-
1.发明申请公开(公告)号：US20200066407A1
公开(公告)日：2020-02-27
申请号：US16488029
申请日：2017-02-23
Applicant: Google LLC
Inventor： Martin Christian Stumpe , Lily Peng , Yun Liu , Krishna K. Gadepalli , Timo Kohlberger
Abstract: A method, system and machine for assisting a pathologist in identifying the presence of tumor cells in lymph node tissue is disclosed. The digital image of lymph node tissue at a first magnification (e.g., 40×) is subdivided into a multitude of rectangular “patches.” A likelihood of malignancy score is then determined for each of the patches. The score is obtained by analyzing pixel data from the patch (e.g., pixel data centered on and including the patch) using a computer system programmed as an ensemble of deep neural network pattern recognizers, each operating on different magnification levels of the patch. A representation or “heatmap” of the slide is generated. Each of the patches is assigned a color or grayscale value in accordance with (1) the likelihood of malignancy score assigned to the patch by the combined outputs of the ensemble of deep neural network pattern recognizers and (2) a code which assigns distinct colors (or grayscale values) to different values of likelihood of malignancy scores assigned to the patches.
-
2.发明授权公开(公告)号：US11170897B2
公开(公告)日：2021-11-09
申请号：US16488029
申请日：2017-02-23
Applicant: Google LLC
Inventor： Martin Christian Stumpe , Lily Peng , Yun Liu , Krishna K. Gadepalli , Timo Kohlberger
Abstract: A method, system and machine for assisting a pathologist in identifying the presence of tumor cells in lymph node tissue is disclosed. The digital image of lymph node tissue at a first magnification (e.g., 40×) is subdivided into a multitude of rectangular “patches.” A likelihood of malignancy score is then determined for each of the patches. The score is obtained by analyzing pixel data from the patch (e.g., pixel data centered on and including the patch) using a computer system programmed as an ensemble of deep neural network pattern recognizers, each operating on different magnification levels of the patch. A representation or “heatmap” of the slide is generated. Each of the patches is assigned a color or grayscale value in accordance with (1) the likelihood of malignancy score assigned to the patch by the combined outputs of the ensemble of deep neural network pattern recognizers and (2) a code which assigns distinct colors (or grayscale values) to different values of likelihood of malignancy scores assigned to the patches.
-
Search Results
2
records
(took 0.01 seconds)
