Display with folded optical path
    4.
    发明授权

    公开(公告)号:US12102488B2

    公开(公告)日:2024-10-01

    申请号:US16965755

    申请日:2019-01-30

    IPC分类号: A61B90/00 A61B34/35 G02B27/01

    摘要: The technology described in this document can be embodied in a viewing apparatus for a surgical device, the apparatus including a lens assembly including a first polarizer, a display device configured to present an image of a surgical scene, and a reflective surface oriented at an acute angle with respect to the display device such that light from the display device is reflected from the reflective surface towards the lens assembly. The first polarizer in the lens assembly is configured such that light reflected from the reflective surface passes through the first polarizer, and light reaching the first polarizer without being reflected from the reflective surface is substantially blocked.

    LAYERED FUNCTIONALITY FOR A USER INPUT MECHANISM IN A COMPUTER-ASSISTED SURGICAL SYSTEM

    公开(公告)号:US20240307142A1

    公开(公告)日:2024-09-19

    申请号:US18675783

    申请日:2024-05-28

    摘要: A computer-assisted surgical system is configured to activate a first mode of operation in which movement of a user control mechanism is translated to movement of a surgical instrument coupled to a manipulator arm; receive, during the first mode of operation, a first user input by way of a user input mechanism associated with the user control mechanism; activate, based on the first user input, a second mode of operation in which the user control mechanism is repositionable without causing the surgical instrument to move; receive, during the first mode of operation, a second user input by way of the user input mechanism, wherein the second user input is different from the first user input; and activate, based on the second user input, a function associated with a third mode of operation different from the first and second modes of operation.

    Actuation mechanisms for surgical instruments

    公开(公告)号:US12089844B2

    公开(公告)日:2024-09-17

    申请号:US17414741

    申请日:2019-12-06

    IPC分类号: A61B17/072 A61B34/37

    摘要: The present disclosure provides a surgical instrument, such as a tissue sealing instrument, with an elongate shaft and an end effector. The end effector includes a first jaw and a second jaw that includes a staple cartridge with a plurality of staples for engaging tissue. The instrument further includes a drive member for closing the jaws and engaging the staples, and an actuation mechanism, such as a coil, in contact with the drive member. The actuation mechanism is configured to translate the drive member distally through the first jaw (instead of through the staple cartridge as in conventional surgical stapling instruments). Eliminating the internal channel for the actuation coil from the staple cartridge provides more space in the cartridge for the staples, allowing for the use of taller staples and/or a more compact and maneuverable instrument.

    FEATURE EXTRACTION VIA FEDERATED SELF-SUPERVISED LEARNING

    公开(公告)号:US20240303506A1

    公开(公告)日:2024-09-12

    申请号:US18598123

    申请日:2024-03-07

    IPC分类号: G06N3/098 G06N3/0895

    CPC分类号: G06N3/098 G06N3/0895

    摘要: One embodiment of the present invention sets forth a technique for training a machine learning model to perform feature extraction. The technique includes executing a student version of the machine learning model to generate a first set of features from a first set of image crops and executing a teacher version of the machine learning model to generate a second set of features from a second set of image crops. The technique also includes training the student version of the machine learning model based on one or more losses computed between the first and second sets of features. The technique further includes transmitting the trained student version of the machine learning model to a server, wherein the trained student version can be aggregated by the server with additional trained student versions of the machine learning model to generate a global version of the machine learning model.