公开(公告)号：EP3629898A1

公开(公告)日：2020-04-08

申请号：EP18808993.2

申请日：2018-05-30

申请人： Arterys Inc. ,  Taerum, Torin, Arni ,  Jugdev, Tristan

发明人： TAERUM, Torin, Arni ,  JUGDEV, Tristan ,  LIEMAN-SIFRY, Jesse ,  LAU, Hok, Kan ,  SALL, Sean ,  LE, Matthieu ,  AXERIO-CILIES, John ,  GOLDEN, Daniel, Irving

IPC分类号： A61B5/00 ,  A61B6/03 ,  A61B5/055

公开(公告)号：EP3714467A2

公开(公告)日：2020-09-30

申请号：EP18881685.4

申请日：2018-11-15

申请人： Arterys Inc. ,  Golden, Daniel Irving ,  Beckers, Fabien Rafael David ,  Axerio-Cilies, John ,  Le, Matthieu ,  Lieman-Sifry, Jesse ,  Krishnan, Anitha Priya ,  Sall, Sean Patrick ,  Lau, Hok Kan ,  Didonato, Matthew Joseph ,  Newton, Robert George ,  Taerum, Torin, Arni ,  Law, Shek Bun ,  Leibowitz, Carla Rosa ,  Calmon, Angélique Sophie

发明人： GOLDEN, Daniel Irving ,  BECKERS, Fabien Rafael David ,  AXERIO-CILIES, John ,  LE, Matthieu ,  LIEMAN-SIFRY, Jesse ,  KRISHNAN, Anitha Priya ,  SALL, Sean Patrick ,  LAU, Hok Kan ,  DIDONATO, Matthew Joseph ,  NEWTON, Robert George ,  TAERUM, Torin Arni ,  LAW, Shek Bun ,  LEIBOWITZ, Carla Rosa ,  CALMON, Angélique Sophie

IPC分类号： G16H50/20 ,  G16H50/50 ,  G06N3/02

公开(公告)号：EP3380859A1

公开(公告)日：2018-10-03

申请号：EP16869356.2

申请日：2016-11-29

申请人： Arterys Inc.

发明人： GOLDEN, Daniel, Irving ,  AXERIO-CILIES, John ,  LE, Matthieu ,  TAERUM, Torin, Arni ,  LIEMAN-SIFRY, Jesse

IPC分类号： G01R33/56 ,  G06N3/02 ,  G06T7/00

CPC分类号： G01R33/5608 ,  G01R33/561 ,  G01R33/5613 ,  G01R33/56308 ,  G01R33/56316 ,  G06N3/02 ,  G06T7/0012 ,  G06T7/11 ,  G06T2207/10088 ,  G06T2207/10132 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30048

摘要： Systems and methods for automated segmentation of anatomical structures, such as the human heart. The systems and methods employ convolutional neural networks (CNNs) to autonomously segment various parts of an anatomical structure represented by image data, such as 3D MRI data. The convolutional neural network utilizes two paths, a contracting path which includes convolution/pooling layers, and an expanding path which includes upsampling/convolution layers. The loss function used to validate the CNN model may specifically account for missing data, which allows for use of a larger training set. The CNN model may utilize multi-dimensional kernels (e.g., 2D, 3D, 4D, 6D), and may include various channels which encode spatial data, time data, flow data, etc. The systems and methods of the present disclosure also utilize CNNs to provide automated detection and display of landmarks in images of anatomical structures.