公开(公告)号：US20220319001A1

公开(公告)日：2022-10-06

申请号：US17710026

申请日：2022-03-31

Applicant: KOREA INSTITUTE OF SCIENCE AND TECHNOLOGY

Inventor： Hyung Min KIM ,  Kyungho YOON ,  Tae Young PARK ,  Heekyung KOH

IPC: G06T7/00 ,  G16H20/30

Abstract: A real-time acoustic simulation method based on artificial intelligence according to an embodiment of the present disclosure includes acquiring medical image data of a target area to be treated; determining ultrasound parameters related to the output of an ultrasonic transducer based on the medical image data; inputting the ultrasound parameters to a numerical model to generate a numerical model based acoustic simulation image for a specific position of the ultrasonic transducer; training an artificial intelligence model using the medical image data and the numerical model based acoustic simulation image; generating an artificial intelligence model based acoustic simulation image for an arbitrary position of the ultrasonic transducer using the trained artificial intelligence model; and outputting a real-time acoustic simulation image with a position change of the ultrasonic transducer.

公开(公告)号：US20240062882A1

公开(公告)日：2024-02-22

申请号：US18449093

申请日：2023-08-14

Applicant: KOREA INSTITUTE OF SCIENCE AND TECHNOLOGY

Inventor： Hyung Min KIM ,  Heekyung KOH ,  Taeyoung PARK

IPC: G16H30/40 ,  G06T17/00

CPC classification number: G16H30/40 ,  G06T17/00 ,  G06T2207/30036

Abstract: Disclosed in the present application is provided a method of automating a dental crown design based on artificial intelligence, the method may include: acquiring a three-dimensional intra-oral scanner image acquired from a patient and a three-dimensional dental crown mesh image designed by a dental technician in correspondence with the intra-oral scanner image; preprocessing the acquired three-dimensional intra-oral scanner image and the three-dimensional dental crown mesh image designed by the dental technician in correspondence with the intra-oral scanner image; converting an input mesh model and an output mesh model into an input voxel image and an output voxel image, respectively; and generating an AI output voxel image corresponding to the input voxel image using the converted input voxel image and output voxel image as training data, and training an artificial neural network by comparing the generated AI output voxel image with the output voxel image included in the training data.

公开(公告)号：US20220292737A1

公开(公告)日：2022-09-15

申请号：US17689032

申请日：2022-03-08

Applicant: KOREA INSTITUTE OF SCIENCE AND TECHNOLOGY

Inventor： Hyung Min KIM ,  Kyungho YOON ,  Tae Young PARK ,  Heekyung KOH

IPC: G06T11/00 ,  G06T7/11 ,  A61N7/02 ,  A61B5/00 ,  A61B5/055 ,  G16H30/40

Abstract: The present disclosure relates to a method for converting magnetic resonance imaging (MRI) to a computed tomography (CT) image using an artificial intelligence machine learning model, for use in ultrasound treatment device applications. The method includes acquiring training data including an MRI image and a CT image for machine learning; training an artificial neural network model using the training data, wherein artificial neural network model generates a CT image corresponding to the MRI image, and compares the generated CT image with the original CT image included in the training data; receiving an input MRI image to be converted to a CT image; splitting the input MRI image into a plurality of patches; generating patches of a CT image corresponding to the patches of the input MRI image using the trained artificial neural network model; and merging the patches of the CT image to generate an output CT image.