takes the form of thousands of pairs of precisely aligned images, one of which is an image of a tissue specimen stained with H&E or unstained, and the other of which is an image of the tissue specimen stained with the special stain. The model can be trained to predict special stain images for a multitude of different tissue types and special stain types, in use, an input image, e.g., an H&E image of a given tissue specimen at a particular magnification level is provided to the model and the model generates a prediction of the appearance of the tissue specimen as if it were stained with the special stain. The predicted image is provided to a user and displayed, e.g., on a pathology workstation.

公开(公告)号：US20230419694A1

公开(公告)日：2023-12-28

申请号：US18462930

申请日：2023-09-07

Applicant: Verily Life Sciences LLC

Inventor： Martin Stumpe ,  Philip Nelson ,  Lily Peng

IPC: G06V20/69 ,  G16H30/40 ,  G01N1/30 ,  G06N3/08 ,  G06T7/00 ,  G06T11/00 ,  G06F18/214 ,  G06V10/82

CPC classification number: G06V20/69 ,  G16H30/40 ,  G01N1/30 ,  G06N3/08 ,  G06T7/0012 ,  G06T11/001 ,  G06F18/214 ,  G06V10/82 ,  G06V20/695 ,  G01N2001/302 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30024 ,  G06T2210/41 ,  G06V2201/03

Abstract: A machine learning predictor model is trained to generate a prediction of the appearance of a tissue sample stained with a special stain such as an IHC stain from an input image that is either unstained or stained with H&E. Training data takes the form of thousands of pairs of precisely aligned images, one of which is an image of a tissue specimen stained with H&E or unstained, and the other of which is an image of the tissue specimen stained with the special stain. The model can be trained to predict special stain images for a multitude of different tissue types and special stain types, in use, an input image, e.g., an H&E image of a given tissue specimen at a particular magnification level is provided to the model and the model generates a prediction of the appearance of the tissue specimen as if it were stained with the special stain. The predicted image is provided to a user and displayed, e.g., on a pathology workstation.