公开(公告)号：US20240428412A1

公开(公告)日：2024-12-26

申请号：US18687570

申请日：2022-08-22

Applicant: Shimadzu Corporation

Inventor： Shin KAWAMATA ,  Takako YAMAMOTO ,  Takashi SUZUKI ,  Ryuji SAWADA ,  Shuhei YAMAMOTO

IPC: G06T7/00 ,  G06T7/62 ,  G06T11/00

Abstract: A cell image analysis system (200) according to this invention includes a cell image acquirer (11) configured to acquire a cell image (30) including cells (90); a cell area acquirer (12) configured to acquire cell areas (91) from the cell image; a pseudopodium area acquirer (13) configured to acquire areas (92) of pseudopodia (90b) that are elongated areas in the cell areas of the cell image; and an aging index information acquirer (14) configured to acquire aging index information (24) that indicates a degree of aging of the cells based lengths of pseudopodia.

公开(公告)号：US20240370998A1

公开(公告)日：2024-11-07

申请号：US18567494

申请日：2022-07-26

Applicant: SHIMADZU CORPORATION

Inventor： Ryuji SAWADA ,  Shuhei YAMAMOTO

IPC: G06T7/00 ,  G06T7/143

Abstract: A cell image analysis method according to this invention includes a step of acquiring a cell image (10) including a cell (90); a step of inputting the cell image to a learned model (6) that has learned classification of the cell into one of two or more types; a step of acquiring an index value (20) indicating accuracy of the classification of the cell that is included in the cell image into one of two or more types based on an analysis result of each of pixels of the cell image output from the learned model; and a step of displaying the acquired index value.

公开(公告)号：US20240273683A1

公开(公告)日：2024-08-15

申请号：US18568342

申请日：2022-07-28

Applicant: SHIMADZU CORPORATION

Inventor： Ryuji SAWADA ,  Shuhei YAMAMOTO

IPC: G06T5/60 ,  G06T5/20 ,  G06T7/00

CPC classification number: G06T5/60 ,  G06T5/20 ,  G06T7/0012 ,  G06T2207/20032 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30024 ,  G06T2207/30204

Abstract: A cell image analysis method according to this invention includes a step of acquiring a cell image (10) including a cell (90); a step of generating a background component image (14) that extracts a distribution of a brightness component of a background (91) by filtering the cell image; a step of generating a corrected cell image (11) that is corrected based on the cell image and the background component image to reduce unevenness of brightness; and a first estimation step of estimating whether the cell in the image is a normal cell or an abnormal cell by using the corrected cell image and a learned model (6) that has learned to analyze the cell.

公开(公告)号：US20240265686A1

公开(公告)日：2024-08-08

申请号：US18565884

申请日：2022-09-08

Applicant: SHIMADZU CORPORATION

Inventor： Hiroaki TSUSHIMA ,  Shuhei YAMAMOTO ,  Takeshi ONO ,  Ryuji SAWADA

IPC: G06V10/776 ,  G06V10/94 ,  G06V20/69

CPC classification number: G06V10/776 ,  G06V10/945 ,  G06V20/69

Abstract: A memory capacity determination system (200) in learning of cell images (80) includes a learning processor (10) including a first processor (10a) configured to execute processes of training a learning model (21), and a memory (10b); a selector (45) configured to select between a training mode of training the learning model, and a validation mode of validating whether a capacity of the memory becomes insufficient; and a determiner (12d) configured to determine whether the capacity of the memory becomes insufficient in the verification mode; and a display (121) configured to give a notice based on a first determination result (32).

公开(公告)号：US20230334832A1

公开(公告)日：2023-10-19

申请号：US18027799

申请日：2021-04-27

Applicant: SHIMADZU CORPORATION

Inventor： Ryuji SAWADA ,  Shuhei YAMAMOTO ,  Takeshi ONO

IPC: G06V10/774 ,  G06T7/00 ,  G06V20/69 ,  G06V10/70 ,  G06V10/776

CPC classification number: G06V10/774 ,  G06T7/0012 ,  G06V20/69 ,  G06V10/87 ,  G06V10/776 ,  G06T2207/20081 ,  G06T2207/30024 ,  G06T2207/30072 ,  G06T2207/10056 ,  G06T2207/10064

Abstract: An image analyzing device (1) includes an image holder (8) that holds an image, a trained model registration part (10) configured to register trained models created by machine learning, a trained model holder (12) that holds the trained models registered by the trained model registration part (10), an algorithm holder (14) that holds a plurality of analysis algorithms for executing analysis processing of an image, a recipe creation part (18) configured, for an image to be analyzed optionally selected from among images held in the image holder (8), to create an analysis recipe for analyzing the image to be analyzed by combining a trained model selected from the trained models held in the trained model holder (10) and an analysis algorithm optionally selected from the plurality of analysis algorithms held in the algorithm holder (14), and an analysis execution part (20) configured to execute analysis of the image to be analyzed based on the analysis recipe created by the recipe creation part (18).

公开(公告)号：US20230145376A1

公开(公告)日：2023-05-11

申请号：US17981948

申请日：2022-11-07

Applicant: SHIMADZU CORPORATION

Inventor： Ryuji SAWADA ,  Shuhei YAMAMOTO ,  Takeshi ONO

IPC: G06T7/00

CPC classification number: G06T7/0002 ,  G06T2207/30024

Abstract: A data processing system includes a cell image processing device including an image analysis unit that analyzes the acquired cell image, a storage unit that stores relative data in which the cell image, an analysis result of the cell image, and at least one or more pieces of group division information used to perform group division on the cell image are associated with each other, and a data tree creating unit that creates a virtual data tree including result information based on the analysis result to be displayed in any hierarchy of the data tree on which group division is performed so that a plurality of the relative data belong to the same group, and an information display device including a display unit configured to display the data tree.

公开(公告)号：US20230111880A1

公开(公告)日：2023-04-13

申请号：US17959800

申请日：2022-10-04

Applicant: SHIMADZU CORPORATION

Inventor： Hiroaki TSUSHIMA ,  Ryuji SAWADA ,  Takeshi ONO ,  Shuhei YAMAMOTO

IPC: G06V10/72 ,  G06T7/00

Abstract: A migration system of a learning model for cell image analysis is a system that migrates a learning model from a first learning device to a second learning device, in which the second learning device includes an algorithm consistency determination unit that determines, based on second algorithm specification information and first algorithm specification information, whether or not consistency is established between a first algorithm and a second algorithm, and a learning model parameter setting unit that sets a first parameter to be used together with the second algorithm.

公开(公告)号：US20200057294A1

公开(公告)日：2020-02-20

申请号：US16490123

申请日：2017-03-02

Applicant: SHIMADZU CORPORATION ,  iPS PORTAL, Inc.

Inventor： Yasushi KONDO ,  Shuhei YAMAMOTO ,  Mika OKADA ,  Minoru OKADA

IPC: G02B21/36 ,  G03H1/08 ,  G03H1/04 ,  C12M1/34

Abstract: A cell area extraction unit (241) extracts a cell area in a phase image that is created based on a hologram obtained by in-line holographic microscope (IHM). A background value acquisition unit (242) obtains a background value from phase values at a plurality of positions outside the cell area. An intracellular phase value acquisition unit (243) averages a plurality of phase values on a sampling line set at a position close to the periphery of a cell, while avoiding a central portion in which the phase value may be lowered in the cell area, to obtain an intracellular phase value. A phase change amount calculation unit (244) obtains the difference between the intracellular phase value and the background value. A phase change amount determination unit (245) compares the value of the difference with thresholds in two levels to determine whether the cell is in an undifferentiated state or an undifferentiation deviant state. It is thereby possible to automatically make a correct determination while removing the influence of a theoretical measurement error by IHM.