Korea Advanced Institute of Science and Technology

University of Ulsan Foundation for Industry Cooperation

The Asan Foundation

JongChul Ye

Yoseob Han

Sangjoon Park

Shujaat Khan

Boah Kim

Jaeyoung Huh

Gwanghyun Kim

Gyutaek Oh

Hyun Woo Koo

Ju Young Lee

Dongwook Lee

Dong Hyun Yang

Yujin Oh

Byeongsu Sim

Eunhee Kang

Eunju Cha

Joon Bum Seo

Hyungjin Chung

Yeohun Yoon

Taesung Kwon

A magnetic resonance imaging (MRI) recovery method using a score-based diffusion model and an apparatus thereof are provided. The MRI recovery method using the score-based diffusion model, which is performed by a computer, is implemented, including training a continuous time-dependent score function with denoising score matching and sampling data from a conditional distribution given the measurements, leveraging the learned score function, and recovering an image.

Magnetic resource imaging recovery method using score-based diffusion model and apparatus thereof

Disclosed is a quantitative susceptibility mapping image processing method using an unsupervised learning-based neural network and an apparatus therefor. The quantitative susceptibility mapping image processing method includes receiving a phase image and a magnitude image for reconstructing the quantitative susceptibility mapping image, and reconstructing the quantitative susceptibility mapping image corresponding to the received phase image and the received magnitude image using an unsupervised learning-based neural network, and the neural network may be generated based on an optimal transport theory.

Quantitative susceptibility mapping image processing method using neural network based on unsupervised learning and apparatus therefor

Disclosed are a method and apparatus for processing a low-dose X-ray computed tomography image based on efficient unsupervised learning by using an invertible neural network. The method of processing a low-dose X-ray computed tomography image based on unsupervised learning by using an invertible neural network performed by a computer device includes providing an invertible generator for restoring an image, and training the invertible generator to restore a low-dose computed tomography image to a normal computed tomography image.

Method and apparatus for low-dose X-ray computed tomography image processing based on efficient unsupervised learning using invertible neural network

Disclosed are an unsupervised learning method and an apparatus therefor applicable to general inverse problems. An unsupervised learning method applicable to inverse problems includes receiving a training data set and training an unsupervised learning-based neural network generated based on an optimal transport theory and a penalized least square (PLS) approach using the training data set, wherein the receiving of the training data set includes receiving the training data set including unmatched data.

Unsupervised learning method for general inverse problem and apparatus therefor

Disclosed are an unsupervised learning-based image registration method using a neural network with cycle consistency and an apparatus therefor. An image registration method includes receiving a first image and a second image for image registration, outputting a deformation field for the first image and the second image using an unsupervised learning-based neural network with cycle consistency for the deformation field, and generating a registration image for the first image and the second image based on a spatial deformation function using the output deformation field. The outputting of the deformation field includes outputting the deformation field for the first image for registering the first image to the second image may be output, when the first image is a moving image and the second image is a fixed image, and the generating of the registration image includes generating the registration image by applying the deformation field for the first image to the first image using the spatial deformation function.

Unsupervised deformable image registration method using cycle-consistent neural network and apparatus therefor

Disclosed is a method and apparatus for quantifying severity of infectious disease based on a vision transformer using a chest X-ray (CXR) image. Here, a method of quantifying severity of infectious disease based on a vision transformer includes receiving an input CXR image; extracting a feature map from the received input CXR image using a pretrained neural network; classifying a lesion in the input CXR image using the vision transformer based on the extracted feature map; and quantifying severity of the input CXR image based on the extracted feature map and the classified lesion.

Severity quantification and lesion localization method of infectious disease on CXR using vision transformer and apparatus therefor

Disclosed is an image segmentation method including receiving an image to be segmented and segmenting the received image by using a neural network learned through a Mumford-Shah function-based loss function.

Image segmentation method using neural network based on mumford-shah function and apparatus therefor

Disclosed are a method of classifying lesions of chest x-ray radiographs based on data normalization and local patches and an apparatus thereof. The method includes converting an input chest x-ray radiograph into a normalized image, segmenting the converted normalized image into an organ area by using a first neural network based on a pre-learned segmentation model, generating local patches for the segmented organ area, and classifying a lesion in the input chest x-ray radiograph by using a second neural network based on a pre-learned classification model for the generated local patches.

Method of classifying lesion of chest x-ray radiograph based on data normalization and local patch and apparatus thereof

Disclosed are a method and apparatus for replacing missing image data. The method of replacing missing image data includes receiving input image data for at least two or more domains among preset multiple domains, and restoring missing image data of a preset target domain by using a neural network that uses the two or more input image data as inputs. The neural network may combine fake image data of a first target domain generated by inputting real image data of at least two or more domains of the multiple domains and the real image data, and be trained by using a multi-cycle consistency loss in which an image restored by inputting the combined image data is similar with the real image data.

Method of replacing missing image data by using neural network and apparatus thereof

An apparatus and method for processing an ultrasound image in various sensor conditions are provided. The method includes receiving a data cube via sensors, transforming the received data cube into focus data through beam focusing, and outputting inphase data and quadrature phase data for the focus data using a neural network corresponding to signal adder and Hilbert transform functions. The method further includes detecting an envelope of the inphase data and the quadrature phase data and reconstructing an ultrasound image for the data cube using log compression.

Apparatus and method for processing ultrasound image in various sensor conditions

An image processing apparatus according to an embodiment removes the noise included in the three-dimensional input image, determines the lost information in a process of obtaining the three-dimensional input image, or enhances the resolution of the three-dimensional input image, by using the neural network learned in advance. The image processing apparatus slices the three-dimensional input image along a depth, converts a three-dimensional input image into a two-dimensional input image, and inputs the converted two-dimensional input image into a neural network. The image processing apparatus generates a three-dimensional output image of which the quality of the three-dimensional input image is enhanced, based on the output of the neural network.

Image processing apparatus using neural network and method performed by image processing apparatus

Disclosed herein are a method and an apparatus for removing ghost artifacts of an echo planner image using a neural network. An image processing method according to an embodiment of the inventive concept includes receiving Fourier space data of an echo planar image, and restoring the echo planar image in which ghost artifacts are removed using a neural network. The receiving of the Fourier space data may include dividing the Fourier space data into the odd-numbered Fourier space data and even-numbered Fourier space data, and the restoring of the echo planar image may include obtaining the odd-numbered Fourier space data and even-numbered Fourier space data with the Fourier space interpolated using the neural network and restoring the echo planar image in which the ghost artifacts are removed based on the odd-numbered Fourier space data and even-numbered Fourier space data with the Fourier space interpolated.

Method for removing ghost artifact of echo planar imaging by using neural network and apparatus therefor

A method for processing an unmatched low-dose X-ray computed tomography (CT) image using a neural network and an apparatus therefor are provided. The method includes receiving a low-dose X-ray CT image and removing noise from the low-dose X-ray CT image using a unsupervised learning based neural network learned using unmatched data to reconstruct a routine-dose X-ray CT image corresponding to the low-dose X-ray CT image.

Method for processing unmatched low-dose X-ray computed tomography image using neural network and apparatus therefor

A method for processing a sparse-view computed tomography (CT) image using a neural network and an apparatus therefor are provided. The method includes receiving a sparse-view CT data and reconstructing an image for the sparse-view CT data using a neural network of a learning model satisfying a predetermined frame condition.

Method for processing sparse-view computed tomography image using neural network and apparatus therefor

A method for processing a multi-directional X-ray computed tomography (CT) image using a neural network and an apparatus therefor are provided. The method includes receiving a predetermined number of multi-directional X-ray CT data and reconstructing an image for the multi-directional X-ray CT data using a neural network learned in each of an image domain and a sinogram domain.

Growing community of inventors

Daejeon, South Korea

JongChul Ye