公开(公告)号：US20200074622A1

公开(公告)日：2020-03-05

申请号：US16552467

申请日：2019-08-27

Applicant: Topcon Corporation

Inventor： Qi Yang ,  Bisrat Zerihun ,  Charles A. Reisman

IPC: G06T7/00 ,  G06N3/08 ,  A61B3/10 ,  G06N20/20

Abstract: Machine learning technologies are used to identify and separating abnormal and normal subjects and identifying possible disease types with images (e.g., optical coherence tomography (OCT) images of the eye), where the machine learning technologies are trained with only normative data. In one example, a feature or a physiological structure of an image is extracted, and the image is classified based on the extracted feature. In another example, a region of the image is masked and then reconstructed, and a similarity is determined between the reconstructed region and the original region of the image. A label (indicating an abnormality) and a score (indicating a severity) can be determined based on the classification and/or the similarity.

公开(公告)号：US11704791B2

公开(公告)日：2023-07-18

申请号：US16552467

申请日：2019-08-27

Applicant: Topcon Corporation

Inventor： Qi Yang ,  Bisrat Zerihun ,  Charles A. Reisman

IPC: G06K9/00 ,  A61B3/02 ,  G06T7/00 ,  G06N3/08 ,  A61B3/10 ,  G06N20/20 ,  A61B5/00 ,  A61B3/12 ,  G06N3/045

CPC classification number: G06T7/0012 ,  A61B3/102 ,  G06N3/08 ,  G06N20/20 ,  A61B3/12 ,  A61B5/7275 ,  G06N3/045 ,  G06T2207/30041

Abstract: Machine learning technologies are used to identify and separating abnormal and normal subjects and identifying possible disease types with images (e.g., optical coherence tomography (OCT) images of the eye), where the machine learning technologies are trained with only normative data. In one example, a feature or a physiological structure of an image is extracted, and the image is classified based on the extracted feature. In another example, a region of the image is masked and then reconstructed, and a similarity is determined between the reconstructed region and the original region of the image. A label (indicating an abnormality) and a score (indicating a severity) can be determined based on the classification and/or the similarity.