公开(公告)号：US10242292B2

公开(公告)日：2019-03-26

申请号：US15997408

申请日：2018-06-04

Applicant: Digital Surgery Limited

Inventor： Odysseas Zisimopoulos ,  Evangello Flouty ,  Imanol Luengo Muntion ,  Mark Stacey ,  Sam Muscroft ,  Petros Giataganas ,  Andre Chow ,  Jean Nehme ,  Danail Stoyanov

IPC: G06K9/00 ,  G06K9/62 ,  G06N99/00 ,  A61B34/10

Abstract: A set of virtual images can be generated based on one or more real images and target rendering specifications, such that the set of virtual images correspond to (for example) different rendering specifications (or combinations thereof) than do the real images. A machine-learning model can be trained using the set of virtual images. Another real image can then be processed using the trained machine-learning model. The processing can include segmenting the other real image to detect whether and/or which objects are represented (and/or a state of the object). The object data can then be used to identify (for example) a state of a procedure.

公开(公告)号：US10758309B1

公开(公告)日：2020-09-01

申请号：US16511978

申请日：2019-07-15

Applicant: Digital Surgery Limited

Inventor： Andre Chow ,  Danail Stoyanov ,  Imanol Luengo Muntion ,  Petros Giataganas ,  Jean Nehme

IPC: G05B13/02 ,  A61B34/10 ,  G06K9/62 ,  G06N20/00 ,  G05B19/4155 ,  A61F5/00 ,  A61B17/32 ,  A61B17/068 ,  G06K9/00 ,  A61B17/00

Abstract: The present disclosure relates to systems and methods that use computer-vision processing systems to improve patient safety during surgical procedures. Computer-vision processing systems may train machine-learning models using machine-learning techniques. The machine-learning techniques can be executed to train the machine-learning models to recognize, classify, and interpret objects within a live video feed. Certain embodiments of the present disclosure can control (or facilitate control of) surgical tools during surgical procedures using the trained machine-learning models.

公开(公告)号：US20190279524A1

公开(公告)日：2019-09-12

申请号：US16294576

申请日：2019-03-06

Applicant: Digital Surgery Limited

Inventor： Danail Stoyanov ,  Petros Giataganas ,  Piyamate Wisanuvej ,  Paul Riordan ,  Imanol Luengo Muntion ,  Jean Nehme

IPC: G09B9/00 ,  G09B23/28 ,  G06F3/01

Abstract: A computer implemented method is provided for a virtual training system. A virtual surgical simulation associated with a type of surgical procedure is accessed. Image data associated with a controller and a workspace is received. Controller data corresponding to a controller interaction is received. A first interaction of the controller within the workspace based on at least one of the image data and the controller data is determined. Using the set of one or more transformation rules, the first interaction of the controller is transformed to a manipulation of the virtualized surgical tool in the virtual surgical simulation. A representation is output of the manipulation of the virtualized surgical tool.

公开(公告)号：US20220409285A1

公开(公告)日：2022-12-29

申请号：US17899687

申请日：2022-08-31

Applicant: DIGITAL SURGERY LIMITED

Inventor： Andre Chow ,  Danail Stoyanov ,  Imanol Luengo Muntion ,  Petros Giataganas ,  Jean Nehme

IPC: A61B34/10 ,  G06K9/62 ,  G06N20/00 ,  G05B19/4155 ,  A61F5/00 ,  A61B17/32 ,  A61B17/068 ,  G06V20/40

Abstract: The present disclosure relates to systems and methods that use computer-vision processing systems to improve patient safety during surgical procedures. Computer-vision processing systems may train machine-learning models using machine-learning techniques. The machine-learning techniques can be executed to train the machine-learning models to recognize, classify, and interpret objects within a live video feed. Certain embodiments of the present disclosure can control (or facilitate control of) surgical tools during surgical procedures using the trained machine-learning models.

公开(公告)号：US20220020486A1

公开(公告)日：2022-01-20

申请号：US17491658

申请日：2021-10-01

Applicant: DIGITAL SURGERY LIMITED

Inventor： Petros Giataganas ,  Imanol Luengo Muntion ,  Andre Chow ,  Jean Nehme ,  Danail Stoyanov

IPC: G16H40/63 ,  G16H50/70 ,  G06F16/22 ,  G06K9/00 ,  G06N5/02 ,  G06F3/01 ,  G09B9/00 ,  G09B23/28 ,  G16H10/60 ,  G16H30/40

Abstract: The present disclosure relates to processing data streams from a surgical procedure using multiple interconnected data structures to generate and/or continuously update an electronic output. Each surgical data structure is used to determine a current node associated with a characteristic of a surgical procedure and present relevant metadata associated with the surgical procedure. Each surgical data structure includes at least one node interconnected to one or more nodes of another data structure. The interconnected nodes between one or more data structures includes relational metadata associated with the surgical procedure.

公开(公告)号：US20180357514A1

公开(公告)日：2018-12-13

申请号：US15997408

申请日：2018-06-04

Applicant: Digital Surgery Limited

Inventor： Odysseas Zisimopoulos ,  Evangello Flouty ,  Imanol Luengo Muntion ,  Mark Stacey ,  Sam Muscroft ,  Petros Giataganas ,  Andre Chow ,  Jean Nehme ,  Danail Stoyanov

IPC: G06K9/62 ,  G06N99/00 ,  A61B34/10

CPC classification number: G06K9/6256 ,  A61B34/10 ,  A61B2034/101 ,  A61B2034/104 ,  A61B2034/105 ,  G06K9/6262 ,  G06K2209/057 ,  G06N99/005

Abstract: A set of virtual images can be generated based on one or more real images and target rendering specifications, such that the set of virtual images correspond to (for example) different rendering specifications (or combinations thereof) than do the real images. A machine-learning model can be trained using the set of virtual images. Another real image can then be processed using the trained machine-learning model. The processing can include segmenting the other real image to detect whether and/or which objects are represented (and/or a state of the object). The object data can then be used to identify (for example) a state of a procedure.

公开(公告)号：US20240122734A1

公开(公告)日：2024-04-18

申请号：US18394027

申请日：2023-12-22

Applicant: DIGITAL SURGERY LIMITED

Inventor： Andre Chow ,  Danail V. Stoyanov ,  Imanol Luengo Muntion ,  Petros Giataganas ,  Jean Nehme

IPC: A61F5/00 ,  A61B1/00 ,  A61B17/068 ,  A61B17/32 ,  A61B34/10 ,  G05B19/4155 ,  G06F18/21 ,  G06N20/00 ,  G06V10/70 ,  G06V20/40

CPC classification number: A61F5/0076 ,  A61B1/000096 ,  A61B17/068 ,  A61B17/320016 ,  A61B17/320092 ,  A61B34/10 ,  G05B19/4155 ,  G06F18/217 ,  G06N20/00 ,  G06V10/70 ,  G06V20/41 ,  A61B2017/00212

Abstract: The present disclosure relates to systems and methods that use computer-vision processing systems to improve patient safety during surgical procedures. Computer-vision processing systems may train machine-learning models using machine-learning techniques. The machine-learning techniques can be executed to train the machine-learning models to recognize, classify, and interpret objects within a live video feed. Certain embodiments of the present disclosure can control (or facilitate control of) surgical tools during surgical procedures using the trained machine-learning models.

公开(公告)号：US20210015554A1

公开(公告)日：2021-01-21

申请号：US16933454

申请日：2020-07-20

Applicant: DIGITAL SURGERY LIMITED

Inventor： Andre Chow ,  Danail Stoyanov ,  Imanol Luengo Muntion ,  Petros Giataganas ,  Jean Nehme

IPC: A61B34/10 ,  G06K9/62 ,  G06N20/00 ,  G05B19/4155 ,  A61F5/00 ,  A61B17/32 ,  A61B17/068 ,  G06K9/00

Abstract: The present disclosure relates to systems and methods that use computer-vision processing systems to improve patient safety during surgical procedures. Computer-vision processing systems may train machine-learning models using machine-learning techniques. The machine-learning techniques can be executed to train the machine-learning models to recognize, classify, and interpret objects within a live video feed. Certain embodiments of the present disclosure can control (or facilitate control of) surgical tools during surgical procedures using the trained machine-learning models.

公开(公告)号：US20190164012A1

公开(公告)日：2019-05-30

申请号：US16265417

申请日：2019-02-01

Applicant: Digital Surgery Limited

Inventor： Odysseas Zisimopoulos ,  Evangello Flouty ,  Imanol Luengo Muntion ,  Mark Stacey ,  Sam Muscroft ,  Petros Giataganas ,  Andre Chow ,  Jean Nehme ,  Danail Stoyanov

IPC: G06K9/62 ,  A61B34/10 ,  G06N20/00

Abstract: A set of virtual images can be generated based on one or more real images and target rendering specifications, such that the set of virtual images correspond to (for example) different rendering specifications (or combinations thereof) than do the real images. An image style can be transferred to the at least some of the virtual images of the set of virtual images to generate a stylized virtual image. A machine-learning model can be trained using a plurality of stylized virtual images. Another real image can then be processed using the trained machine-learning model. The processing can include segmenting the other real image to detect whether and/or which objects are represented (and/or a state of the object). The object data can then be used to identify (for example) a state of a procedure.

公开(公告)号：US11883312B2

公开(公告)日：2024-01-30

申请号：US17899687

申请日：2022-08-31

Applicant: DIGITAL SURGERY LIMITED

Inventor： Andre Chow ,  Danail Stoyanov ,  Imanol Luengo Muntion ,  Petros Giataganas ,  Jean Nehme

IPC: A61F5/00 ,  A61B34/10 ,  G06N20/00 ,  G05B19/4155 ,  A61B17/32 ,  A61B17/068 ,  G06V20/40 ,  A61B1/00 ,  G06F18/21 ,  G06V10/70 ,  A61B17/00

CPC classification number: A61F5/0076 ,  A61B1/000096 ,  A61B17/068 ,  A61B17/320016 ,  A61B17/320092 ,  A61B34/10 ,  G05B19/4155 ,  G06F18/217 ,  G06N20/00 ,  G06V10/70 ,  G06V20/41 ,  A61B2017/00061 ,  A61B2017/00119 ,  A61B2017/00199 ,  A61B2017/00212 ,  A61B2017/320082 ,  A61B2017/320095 ,  A61B2034/107 ,  G05B2219/36414 ,  G06V2201/034

Abstract: The present disclosure relates to systems and methods that use computer-vision processing systems to improve patient safety during surgical procedures. Computer-vision processing systems may train machine-learning models using machine-learning techniques. The machine-learning techniques can be executed to train the machine-learning models to recognize, classify, and interpret objects within a live video feed. Certain embodiments of the present disclosure can control (or facilitate control of) surgical tools during surgical procedures using the trained machine-learning models.