公开(公告)号：US11596482B2

公开(公告)日：2023-03-07

申请号：US16881906

申请日：2020-05-22

Applicant: SURGICAL SAFETY TECHNOLOGIES INC.

Inventor： Shuja Khalid ,  Mitchell Geoffrey Goldenberg ,  Teodor Pantchev Grantcharov ,  Babak Taati ,  Frank Rudzicz

IPC: G05B13/02 ,  A61B34/20 ,  G06N20/00 ,  G06N3/063 ,  A61B34/00 ,  H04N19/54 ,  G06K9/62 ,  G06V20/40

Abstract: Computer implemented methods and systems are provided for training a machine learning architecture for surgical performance tracking and measurement based on surgical procedure video data set. The methods and systems include, in a first aspect, a sequential relation architecture and a dimensionality reduction architecture. In a second aspect, the methods and systems include a surgical instrument instance segmentation architecture, a decomposition model, and a sequential relation architecture. The video data is processed on a frame level to generate compressed or reduced representations of the video data.