公开(公告)号：US20220415013A1

公开(公告)日：2022-12-29

申请号：US17895315

申请日：2022-08-25

Applicant: LUNIT INC.

Inventor： Dong Geun YOO ,  Min Chul KIM ,  Hyo Eun KIM ,  Hyun Jae LEE ,  Jae Hwan LEE ,  Hae Joon KIM

IPC: G06V10/46 ,  G06V10/25 ,  G06V10/44 ,  G06V10/74 ,  G06T7/70 ,  G06T11/20

Abstract: A method for operating a medical imaging device includes obtaining lesion information on at least one lesion detected from a medical image, determining a shape and a position of at least one contour corresponding to the at least one lesion based on the obtained lesion information, determining a position of at least one text region that includes a text indicating the lesion information on the at least one lesion in the medical image, and displaying the at least one contour and the text included in the at least one text region on the medical image, based on the determined shape and position of the at least one contour and the determined position of the at least one text region.

公开(公告)号：US20200342276A1

公开(公告)日：2020-10-29

申请号：US16535314

申请日：2019-08-08

Applicant: Lunit Inc.

Inventor： Jae Hwan LEE

IPC: G06K9/62 ,  G06N3/08 ,  G06K9/66

Abstract: A normalization method for machine learning and an apparatus thereof are provided. The normalization method according to some embodiments of the present disclosure may calculate a value of a normalization parameter for an input image through a normalization model before inputting the input image to a target model and normalize the input image using the calculated value of the normalization parameter. Because the normalization model is updated based on a prediction loss of the target model, the input image can be normalized to an image suitable for a target task, so that stability of the learning and performance of the target model can be improved.

公开(公告)号：US20210295151A1

公开(公告)日：2021-09-23

申请号：US17077114

申请日：2020-10-22

Applicant: Lunit Inc.

Inventor： Donggeun YOO ,  Jeong Hoon LEE ,  Jae Hwan LEE

IPC: G06N3/08 ,  G06N3/04 ,  G06K9/62 ,  G06K9/46

Abstract: There is provided a method and apparatus that collects feature points of data and performs machine learning. A machine learning method comprises receiving first feature data obtained by applying a basic model to first analysis target data, receiving second feature data obtained by applying the basic model to second analysis target data, and obtaining a final machine learning model through performing machine learning on a correlation between the first feature data and first analysis result data and a correlation between the second feature data and second analysis result data.