Eunji Jun

Eunsong Kang

Wonjun Ko

A. Wisnu Mulyadi

Eunjin Jeon

Wonsik Jung

Jee-Seok Yoon

SeungWoo Jeong

Bum-Chae Kim

Eunho Lee

Jiyeon Lee

Chan-Woo Kim

Changhyun Park

Jaein Lee

Yurim Lee

HyoJune Kwon

Jaeun Phyo

Jieun Lee

Yooseung Shin

Wooyeol Park

Jaehyun Jeon

Hannah Yun

Jay Park

Yujin Ha

Ahyeong Jeong

Yoonsung Jeong

Chaehee Song

YoungJoon Chun

The Machine Intelligence Laboratory focuses on developing machine learning and deep learning methods. Research includes the investigation and analysis of patterns inherent in various forms of data, with applications to medical/computer vision, brain-computer interfaces, healthcare, and neuroinformatics.

본 연구실은 기계 학습 및 딥 러닝 방법 개발에 중점을 둔다. 주요 연구 분야는 의료/컴퓨터 비전, 뇌-컴퓨터 인터페이스, 헬스케어 및 신경정보학에 적용하여 다양한 형태의 데이터에 내재된 패턴을 분석하고 연구한다.

A learnable counter-condition analysis framework for functional connectivity-based neurological disorder diagnosis

ProtoBrainMaps: Prototypical Brain Maps for Alzheimer's Disease Progression Modeling

DyMix: Dynamic Frequency Mixup Scheduler based Unsupervised Domain Adaptation for Enhancing Alzheimer's Disease Identification

인포메디텍-치매 예측 솔루션 전문 기업

A hybrid of deep network and hidden Markov model for MCI identification with resting-state fMRI

Deep feature learning for pulmonary nodule classification in a lung CT

Learning-based Sleep Quality Evaluation

Medical transformer: Universal brain encoder for 3D MRI analysis

Unveiling diagnostic potential: Eeg microstate representation model for alzheimer's disease and frontotemporal dementia

Vignet: A deep convolutional neural network for eeg-based driver vigilance estimation

Continuous Riemannian geometric learning for sleep staging classification

TransSleep: Transitioning-aware attention-based deep neural network for sleep staging

Domain adaptation with source selection for motor-imagery based BCI

Mutual information-driven subject-invariant and class-relevant deep representation learning in BCI

Explainable Normative Modeling for Brain Disorder Identification in Resting-State fMRI

Enhancing EEG domain generalization via weighted contrastive learning

Energy-Guided Topology Mamba for EEG-Based BCI

Channel-aware self-supervised learning for EEG-based BCI

Deep geometric learning with monotonicity constraints for alzheimer's disease progression

EAG-RS: a novel explainability-guided ROI-selection framework for ASD Diagnosis via inter-regional relation learning

Uncertainty-aware variational-recurrent imputation network for clinical time series

Site-invariant meta-modulation learning for multisite autism spectrum disorders diagnosis

An empirical suggestion for collaborative learning in motor imagery-based BCIs

Fine-grained Temporal Attention Network for EEG-based Seizure Detection

Uncertainty-gated stochastic sequential model for EHR mortality prediction

Medical transformer: Universal encoder for 3-D brain MRI analysis

Semi-supervised deep adversarial learning for brain-computer interface

강화학습 방식을 통한 의도-상관적 뇌신호 분석 및 인식 모델링

Sociomarkers and Connectomes: Neurodevelopmental Imprints in Adolescent Brains

Fiesta: Fourier-based semantic augmentation with uncertainty guidance for enhanced domain generalizability in medical image segmentation

뇌전도 신호 자가-지도 표현 학습을 통한 발화 상상 BCI 성능 향상

Eeg-oriented self-supervised learning with triple information pathways network

Multi-view integrative attention-based deep representation learning for irregular clinical time-series data

Semi-Supervised Generative and Discriminative Adversarial Learning for Motor Imagery-based Brain–Computer Interface

A deep generative–discriminative learning for multimodal representation in imaging genetics

Age-aware guidance via masking-based attention in face aging

Knowledge-induced medicine prescribing network for medication recommendation

ADT²R: Adaptive Decision Transformer for Dynamic Treatment Regimes in Sepsis

Efficient continuous manifold learning for time series modeling

SIGMAformer: a spatiotemporal gaussian mixture correlation transformer for global weather forecasting

ExpertDiff: Head-less Model Reprogramming with Diffusion Classifiers for Out-of-Distribution Generalization

Individual identification using cognitive electroencephalographic neurodynamics

MEASURE: Multi-scale Minimal Sufficient Representation Learning for Domain Generalization in Sleep Staging

A plug-in method for representation factorization in connectionist models

Learn-explain-reinforce: counterfactual reasoning and its guidance to reinforce an Alzheimer's Disease diagnosis model

Toward Subject Invariant and Class Disentangled Representation in BCI via Cross-Domain Mutual Information Estimator.

Commanding a brain-controlled wheelchair using steady-state somatosensory evoked potentials

Domain generalization for medical image analysis: A review

Parameter-Efficient Transfer Learning for EEG Foundation Models via Task-Relevant Feature Focusing

Deep recurrent spatio-temporal neural network for motor imagery based BCI

Frequency-Conditioned Diffusion Models for Time Series Generation

ENGINE: Enhancing neuroimaging and genetic information by neural embedding

Clinically-guided Prototype Learning and Its Use for Explanation in Alzheimer's Disease Identification

Quantifying Explainability of Counterfactual-Guided MRI Feature for Alzheimer's Disease Prediction

Deep efficient continuous manifold learning for time series modeling

Deep Counterfactual-Guided MRI Feature Representation and Quantitatively Interpretable Alzheimer's Disease Prediction

Deep recurrent disease progression model for conversion-time prediction of Alzheimer's disease

Efficient Continuous Manifold Learning for Time Series Modeling

Xadlime: explainable Alzheimer's disease likelihood map estimation via clinically-guided prototype learning

Quantized Factor Identifiable Causal Effect Variational Autoencoder

Learning in Structural MRI for AD/MCI

Deep geometrical learning for Alzheimer's disease progression modeling

A novel RL-assisted deep learning framework for task-informative signals selection and classification for spontaneous BCIs

Born Identity Network: Multi-way Counterfactual Map Generation to Explain a Classifier's Decision

휴지-상태 fMRI 영상 기반 자폐증 진단을 위한 다중-레벨 그래프 컨볼루션 네트워크

조기 경도인지장애 진단을 위한 뇌 영역간 지역적 관계 표현 학습

Leveraging coupled interaction for multimodal Alzheimer's disease diagnosis

조건부 적대적 생성 신경망을 이용한 동작 상상 기반 뇌-컴퓨터 인터페이스 성능 향상을 위한 뇌 신호 데이터 증대

임상 상태 예측을 위한 자가 주의집중 메커니즘 기반 불규칙적 시계열 전자건강기록 데이터 모델링

Eeg-oriented self-supervised learning and cluster-aware adaptation

데이터 기반 시간 및 다변수 간 상관관계를 통한 결측값 대체 방법을 이용한 알츠하이머병 진행 모델링

Deep Learning in Medical Image Analysis

휴지-상태 fMRI 영상에서의 동적 특징 추출 및 자폐증 조기 진단

다중-크기 다중-인스턴스 학습 기반 해석 가능한 알츠하이머병 진단 모델

Multifrequency Analysis of Brain-Computer Interfaces

자기공명영상 기반 알츠하이머병 진단을 위한 설명 가능한 주의 네트워크

Fine-grained attention for weakly supervised object localization

다중-사이트 휴지-상태 fMRI 영상 기반 주요우울장애 진단을 위한 메타학습 모델

Stochastic imputation and uncertainty-aware attention to EHR for mortality prediction

딥러닝 기반의 멀티-모달 MRI 영상에서의 뇌종양 영역 분할

쌓아올린 잡음제거 오토인코더를 이용한 알츠하이머병 진단 및 관심 영역별 정량적 분석 모델

Multi-scale neural network for EEG representation learning in BCI

딥러닝 기반 기능적 뇌 영상 분석 및 경도인지장애 진단 프레임워크

“딥러닝이 바꾸는 미래사회” 특집을 내면서

of KIISE

카카오의 AI 기반 영상 처리 기술

정보과학회지 월별 특집계획

BRAIN IMAGE-BASED QUANTITATIVE BRAIN DISEASE PREDICTION METHOD AND APPARATUS

스펙트럴 표현 학습을 통한 뇌전도 기반 기능적 자기공명영상 합성 방법 및 장치

fMRI 기반 주의 집중 일관성 유지 기법을 통한 이미지 재구성 방법 및 장치

병리학적 정보를 보존하는 뇌영상 합성 방법 및 장치

의료 리포트와 생성형 AI를 이용한 자동 의료 영상 분할 방법 및 그 장치

수면 단계 변화 패턴을 이용한 수면 평가 방법 및 수면 평가 장치

알츠하이머병 진단 예측 및 설명 방법과 그 장치

불확실성 가이드를 활용한 푸리에 기반 의미론적 데이터 증강 방법 및 그 장치

METHOD AND APPARATUS FOR REASONING AND REINFORCING DECISION IN BRAIN DISEASE DIAGNOSIS MODEL

생성형 인공지능 기반 텍스트-이미지 편집 방법 및 장치

자기공명영상 기반 뇌질환 예측 방법 및 장치

딥러닝 기반 인과 효과 추정 방법 및 그 장치

딥러닝 기반 유전자형-표현형 데이터 분석 및 질병 진단 방법 및 장치

가중 대조학습을 이용한 뇌전도 도메인 일반화 능력 향상 방법 및 장치

태스크 적응형 뇌전도 신호 분석 방법 및 장치

기능적 자기공명 영상에서의 뇌 기능 이상 탐지 방법 및 그 장치

상호정보량 기반 여러 사용자간 공통된 클래스 관련 특징 학습을 통한 뇌-컴퓨터 인터페이스 방법 및 장치

환자 진단 예측 방법 및 그 장치

공간-시간 뇌 신호 처리 방법 및 그 장치

뇌 질환 예측 장치 및 방법, 뇌 질환을 예측하기 위한 학습 장치

알츠하이머병 진단 모델의 결정을 추론하고 강화하는 방법 및 장치

딥러닝 기반 뇌전증 발작 진단 방법 및 장치

딥러닝 기반 시계열 데이터 분석 방법 및 그 장치

개인 맞춤 뇌 지도 생성 방법 및 그 장치

약한 지도 학습 기반 객체 지역화와 의미론적 분할 방법 및 그 장치

뇌 자기공명영상 나이 변형 방법 및 그 장치

알츠하이머 질병 진단을 위한 비지도 도메인 적응 방법 및 그 장치

3차원 의료 영상 분석을 위한 자가학습 기반 전이 학습 방법 및 그 장치

분류 결과 설명이 가능한 반 사실적 맵 생성 방법 및 그 장치

위치 기반 뇌 질환 판별 가능 영역 지역화 및 설명력 있는 뇌 질환 진단 방법 및 장치

상호정보량 기반 여러 사용자간 공통된 클래스 관련 특징 학습을 통한 뇌 – 컴퓨터 인터페이스 방법 및 장치

불규칙 임상 시계열 데이터 예측 및 분류 방법, 및 장치

차량에서의 돌발적으로 출현한 이동 객체를 탐지하는 방법 및 장치

설명 가능한 소수샷 영상 분류 방법 및 장치

딥러닝 기반 고자기장 자기공명영상 합성 방법 및 장치

적대적 학습 기반 뇌-컴퓨터 인터페이스 방법 및 장치

딥러닝 기반 인공 뇌전도 신호 생성 및 뇌-컴퓨터 인터페이스 방법 및 장치

딥러닝 기반 뇌 질환 진단 방법

병변 스크리닝 장치 및 방법

흉부 단층영상에서 검색된 폐결절의 암 진단 보조 시스템 및 프로그램

다중 뇌 연결망 구축을 통한 뇌 상태 모니터링 방법 및 장치

주행 환경 이해에 기반을 둔 갑작스러운 보행자 출현 경고 방법 및 시스템

Deep learning in medical image analysis

Hierarchical feature representation and multimodal fusion with deep learning for AD/MCI diagnosis

Deep learning based imaging data completion for improved brain disease diagnosis

Latent feature representation with stacked auto-encoder for AD/MCI diagnosis

Deep learning-based feature representation for AD/MCI classification

State-space model with deep learning for functional dynamics estimation in resting-state fMRI

Deep ensemble learning of sparse regression models for brain disease diagnosis

A novel Bayesian framework for discriminative feature extraction in brain-computer interfaces

Hand gesture recognition based on dynamic Bayesian network framework

A novel relational regularization feature selection method for joint regression and classification in AD diagnosis

Subspace regularized sparse multitask learning for multiclass neurodegenerative disease identification

A novel matrix-similarity based loss function for joint regression and classification in AD diagnosis

Deep sparse multi-task learning for feature selection in Alzheimer’s disease diagnosis

Person authentication from neural activity of face-specific visual self-representation

An introduction to neural networks and deep learning

Non-homogeneous spatial filter optimization for ElectroEncephaloGram (EEG)-based motor imagery classification

Multimodal manifold-regularized transfer learning for MCI conversion prediction

Dinggang Shen

Xiaofeng ZHU

Li Wang

Yinghuan Shi（史颖欢）

Mingxia Liu

Seul-Ki Yeom

Shuiwang Ji, Professor and Truchard...

Rongjian Li

Daoqiang Zhang

Klaus-Robert Müller

Siamac Fazli

Kim Han Thung

Feng Liu

Hee-Deok Yang

Christian Wallraven

Seong-Whan Lee

Chong-Yaw Wee

HEUNG-IL SUK

This review covers computer-assisted analysis of images in the field of medical imaging. Recent advances in machine learning, especially with regard to deep learning, are helping to identify, classify, and quantify patterns in medical images. At the core of these advances is the ability to exploit hierarchical feature representations learned solely from data, instead of features designed by hand according to domain-specific knowledge. Deep learning is rapidly becoming the state of the art, leading to enhanced performance in various medical applications. We introduce the fundamentals of deep learning methods and review their successes in image registration, detection of anatomical and cellular structures, tissue segmentation, computer-aided disease diagnosis and prognosis, and so on. We conclude by discussing research issues and suggesting future directions for further improvement.

For the last decade, it has been shown that neuroimaging can be a potential tool for the diagnosis of Alzheimer's Disease (AD) and its prodromal stage, Mild Cognitive Impairment (MCI), and also fusion of different modalities can further provide the complementary information to enhance diagnostic accuracy. Here, we focus on the problems of both feature representation and fusion of multimodal information from Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET). To our best knowledge, the previous methods in the literature mostly used hand-crafted features such as cortical thickness, gray matter densities from MRI, or voxel intensities from PET, and then combined these multimodal features by simply concatenating into a long vector or transforming into a higher-dimensional kernel space. In this paper, we propose a novel method for a high-level latent and shared feature representation …

Combining multi-modality brain data for disease diagnosis commonly leads to improved performance. A challenge in using multi-modality data is that the data are commonly incomplete; namely, some modality might be missing for some subjects. In this work, we proposed a deep learning based framework for estimating multi-modality imaging data. Our method takes the form of convolutional neural networks, where the input and output are two volumetric modalities. The network contains a large number of trainable parameters that capture the relationship between input and output modalities. When trained on subjects with all modalities, the network can estimate the output modality given the input modality. We evaluated our method on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database, where the input and output modalities are MRI and PET images, respectively. Results showed that our method …

Recently, there have been great interests for computer-aided diagnosis of Alzheimer’s disease (AD) and its prodromal stage, mild cognitive impairment (MCI). Unlike the previous methods that considered simple low-level features such as gray matter tissue volumes from MRI, and mean signal intensities from PET, in this paper, we propose a deep learning-based latent feature representation with a stacked auto-encoder (SAE). We believe that there exist latent non-linear complicated patterns inherent in the low-level features such as relations among features. Combining the latent information with the original features helps build a robust model in AD/MCI classification, with high diagnostic accuracy. Furthermore, thanks to the unsupervised characteristic of the pre-training in deep learning, we can benefit from the target-unrelated samples to initialize parameters of SAE, thus finding optimal parameters in fine-tuning …

In recent years, there has been a great interest in computer-aided diagnosis of Alzheimer’s Disease (AD) and its prodromal stage, Mild Cognitive Impairment (MCI). Unlike the previous methods that consider simple low-level features such as gray matter tissue volumes from MRI, mean signal intensities from PET, in this paper, we propose a deep learning-based feature representation with a stacked auto-encoder. We believe that there exist latent complicated patterns, e.g. , non-linear relations, inherent in the low-level features. Combining latent information with the original low-level features helps build a robust model for AD/MCI classification with high diagnostic accuracy. Using the ADNI dataset, we conducted experiments showing that the proposed method is 95.9%, 85.0%, and 75.8% accurate for AD, MCI, and MCI-converter diagnosis, respectively.

Studies on resting-state functional Magnetic Resonance Imaging (rs-fMRI) have shown that different brain regions still actively interact with each other while a subject is at rest, and such functional interaction is not stationary but changes over time. In terms of a large-scale brain network, in this paper, we focus on time-varying patterns of functional networks, i.e., functional dynamics, inherent in rs-fMRI, which is one of the emerging issues along with the network modelling. Specifically, we propose a novel methodological architecture that combines deep learning and state-space modelling, and apply it to rs-fMRI based Mild Cognitive Impairment (MCI) diagnosis. We first devise a Deep Auto-Encoder (DAE) to discover hierarchical non-linear functional relations among regions, by which we transform the regional features into an embedding space, whose bases are complex functional networks. Given the embedded …

Recent studies on brain imaging analysis witnessed the core roles of machine learning techniques in computer-assisted intervention for brain disease diagnosis. Of various machine-learning techniques, sparse regression models have proved their effectiveness in handling high-dimensional data but with a small number of training samples, especially in medical problems. In the meantime, deep learning methods have been making great successes by outperforming the state-of-the-art performances in various applications. In this paper, we propose a novel framework that combines the two conceptually different methods of sparse regression and deep learning for Alzheimer’s disease/mild cognitive impairment diagnosis and prognosis. Specifically, we first train multiple sparse regression models, each of which is trained with different values of a regularization control parameter. Thus, our multiple sparse regression …

Professor

Machine Intelligence Laboratory

교수님 소개

석흥일

연구실 소개

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

Explainable Normative Modeling for Brain Disorder Identification in Resting-State fMRI

Energy-Guided Topology Mamba for EEG-Based BCI

Fiesta: Fourier-based semantic augmentation with uncertainty guidance for enhanced domain generalizability in medical image segmentation

연구실 보유 특허

대학별 입시끈

우리 연구실 모집

교수님 소개

석흥일

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

Explainable Normative Modeling for Brain Disorder Identification in Resting-State fMRI

Energy-Guided Topology Mamba for EEG-Based BCI

Fiesta: Fourier-based semantic augmentation with uncertainty guidance for enhanced domain generalizability in medical image segmentation

연구실 보유 특허

최근 3년간 연구실적 높은 연구실

대학별 입시끈

우리 연구실 모집