US 12,334,211 B2
Storage medium, diagnosis support apparatus and diagnosis support method
Tetsu Hayashida, Tokyo (JP); Noriyuki Futatsugi, Tokyo (JP); and Yasuhiko Shiota, Tokyo (JP)
Assigned to FIXSTARS CORPORATION, Tokyo (JP)
Appl. No. 17/796,694
Filed by FIXSTARS CORPORATION, Tokyo (JP)
PCT Filed Jan. 28, 2021, PCT No. PCT/JP2021/002960
§ 371(c)(1), (2) Date Aug. 1, 2022,
PCT Pub. No. WO2021/153648, PCT Pub. Date Aug. 5, 2021.
Claims priority of application No. 2020-014823 (JP), filed on Jan. 31, 2020.
Prior Publication US 2023/0057933 A1, Feb. 23, 2023
Int. Cl. G16H 30/40 (2018.01); G06T 7/00 (2017.01); G06V 40/10 (2022.01); G16H 50/20 (2018.01)
CPC G16H 30/40 (2018.01) [G06T 7/0012 (2013.01); G06V 40/10 (2022.01); G16H 50/20 (2018.01); G06T 2207/10016 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30068 (2013.01); G06T 2207/30096 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A storage medium storing a diagnosis support program for making one computer or a plurality of computers having at least one processor and at least one memory perform steps of:
retrieving examination information relating to an examination of the subject, said examination information comprising a type of examination to be performed selected from a predetermined plurality of examination types;
based on the examination information, automatically selecting a recognizer to be used for recognition processing of a breast image showing a projection image or a section image of a breast of a subject or a recognizer that is to output a recognition result of the recognition processing, from among a plurality of recognizers comprising at least a first recognizer and a second recognizer each including a neural network, wherein the first recognizer is associated with a first type of examination and the second recognizer is associated with a second type of examination, wherein the first recognizer is a recognizer trained on a first data set to have a lower false-positive rate than the second recognizer, and wherein the second recognizer is a recognizer trained on a second data set different from the first data set to have a lower false-negative rate than the first recognizer; and
with the first recognizer or the second recognizer, performing the recognition processing.