IP Library › Granted Patent US 12,646,216
Granted Patent B2
US 12,646,216 · App. 18/561,150 · Granted Jun 2, 2026

Information processing device, biological sample observation system, and image generation method

Inventors: Noe Kaneko (Kanagawa, JP); Hirokazu Tatsuta (Kanagawa, JP); Kazuhiro Nakagawa (Saitama, JP); Sakiko Yasukawa (Tokyo, JP); Noriyuki Kishii (Kanagawa, JP)
Assignee: Sony Group Corporation
G06T7/90G01N21/6428G01N21/6456G01N2021/6439G06T2207/10024G06T2207/10064G06T2207/20072G06T2207/30024
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,646,216
App. No.
18/561,150
Granted
Jun 2, 2026
Kind
B2
Abstract

An information processing device according to an aspect of the present disclosure includes a simulated image generation unit ( 131 a ) that generates a simulated image by superimposing a non-stained image including an autofluorescence component and a dye tile image in which a reference spectrum of a first fluorescent dye and imaging noise of each of pixels of the non-stained image are associated, a fluorescence separation unit ( 131 b ) that separates a component of the first fluorescent dye and the autofluorescence component on the basis of the simulated image and generates a separated image, and an evaluation unit ( 131 c ) that evaluates a degree of separation of the separated image.

Claims (52)

1 . An information processing device, comprising:

a simulated image generation unit that generates a simulated image by superimposing a non-stained image including an autofluorescence component and a dye tile image in which a reference spectrum of a first fluorescent dye and imaging noise of each of pixels of the non-stained image are associated;

a fluorescence separation unit that separates a component of the first fluorescent dye and the autofluorescence component on the basis of the simulated image and generates a separated image; and

an evaluation unit that evaluates a degree of separation of the separated image.

2 . The information processing device according to claim 1 , wherein

the dye tile image includes a reference spectrum of a second fluorescent dye in addition to the first fluorescent dye, and is an image in which the reference spectrum of each of the first fluorescent dye and the second fluorescent dye and the imaging noise of each of the pixels of the non-stained image are associated.

3 . The information processing device according to claim 1 , wherein

the imaging noise is noise that changes according to an imaging condition of the non-stained image.

4 . The information processing device according to claim 3 , wherein

the imaging condition of the non-stained image includes at least one or all of laser power, gain, and exposure time.

5 . The information processing device according to claim 1 , wherein

the dye tile image is a dye tile group having a plurality of dye tiles.

6 . The information processing device according to claim 5 , wherein

a size of each of the plurality of dye tiles is same as a size of a cell.

7 . The information processing device according to claim 5 , wherein

the plurality of dye tiles is arranged in a predetermined color arrangement pattern.

8 . The information processing device according to claim 5 , wherein

a degree of the imaging noise is quantified or visualized for each of the dye tiles.

9 . The information processing device according to claim 5 , wherein

the simulated image generation unit repeatedly arranges the dye tiles corresponding to a number of dyes designated by a user, and generates the dye tile image.

10 . The information processing device according to claim 5 , wherein

the simulated image generation unit mixes a plurality of dyes and creates the dye tile.

11 . The information processing device according to claim 1 , wherein

the simulated image generation unit determines spectral intensity of a dye to be imparted to autofluorescence intensity of the non-stained image.

12 . The information processing device according to claim 1 , wherein

the simulated image generation unit superimposes the imaging noise on a reference spectrum of the first fluorescent dye.

13 . The information processing device according to claim 12 , wherein

the imaging noise is shot noise.

14 . The information processing device according to claim 1 , wherein

the fluorescence separation unit separates the component of the first fluorescent dye and the autofluorescence component by color separation calculation including at least one of a least squares method, a weighted least squares method, or non-negative matrix factorization.

15 . The information processing device according to claim 1 , wherein

the evaluation unit

generates a histogram from the separated image,

calculates a signal separation value between a dye and a signal other than the dye from the histogram, and

evaluates the degree of separation on the basis of the signal separation value.

16 . The information processing device according to claim 1 , further comprising:

a recommendation unit that recommends an optimal reagent corresponding to a dye designated by a user on the basis of the degree of separation.

17 . The information processing device according to claim 16 , wherein

the recommendation unit generates an image indicating a combination of dyes or a combination of a dye and the reagent.

18 . The information processing device according to claim 16 , wherein

the recommendation unit generates an image indicating a combination of an antibody and a dye.

19 . A biological sample observation system, comprising:

an imaging device that acquires a non-stained image including an autofluorescence component; and

an information processing device that processes the non-stained image, wherein

the information processing device includes

a simulated image generation unit that generates a simulated image by superimposing the non-stained image and a dye tile image in which a reference spectrum of a first fluorescent dye and imaging noise of each of pixels of the non-stained image are associated,

a fluorescence separation unit that separates a component of the first fluorescent dye and the autofluorescence component on the basis of the simulated image and generates a separated image, and

an evaluation unit that evaluates a degree of separation of the separated image.

20 . An image generation method, comprising

generating a simulated image by superimposing a non-stained image including an autofluorescence component and a dye tile image in which a reference spectrum of a first fluorescent dye and imaging noise of each of pixels of the non-stained image are associated;

separating a component of the first fluorescent dye and the autofluorescence component on the basis of the simulated image and generates a separated image; and

evaluating a degree of separation of the separated image.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 14, 2024
From: KANEKO, NOE; TATSUTA, HIROKAZU; NAKAGAWA, KAZUHIRO; YASUKAWA, SAKIKO; KISHII, NORIYUKI
To: SONY GROUP CORPORATION
Reel/Frame 066583/0364 →
Priority Claims (1)
JP 2021-088623 · May 26, 2021 · national
Continuity (1)
Related Publication 20240371042A1 · Nov 7, 2024
References Cited (33)
US 7932502B2 · Kubo · 2011 [cited by examiner]
US 8107158B2 · Yamazaki · 2012 [cited by examiner]
US 8169471B2 · Yamaguchi · 2012 [cited by examiner]
US 8214025B2 · Takaoka · 2012 [cited by examiner]
US 9128055B2 · Sekino · 2015 [cited by examiner]
US 9516235B2 · Shida · 2016 [cited by examiner]
US 9686484B2 · Lee · 2017 [cited by examiner]
US 9949645B2 · Shida · 2018 [cited by examiner]
US 10684458B2 · Chung · 2020 [cited by examiner]
US 10729310B2 · Takahashi · 2020 [cited by examiner]
US 10750929B2 · Mitamura · 2020 [cited by examiner]
US 11439468B2 · Ikehara · 2022 [cited by examiner]
US 20040044275A1 · Hakamata · 2004 [cited by applicant]
US 20050163359A1 · Murao et al. · 2005 [cited by applicant]
US 20060247535A1 · Sendai · 2006 [cited by examiner]
US 20070273877A1 · Kawano · 2007 [cited by examiner]
US 20090245611A1 · Can · 2009 [cited by examiner]
US 20120269723A1 · Brinkmann · 2012 [cited by examiner]
US 20130044126A1 · Yamada · 2013 [cited by examiner]
US 20150098126A1 · Keller et al. · 2015 [cited by applicant]
US 20150257635A1 · Kubo · 2015 [cited by examiner]
US 20170234795A1 · Issadore et al. · 2017 [cited by applicant]
US 20180252702A1 · Irudayaraj · 2018 [cited by examiner]
US 20200327657A1 · Klaiman · 2020 [cited by examiner]
US 20240053267A1 · Ikeda · 2024 [cited by examiner]
US 20240371042A1 · Kaneko · 2024 [cited by examiner]
JP 2004112772A · 2004 [cited by applicant]
JP 2018185524A · 2018 [cited by applicant]
JP 2020020791A · 2020 [cited by applicant]
JP 2020180976A · 2020 [cited by applicant]
WO WO2004042392A1 · 2004 [cited by applicant]
Maric et al, Whole-brain tissue mapping toolkit using largescale highly multiplexed immunofluorescence imaging and deep neural networks, Mar. 10, 2021, Nature Communications, https://doi.org/10.1038/s41467-021-21735-x, … [cited by examiner]
International Search Report and English translation thereof mailed Apr. 12, 2022 in connection with International Application No. PCT/JP2022/006169. [cited by applicant]