US 11,854,201 B2
Biological tissue image processing system, and machine learning method
Kohki Konishi, Yokohama (JP); Mitsuo Suga, Akishima (JP); and Hideo Nishioka, Akishima (JP)
Assigned to NIKON CORPORATION, Tokyo (JP)
Filed by NIKON CORPORATION, Tokyo (JP)
Filed on Nov. 23, 2020, as Appl. No. 17/101,267.
Application 17/101,267 is a continuation of application No. PCT/JP2019/019740, filed on May 17, 2019.
Claims priority of application No. 2018-099387 (JP), filed on May 24, 2018.
Prior Publication US 2021/0073992 A1, Mar. 11, 2021
Int. Cl. G06K 9/00 (2022.01); G06T 7/00 (2017.01); G01N 33/483 (2006.01); H01J 37/20 (2006.01); H01J 37/22 (2006.01); H01J 37/28 (2006.01); G06V 20/69 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 10/44 (2022.01); G01N 23/2251 (2018.01)
CPC G06T 7/0014 (2013.01) [G01N 33/4833 (2013.01); G06V 10/454 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 20/693 (2022.01); G06V 20/695 (2022.01); G06V 20/698 (2022.01); H01J 37/20 (2013.01); H01J 37/222 (2013.01); H01J 37/28 (2013.01); G01N 23/2251 (2013.01); G06T 2207/10056 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/30024 (2013.01); G06V 2201/03 (2022.01); H01J 2237/202 (2013.01); H01J 2237/221 (2013.01)] 7 Claims
OG exemplary drawing
 
1. A biological tissue image processing system, comprising:
a machine learning-based estimator configured to apply processing to an image obtained through observation of biological tissue using a microscope, the processing estimating a target component included in the biological tissue;
a determiner configured to determine a current observation area in the biological tissue in a machine learning process of the estimator; and
a controller configured to control operation of the microscope to cause the current observation area to be observed in the machine learning process of the estimator,
wherein the determiner comprises,
a similarity calculator configured to calculate, for each of candidate areas in the biological tissue, a plurality of similarities between the candidate area and a plurality of already observed areas in the biological tissue,
an evaluation value calculator configured to calculate, for each of the candidate areas in the biological tissue, an evaluation value based on the plurality of similarities, wherein the evaluation value represents the degree to which the candidate area is similar to an already observed area set which consists of the plurality of already observed areas, and
a selector configured to select, from the plurality of candidate areas in the biological tissue, a particular candidate area as the current observation area based on a plurality of evaluation values for the plurality of candidate areas in the biological tissue.