US 12,141,969 B2
Medical image processing device and medical image processing program
Yusuke Sakashita, Gamagori (JP)
Assigned to NIDEK CO., LTD., Gamagori (JP)
Appl. No. 17/621,301
Filed by NIDEK CO., LTD., Gamagori (JP)
PCT Filed Jul. 29, 2020, PCT No. PCT/JP2020/028976
§ 371(c)(1), (2) Date Dec. 21, 2021,
PCT Pub. No. WO2021/020419, PCT Pub. Date Feb. 4, 2021.
Claims priority of application No. 2019-138931 (JP), filed on Jul. 29, 2019.
Prior Publication US 2022/0358640 A1, Nov. 10, 2022
Int. Cl. G06T 7/00 (2017.01); A61B 3/00 (2006.01); G06T 11/00 (2006.01); G06V 10/764 (2022.01); G16H 30/40 (2018.01)
CPC G06T 7/0012 (2013.01) [A61B 3/0025 (2013.01); G06T 11/00 (2013.01); G06V 10/764 (2022.01); G16H 30/40 (2018.01); G06T 2207/30096 (2013.01); G06T 2210/41 (2013.01)] 9 Claims
OG exemplary drawing
 
1. A medical image processing device comprising:
a controller configured to execute:
an image acquisition step of acquiring a medical image of a tissue of a subject,
a pre-modification image display step of displaying, on a display, pre-modification image in which at least one of a position and a range of a lesion to be modified on the medical image is displayed,
a lesion reception step of receiving an instruction to designate at least one of a position and a range of the lesion to be modified in a state in which the pre-modification image is displayed on the display,
a predicted disease image acquisition step of, in a case in which at least one of a position and a range of the lesion is designated, acquiring a predicted disease image in which the lesion is modified according to designated information on the basis of the medical image acquired in the image acquisition step,
a predicted disease image display step of displaying the acquired predicted disease image and the pre-modification image on the display simultaneously or in a switching manner, and
acquiring the predicted disease image by inputting the image of the tissue of the subject and information of the lesion to a mathematical model trained by a machine learning algorithm in the predicted disease image acquisition step, such that the predicted disease image is output from the mathematical model, wherein the predicted disease image output from the mathematical model represents a future predicted state of the tissue of the subject.