公开(公告)号：US11335455B2

公开(公告)日：2022-05-17

申请号：US16671430

申请日：2019-11-01

Applicant: Lunit Inc.

Inventor： Kyoung Won Lee ,  Kyung Hyun Paeng

IPC: G16H30/40 ,  G06N3/08 ,  G16H30/20 ,  G06F40/169 ,  G16H10/40 ,  G06T7/00 ,  G06K9/62 ,  G16H40/20 ,  G06Q10/06

Abstract: A computing device obtains information about a medical slide image, and determines a dataset type of the medical slide image and a panel of the medical slide image. The computing device assigns to an annotator account, an annotation job defined by at least the medical slide image, the determined dataset type, an annotation task, and a patch that is a partial area of the medical slide image. The annotation task includes the determined panel, and the panel is designated as one of a plurality of panels including a cell panel, a tissue panel, and a structure panel. The dataset type indicates a use of the medical slide image and is designated as one of a plurality of uses including a training use of a medical learning model and a validation use of the machine learning model.

公开(公告)号：US20220145401A1

公开(公告)日：2022-05-12

申请号：US17521008

申请日：2021-11-08

Applicant: LUNIT INC.

Inventor： Jeong Hoon LEE

IPC: C12Q1/6886 ,  G16B40/20

Abstract: A method for predicting responsiveness to therapy for cancer patient is provided, which includes acquiring a pathology slide image of a cancer patient, determining information on a plurality of lymphocytes and information on a plurality of tumor cells included in the pathology slide image, calculating a lymphocyte and tumor cell interaction score based on the information on the plurality of lymphocytes and the information on the plurality of tumor cells, and predicting responsiveness to therapy for the cancer patient by using the interaction score.

公开(公告)号：US20220036558A1

公开(公告)日：2022-02-03

申请号：US17502260

申请日：2021-10-15

Applicant: LUNIT INC.

Inventor： Jae Hong AUM ,  Chanyoung OCK ,  Donggeun YOO

IPC: G06T7/00 ,  G06T7/11 ,  G16H30/20 ,  G16H50/30 ,  A61B5/00

Abstract: The present disclosure relates to a method for predicting biomarker expression from a medical image. The method for predicting biomarker expression includes receiving a medical image, and outputting indices of biomarker expression for the at least one lesion included in the medical image by using a first machine learning model.

公开(公告)号：US20220036549A1

公开(公告)日：2022-02-03

申请号：US17502661

申请日：2021-10-15

Applicant: LUNIT Inc.

Inventor： Donggeun Yoo ,  Chanyoung Ock ,  Kyunghyun Paeng

IPC: G06T7/00 ,  G16B20/00 ,  G06N3/02

Abstract: The present disclosure relates to a method, performed by at least one computing device, for providing information associated with immune phenotype for pathology slide image. The method may include obtaining information associated with immune phenotype for one or more regions of interest (ROIs) in a pathology slide image, generating, based on the information associated with the immune phenotype for one or more ROIs, an image indicative of the information associated with the immune phenotype, and outputting the image indicative of the information associated with immune phenotype.

公开(公告)号：US20210390679A1

公开(公告)日：2021-12-16

申请号：US17363793

申请日：2021-06-30

Applicant: LUNIT INC.

Inventor： Hyunjae LEE

IPC: G06T7/00

Abstract: Provided is a method for providing annotation information for a 3D image, which may include outputting a representative image for the 3D image including a plurality of slices, selecting at least one pixel associated with a target item from among a plurality of pixels included in the representative image, outputting, among the plurality of slices, a slice associated with the selected at least one pixel, and receiving an annotation for a partial region of the output slice.

公开(公告)号：US11200483B2

公开(公告)日：2021-12-14

申请号：US15378001

申请日：2016-12-13

Applicant: Lunit Inc.

Inventor： Sang Heum Hwang ,  Hyo Eun Kim

IPC: G06N3/04 ,  G06N3/08

Abstract: A machine learning method based on weakly supervised learning according to an embodiment of the present invention includes extracting feature maps about a dataset given a first type of information and not given a second type of information by using a convolutional neural network (CNN), updating the CNN by back-propagating a first error value calculated as a result of performing a task corresponding to the first type of information by using a first model, and updating the CNN by back-propagating a second error value calculated as a result of performing the task corresponding to the first type of information by using a second model different from the first model, wherein the second type of information is extracted when the task corresponding to the first type of information is performed using the second model.

公开(公告)号：US20210366594A1

公开(公告)日：2021-11-25

申请号：US16953693

申请日：2020-11-20

Applicant: LUNIT INC.

Inventor： Chunseong PARK

IPC: G16H30/40 ,  G06T7/00 ,  G06T7/11 ,  G06N3/08

Abstract: A method for refining label information, which is performed by at least one computing device is disclosed. The method includes acquiring a pathology slide image including a plurality of patches, inferring a plurality of label information items for the plurality of patches included in the acquired pathology slide image using a machine learning model, applying the inferred plurality of label information items to the pathology slide image, and providing the pathology slide image applied with the inferred plurality of label information items to an annotator terminal.

公开(公告)号：US20210125059A1

公开(公告)日：2021-04-29

申请号：US16842373

申请日：2020-04-07

Applicant: Lunit Inc.

Inventor： HyunJae LEE ,  Hyeonseob NAM

IPC: G06N3/08 ,  G06N3/04

Abstract: Provided is a method for training a neural network and a device thereof. The method may train a neural network including first and second layers in a computing device. The method may include acquiring, at a processor of the computing device, a layer output of the first layer for training data and extracting, at the processor, statistics information of the layer output. The method may also include normalizing, at the processor, the layer output through the statistics information to generate a normalized output and augmenting, at the processor, the statistics information to generate augmented statistics information associated with the statistics information. The method may further include performing, at the processor, an affine transform on the normalized output using the augmented statistics information to generate a transformed output and providing, at the processor, the transformed output as an input to the second layer.

公开(公告)号：US20210103797A1

公开(公告)日：2021-04-08

申请号：US16694843

申请日：2019-11-25

Applicant: Lunit Inc.

Inventor： Minje JANG

IPC: G06N3/04 ,  G06N3/08 ,  G06K9/46 ,  G06K9/66

Abstract: An image analysis method and an image analysis system are disclosed. The method may include extracting training graphic data including at least one first node corresponding to a plurality of histological features of a training tissue slide image, and at least one first edge defined by a relationship between the histological features The method may also include determining a parameter of a readout function by training a graph neural network (GNN) using the training graphic data and training output data corresponding to the training graphic data. The method may also include extracting inference graphic data including at least one second node corresponding to a plurality of histological features of an inference tissue slide image, and at least one second edge decided by a relationship between the histological features, The method may further include deriving inference output data by the readout function after inputting the inference graphic data to the GNN.

公开(公告)号：US20200321118A1

公开(公告)日：2020-10-08

申请号：US16698878

申请日：2019-11-27

Applicant: Lunit Inc.

Inventor： Hyo-Eun KIM ,  HyunJae LEE

IPC: G16H50/20 ,  G06N20/00 ,  G16H30/20

Abstract: A domain adaptation method and apparatus based on adversarial learning are provided. The method may include extracting feature data from multiple data sets, training a first discriminator discriminating a domain for a first class using first feature data extracted from a first data set corresponding to a first class of a first domain among the multiple data sets and training the first discriminator using second feature data extracted from a second data set corresponding to the first class of a second domain among the multiple data sets. The method may also include training a second discriminator discriminating a domain for a second class using third feature data extracted from a third data set that corresponds to a second class of the first domain, and training the second discriminator using fourth feature data extracted from a fourth data set that corresponds to the second class of the second domain.