公开(公告)号：US20240127446A1

公开(公告)日：2024-04-18

申请号：US18277900

申请日：2022-02-25

申请人： Carl Zeiss Meditec, Inc. ,  Carl Zeiss Meditec AG

发明人： Homayoun Bagherinia ,  Aditya Nair ,  Niranchana Manivannan ,  Mary Durbin ,  Lars Omlor ,  Gary Lee

IPC分类号： G06T7/00 ,  G06T7/246 ,  G06V10/74 ,  G06V10/774 ,  G06V10/776 ,  G06V10/82 ,  G06V10/94 ,  G06V20/50 ,  G06V40/18

CPC分类号： G06T7/0014 ,  G06T7/248 ,  G06V10/761 ,  G06V10/774 ,  G06V10/776 ,  G06V10/82 ,  G06V10/95 ,  G06V20/50 ,  G06V40/197 ,  G06T2207/10016 ,  G06T2207/10101 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30041

摘要： System/Method/Device for labelling images in an automated manner to satisfy a performance of a different algorithm and then applying active learning to learn a deep learning model which would enable ‘real-time’ operation of quality assessment and with high accuracy.

公开(公告)号：US20230196572A1

公开(公告)日：2023-06-22

申请号：US18086016

申请日：2022-12-21

申请人： Carl Zeiss Meditec, Inc.

发明人： Aditya Nair ,  Rogerio Guimaraes ,  Homayoun Bagherinia ,  Ali Salehi

IPC分类号： G06T7/00

CPC分类号： G06T7/0012 ,  G06T2207/20084 ,  G06T2207/20081

摘要： A System/Method/Device for automatic retinal layer segmentation from optical coherence tomography (OCT) implementing a deep learning machine model defined by any of multiple neural networks. The neural networks may use the feature of “attention”, and more specifically self-attention, such as by using transformers, to reduce the size of the OCT data and make the process more efficient. Additionally, new methods of data augmentation suitable for OCT data are presented.