公开(公告)号：US20240090759A1

公开(公告)日：2024-03-21

申请号：US18264385

申请日：2022-01-21

Applicant: SONY GROUP CORPORATION

Inventor： YOHEI KURODA ,  SHINJI KATSUKI ,  KEI TOMATSU ,  YUGO KATSUKI ,  DAISUKE NAGAO

IPC: A61B1/313 ,  A61B1/00 ,  H04N25/47

CPC classification number: A61B1/3132 ,  A61B1/00179 ,  H04N25/47

Abstract: There is provided a medical observation device that includes an imaging unit (200) that can image an environment inside an abdominal cavity of a living body, and the imaging unit includes a plurality of first pixels (302) that are aligned in a matrix, and an event detection unit (308) that detects that a luminance change amount of light incident on each of the plurality of first pixels exceeds a predetermined threshold.

公开(公告)号：US20230282345A1

公开(公告)日：2023-09-07

申请号：US18005661

申请日：2021-06-10

Applicant: SONY GROUP CORPORATION

Inventor： KENJI SUZUKI ,  YOHEI KURODA ,  DAISUKE NAGAO ,  KANA MATSUURA

IPC: G16H40/63

CPC classification number: G16H40/63

Abstract: Provided is a medical support system that supports medical practice by a doctor.
The medical support system includes: a control unit; a recognition unit that recognizes an operative field environment; and



a machine learning model that estimates an operation performed by the medical support system on the basis of a recognition result of the recognition unit. The control unit outputs determination basis information regarding the operation estimated by the machine learning model to an information presentation unit. The control unit further includes a calculation unit that calculates reliability regarding an estimation result of the machine learning model, and outputs the reliability to the information presentation unit.

公开(公告)号：US20220322919A1

公开(公告)日：2022-10-13

申请号：US17640702

申请日：2020-08-07

Applicant: SONY GROUP CORPORATION

Inventor： DAISUKE NAGAO

IPC: A61B1/00 ,  A61B34/32 ,  A61B1/313 ,  A61B17/08

Abstract: A medical support arm includes: a support arm that supports an endoscope; an arm control unit that is configured to cause the support arm to perform a plurality of different interference avoidance operations for avoiding an interference between the endoscope and a surgical tool while maintaining a state in which an objective lens of the endoscope is directed to an observation target; and a determination unit that determines a combination of operation amounts of the plurality of interference avoidance operations.

公开(公告)号：US20240285157A1

公开(公告)日：2024-08-29

申请号：US18573748

申请日：2022-02-14

Applicant: SONY GROUP CORPORATION

Inventor： DAISUKE NAGAO ,  KENJI TAKAHASHI ,  KEI TOMATSU ,  YOHEI KURODA ,  MASAYUKI UMEJIMA

IPC: A61B1/06 ,  A61B1/00

CPC classification number: A61B1/0646 ,  A61B1/00006 ,  A61B1/000095 ,  A61B1/00013 ,  A61B1/00045 ,  A61B1/00149

Abstract: Real-time performance in image recognition is improved, and a deterioration in robustness is inhibited. A medical observation system according to an embodiment includes: a first imaging unit (11) that includes a plurality of pixels (110) each of which detects a change in luminance of incident light as an event and that acquires an image of an environment in an abdominal cavity of a living body; a polarizing filter (15) disposed on an optical path of the incident light incident on the first imaging unit; and an adjustment unit (20) that adjusts luminance of the incident light incident on the first imaging unit by adjusting luminance of light transmitted through the polarizing filter based on the image acquired by the first imaging unit.

公开(公告)号：US20230355332A1

公开(公告)日：2023-11-09

申请号：US18043623

申请日：2021-08-16

Applicant: SONY GROUP CORPORATION

Inventor： DAISUKE NAGAO

IPC: A61B34/32 ,  A61B34/00 ,  B25J9/16

CPC classification number: A61B34/32 ,  A61B34/70 ,  B25J9/161 ,  B25J9/163 ,  A61B2034/301

Abstract: Provided is a medical arm control system including a first determination unit (222) that performs supervised learning using first input data and first training data and generates an autonomous movement control model for autonomously moving a medical arm, a second determination unit (224) that performs supervised learning using second input data and second training data and generates a reward model for calculating a reward to be given to a movement of the medical arm, and a reinforcement learning unit (230) that executes the reward model using third input data and reinforces the autonomous movement control model using the reward calculated by the reward model.