Dong-Hee Shin

Da-Hyun Kim

Sanghyeon Cho

Sangjun Park

The Medical Artificial Intelligence Laboratory (directed by Professor Tae-Eui Kam) focuses on artificial intelligence applications for solving medical problems. Research areas include AI applications in drug development (including ADMET prediction), development of deep learning models using molecular structure and mass spectrometry data, brain decoding technology based on brain signals, multi-modal medical language model research such as medical VQA, and AI-based analysis of brain diseases using medical images and biosignals.

감태의 교수가 지도하는 의료인공지능 연구실에서는 인공지능 기반 의료 문제 해결을 연구한다. 주요 연구 분야는 ADMET 예측을 포함한 신약 개발 전반에 걸친 인공지능 응용, 분자 구조 및 질량 분석 데이터를 활용한 딥러닝 모델 개발, 뇌 신호 기반 뇌 해석 기술, 의료 VQA 등 멀티모달 의료 언어 모델, 의료 영상 및 생체 신호 등을 활용한 AI 기반 뇌 질환 분석을 포함한다.

Image2SignalNet: Image-based deep learning approach for capturing neuronal signals from calcium imaging

Solving Blind Inverse Problem in Microscopy: Diffusion-based Zero-shot Isotropic Reconstruction

정보집약적인 동작 상상 뇌파 분류를 위한 Layer-wise Relevance Propagation 기반 채널 가지치기

Sparse graph representation learning based on reinforcement learning for personalized mild cognitive impairment (MCI) diagnosis

FTMMR: Fusion transformer for integrating multiple molecular representations

Autonomous system for EEG-based multiple abnormal mental states classification using hybrid deep neural networks under flight environment

Meta-learning-based cross-dataset motor imagery brain-computer interface

Curriculum Learning with Sampling Scheduler for Imbalanced EEG-Based Seizure Detection

Visual Decoding Using a Learnable Wavelet-Based Spatial-Spectral-Temporal EEG Embedding

Adaptive Reward Weighting via Reinforcement Learning for Major Depressive Disorder Diagnosis

Graph-based conditional generative adversarial networks for major depressive disorder diagnosis with synthetic functional brain network generation

MARS: multiagent reinforcement learning for spatial—spectral and temporal feature selection in EEG-based BCI

Toward robust canine cardiac diagnosis: Deep prototype alignment network-based few-shot segmentation in veterinary medicine

Molecular optimization with mamba-based gflownet

Hybrid local-global gnn for protein binding interface prediction via ensemble learning

GNN-based antibody structure prediction using quaternion and euler angle combined representation

Dynamic Many-Objective Molecular Optimization: Unfolding Complexity with Objective Decomposition and Progressive Optimization.

Agentic Brain: Agentic AI System for Autonomous Diagnosis of Functional Connectivity Network

Advancing Molecular Structure Elucidation for Mass Spectrum Interpretation via Cepstral Analysis

Spectral graph neural network-based multi-atlas brain network fusion for major depressive disorder diagnosis

Evolutionary reinforcement learning for automated hyperparameter optimization in EEG classification

Designing Selective Drugs: Multi-Objective Optimization to Mitigate Off-Target Effects

Multimodal Integration of MRI and Genetic Information for Glioblastoma Survival Prediction

Dymol: Dynamic many-objective molecular optimization with objective decomposition and progressive optimization

Attention-based spatio-temporal-spectral feature learning for subject-specific EEG classification

Appendix for SeeEEG: Semantic-aware EEG-based Multi-Modal Retrieval-Augmented Generation for High-Fidelity Visual Brain Decoding

Offline model-based optimization for real-world molecular discovery

Motion sickness prediction based on dry EEG in real driving environment

Group-wise Compression and Summarization via LLM-based Ensemble for Chest X-ray Report Generation

Dart: Disease-aware image-text alignment and self-correcting re-alignment for trustworthy radiology report generation

Seeeeg: Semantic-aware eeg-based multi-modal retrieval-augmented generation for high-fidelity visual brain decoding

Multi-modal Contrastive Learning for Tumor-specific Missing Modality Synthesis

A unified multi-modality fusion framework for deep spatio-spectral-temporal feature learning in resting-state fMRI denoising

Treatment Stitching with Schr\" odinger Bridge for Enhancing Offline Reinforcement Learning in Adaptive Treatment Strategies

DeepHealthNet: adolescent obesity prediction system based on a deep learning framework

Deep learning of static and dynamic brain functional networks for early MCI detection

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

Multiple functional networks modeling for autism spectrum disorder diagnosis

A novel deep learning framework on brain functional networks for early MCI diagnosis

Bridging the BCI illiteracy gap: a subject-to-subject semantic style transfer for EEG-based motor imagery classification

A deep learning framework for noise component detection from resting-state functional MRI

META-EEG: Meta-learning-based class-relevant EEG representation learning for zero-calibration brain–computer interfaces

Deep attentive spatio-temporal feature learning for automatic resting-state fMRI denoising

A learnable continuous wavelet-based multi-branch attentive convolutional neural network for spatio–spectral–temporal EEG signal decoding

The effects of layer-wise relevance propagation-based feature selection for EEG classification: a comparative study on multiple datasets

Enriched representation learning in resting-state fMRI for early MCI diagnosis

Tae-Eui Kam

While convolutional neural network (CNN) has been demonstrating powerful ability to learn hierarchical spatial features from medical images, it is still difficult to apply it directly to resting-state functional MRI (rs-fMRI) and the derived brain functional networks (BFNs). We propose a novel CNN framework to simultaneously learn embedded features from BFNs for brain disease diagnosis. Since BFNs can be built by considering both static and dynamic functional connectivity (FC), we first decompose rs-fMRI into multiple static BFNs with modified independent component analysis. Then, the voxel-wise variability in dynamic FC is used to quantify BFN dynamics. A set of paired 3D images representing static/dynamic BFNs can be fed into 3D CNNs, from which we can hierarchically and simultaneously learn static/dynamic BFN features. As a result, the dynamic BFN features can complement static BFN features and, at the …

Neuronal power attenuation or enhancement in specific frequency bands over the sensorimotor cortex, called Event-Related Desynchronization (ERD) or Event-Related Synchronization (ERS), respectively, is a major phenomenon in brain activities involved in imaginary movement of body parts. However, it is known that the nature of motor imagery-related electroencephalogram (EEG) signals is non-stationary and highly variable over time and frequency. In this paper, we propose a novel method of finding a discriminative time- and frequency-dependent spatial filter, which we call ‘non-homogeneous filter.’ We adaptively select bases of spatial filters over time and frequency. By taking both temporal and spectral features of EEGs in finding a spatial filter into account it is beneficial to be able to consider non-stationarity of EEG signals. In order to consider changes of ERD/ERS patterns over the time–frequency domain …

Despite countless studies on autism spectrum disorder (ASD), diagnosis relies on specific behavioral criteria and neuroimaging biomarkers for the disorder are still relatively scarce and irrelevant for diagnostic workup. Many researchers have focused on functional networks of brain activities using resting‐state functional magnetic resonance imaging (rsfMRI) to diagnose brain diseases, including ASD. Although some existing methods are able to reveal the abnormalities in functional networks, they are either highly dependent on prior assumptions for modeling these networks or do not focus on latent functional connectivities (FCs) by considering discriminative relations among FCs in a nonlinear way. In this article, we propose a novel framework to model multiple networks of rsfMRI with data‐driven approaches. Specifically, we construct large‐scale functional networks with hierarchical clustering and find …

The global prevalence of childhood and adolescent obesity is a major concern due to its association with chronic diseases and long-term health risks. Artificial intelligence technology has been identified as a potential solution to accurately predict obesity rates and provide personalized feedback to adolescents. This study highlights the importance of early identification and prevention of obesity-related health issues. To develop effective algorithms for the prediction of obesity rates and provide personalized feedback, factors such as height, weight, waist circumference, calorie intake, physical activity levels, and other relevant health information must be taken into account. Therefore, by collecting health datasets from 321 adolescents who participated in Would You Do It! application, we proposed an adolescent obesity prediction system that provides personalized predictions and assists individuals in making informed …

Although alternations of brain functional networks (BFNs) derived from resting-state functional magnetic resonance imaging (rs-fMRI) have been considered as promising biomarkers for early Alzheimer’s disease (AD) diagnosis, it is still challenging to perform individualized diagnosis, especially at the very early stage of preclinical stage of AD, i.e., early mild cognitive impairment (eMCI). Recently, convolutional neural networks (CNNs) show powerful ability in computer vision and image analysis applications, but there is still a gap for directly applying CNNs to rs-fMRI-based disease diagnosis. In this paper, we propose a novel multiple-BFN-based 3D CNN framework that can automatically and deeply learn complex, high-level, hierarchical diagnostic features from various independent component analysis-derived BFNs. More importantly, the embedded features of different BFNs could comprehensively support each …

Major Depressive Disorder (MDD) imposes a substantial burden within the healthcare domain, impacting millions of individuals worldwide. Functional Magnetic Resonance Imaging (fMRI) has emerged as a promising tool for the objective diagnosis of MDD, enabling the investigation of functional connectivity patterns in the brain associated with this disorder. However, most existing methods focus on a single brain atlas, which limits their ability to capture the complex, multi-scale nature of functional brain networks. To address these limitations, we propose a novel multi-atlas fusion method that incorporates early and late fusion in a unified framework. Our method introduces the concept of the holistic Functional Connectivity Network (FCN), which captures both intra-atlas relationships within individual atlases and inter-regional relationships between atlases with different brain parcellation scales. This comprehensive …

Detection of the pilots’ mental states is particularly critical because their abnormal mental states (AbSs) could cause catastrophic accidents. In this study, we presented the feasibility of classifying the various specific AbSs (namely, low fatigue, high fatigue, low workload, high workload, low distraction, and high distraction) by applying the deep learning method. To the best of our knowledge, this study is the first attempt to classify multiple AbSs of pilots. We proposed the hybrid deep neural networks with five convolutional blocks and two long short-term memory layers for decoding multiple AbSs. We designed the model to extract the informative features from electroencephalography signals. A total of ten pilots conducted the experiment in a simulated flight environment. Compared with five conventional models, our proposed model achieved the highest grand-average accuracy of 68.04(± 5.26)% which is at least 6.55 …

Major Depressive Disorder (MDD) is a pervasive disorder affecting millions of individuals, presenting a significant global health concern. Functional connectivity (FC) derived from resting-state functional Magnetic Resonance Imaging (rs-fMRI) serves as a crucial tool in revealing functional connectivity patterns associated with MDD, playing an essential role in precise diagnosis. However, the limited data availability of FC poses challenges for robust MDD diagnosis. To tackle this, some studies have employed Deep Neural Networks (DNN) architectures to construct Generative Adversarial Networks (GAN) for synthetic FC generation, but this tends to overlook the inherent topology characteristics of FC. To overcome this challenge, we propose a novel Graph Convolutional Networks (GCN)-based Conditional GAN with Class-Aware Discriminator (GC-GAN). GC-GAN utilizes GCN in both the generator and discriminator …

Introduction Brain-computer interfaces (BCIs) facilitate direct interaction between the human brain and computers, enabling individuals to control external devices through cognitive processes. Despite its potential, the problem of BCI illiteracy remains one of the major challenges due to inter-subject EEG variability, which hinders many users from effectively utilizing BCI systems. In this study, we propose a subject-to-subject semantic style transfer network (SSSTN) at the feature-level to address the BCI illiteracy problem in electroencephalogram (EEG)-based motor imagery (MI) classification tasks. Methods Our approach uses the continuous wavelet transform method to convert high-dimensional EEG data into images as input data. The SSSTN 1) trains a classifier for each subject, 2) transfers the distribution of class discrimination styles from the source subject (the best-performing subject for the classifier, i.e., BCI expert) to each subject of the target domain (the remaining subjects except the source subject, specifically BCI illiterates) through the proposed style loss, and applies a modified content loss to preserve the class-relevant semantic information of the target domain, and 3) finally merges the classifier predictions of both source and target subject using an ensemble technique. Results and discussion We evaluate the proposed method on the BCI Competition IV-2a and IV-2b datasets and demonstrate improved classification performance over existing methods, especially for BCI illiterate users. The ablation experiments and t-SNE visualizations further highlight the effectiveness of the proposed method in achieving meaningful feature-level …

Resting-state functional magnetic resonance imaging (rs-fMRI) is a non-invasive functional imaging technique that has been widely used to investigate brain functional connectome. Noises and artifacts are dominant in the raw rs-fMRI, making effective noise removal a necessity prior to any subsequent analysis. Without requiring any additional biophysiological recording devices, directly applying independent component analysis on rs-fMRI data becomes a popular process further separating structured noise from signals. However, fast and accurate automatic identification of the noise-related components is critical. Conventional machine learning techniques have been used in training such a classifier with manually engineered features of the components, which usually takes a long time even in the testing phase because its success relies on exhaustively extraction of spatial and temporal features and assembling …

Transfer learning for motor imagery-based brain–computer interfaces (MI-BCIs) struggles with inter-subject variability, hindering its generalization to new users. This paper proposes an advanced implicit transfer learning framework, META-EEG, designed to overcome the challenge arising from inter-subject variability. By incorporating gradient-based meta-learning with an intermittent freezing strategy, META-EEG ensures efficient feature representation learning, providing a robust zero-calibration solution. A comparative analysis reveals that META-EEG significantly outperforms all the baseline methods and competing methods on three different public datasets. Moreover, we demonstrate the efficiency of the proposed model through a neurophysiological and feature-representational analysis. With its robustness and superior performance on challenging datasets, META-EEG provides an effective solution for …

In recent years, deep learning methods have shown promising capabilities for extracting informative and discriminative features from electroencephalography (EEG) data. However, several studies have reported that the feature selection process followed by feature extraction can be beneficial to achieve further performance improvement. Even though a recent work achieved promising results by using the single-agent reinforcement learning (RL)-based framework to select task-relevant features in the temporal domain, it still failed to consider other significant features in the spatial-spectral domain. To overcome such limitations, we propose a cooperative multiagent RL-based framework (MARS) that performs feature selection in both the spatial–spectral and temporal domains simultaneously for a motor imagery (MI)-EEG classification task. In this framework, we enable our RL agents to collaborate with each other as a …

Currently, the expectations for autonomous vehicles (AVs) are increasing. However, it is expected to take at least a decade to develop a fully AV, where human intervention is completely unrequired. By then, human driving is required if necessary. Currently, when the AV hands over control to the driver, a safe driving environment can be created only if it is possible to determine whether the driver is in an abnormal state. Unfortunately, according to the sensory conflict theory, the risk of motion sickness (MS) is higher in AV than in ordinary vehicles. This is because neither passengers nor drivers can predict the movement path of the vehicle under AV, so there is more dissonance between vision and perception. Because the technology to remove MS when it occurs has not yet been developed, the best way to maintain the driver’s good condition is to quickly predict MS through the driver’s bio-signals and establish a …

Resting-state functional magnetic resonance imaging (rs-fMRI) is a non-invasive functional neuroimaging modality that has been widely used to investigate functional connectomes in the brain. Since noise and artifacts generated by non-neuronal physiological activities are predominant in raw rs-fMRI data, effective noise removal is one of the most important preprocessing steps prior to any subsequent analysis. For rs-fMRI denoising, a common trend is to decompose rs-fMRI data into multiple components and then regress out noise-related components. Therefore, various machine learning techniques have been used in such analyses with predefined procedures and manually engineered features. However, the lack of a universal definition of a noise-related source or artifact complicates manual feature engineering. Manual feature selection can result in the failure to capture unknown types of noise. Furthermore …

Deep learning methods, particularly convolutional neural networks (CNNs), have advanced the field of motor imagery (MI) by effectively extracting spatio-spectral–temporal (SST) features from electroencephalography (EEG) signals. Image-based CNNs using time–frequency analysis such as wavelet transform have outperformed signal-based CNNs in MI-EEG classification. However, the spatial characteristics of EEG signals can be neglected due to the high dimensionality of spectral–temporal feature space. Moreover, the performance hinges on whether the predefined transformation can capture the class-discriminative spectral–temporal representations of EEG signals well. Despite attempts to alleviate these challenges by selecting EEG electrodes or restricting spectral–temporal feature space, large inter-subject variabilities have impeded successful MI-EEG decoding. In this paper, we propose a learnable …

Introduction The brain-computer interface (BCI) allows individuals to control external devices using their neural signals. One popular BCI paradigm is motor imagery (MI), which involves imagining movements to induce neural signals that can be decoded to control devices according to the user's intention. Electroencephalography (EEG) is frequently used for acquiring neural signals from the brain in the fields of MI-BCI due to its non-invasiveness and high temporal resolution. However, EEG signals can be affected by noise and artifacts, and patterns of EEG signals vary across different subjects. Therefore, selecting the most informative features is one of the essential processes to enhance classification performance in MI-BCI. Methods In this study, we design a layer-wise relevance propagation (LRP)-based feature selection method which can be easily integrated into deep learning (DL)-based models. We assess its effectiveness for reliable class-discriminative EEG feature selection on two different publicly available EEG datasets with various DL-based backbone models in the subject-dependent scenario. Results and discussion The results show that LRP-based feature selection enhances the performance for MI classification on both datasets for all DL-based backbone models. Based on our analysis, we believe that it can broad its capability to different research domains.

In recent studies, we have witnessed the applicability of deep learning methods on resting-state functional Magnetic Resonance Image (rs-fMRI) analysis and on its use for brain disease diagnosis, e.g. , early Mild Cognitive Impairment (eMCI) identification. However, to our best knowledge, many of the existing methods are generally limited from improving the performance in a target task, e.g. , eMCI diagnosis, by the unexpected information loss in transforming an input into hierarchical or compressed representations. In this paper, we propose a novel network architecture that discovers enriched representations of the spatio-temporal patterns in rs-fMRI such that the most compressed or latent representations include the maximal amount of information to recover the original input, but are decomposed into diagnosis-relevant and diagnosis-irrelevant features. In order to learn those favourable representations, we utilize …

In recent years, deep learning (DL) methods have become one of the de-facto standard models for various EEG-based BCI tasks. However, it is well known that DL-based methods tend to be susceptible to hyperparameter settings and thus must be properly fine-tuned to provide reasonable performance. In spite of the importance of hyperparameter tuning, its optimization is often done by naive brute-force search methods that exhaustively evaluate all the possible candidates for each hyperparameter setting. To circumvent this problem, we propose to use population-based evolutionary search methods to solve the hyperparameter optimization problem dynamically and automatically without considerable human intervention. The main advantage of our method is that it only requires a single run of model for tuning process, as evolutionary search keeps track of past evaluation results and leverage this information to …

Molecular discovery has received significant attention across various scientific fields by enabling the creation of novel chemical compounds. In recent years, the majority of studies have approached this process as a multi-objective optimization problem. Despite notable advancements, most methods optimize only up to four molecular objectives and are mainly designed for scenarios with a predetermined number of objectives. However, in real-world applications, the number of molecular objectives can be more than four (many-objective) and additional objectives may be introduced over time (dynamicobjective). To fill this gap, we propose DyMol, the first method designed to tackle the dynamic manyobjective molecular optimization problem by utilizing a novel divide-and-conquer approach combined with a decomposition strategy. Additionally, we comprehensively integrate convergence, Pareto diversity, and structural diversity into the optimization process to provide efficient exploration of the search space. We validate the superior performance of our method using the practical molecular optimization (PMO) benchmark. The source code and supplementary material are available online.

Molecular property prediction has gained substantial attention due to its potential for various bio-chemical applications. Numerous attempts have been made to enhance the performance by combining multiple molecular representations (1D, 2D, and 3D). However, most prior works only merged a limited number of representations or tried to embed multiple representations through a single network without using representation-specific networks. Furthermore, the heterogeneous characteristics of each representation made the fusion more challenging. Addressing these challenges, we introduce the Fusion Transformer for Multiple Molecular Representations (FTMMR) framework. Our strategy employs three distinct representation-specific networks and integrates information from each network using a fusion transformer architecture to generate fused representations. Additionally, we use self-supervised learning …

MAILAB | Medical Artificial Intelligence

교수님 소개

감태의

연구실 소개

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

Adaptive Reward Weighting via Reinforcement Learning for Major Depressive Disorder Diagnosis

Agentic Brain: Agentic AI System for Autonomous Diagnosis of Functional Connectivity Network

Advancing Molecular Structure Elucidation for Mass Spectrum Interpretation via Cepstral Analysis

연구실 보유 특허

대학별 입시끈

우리 연구실 모집

교수님 소개

감태의

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

Adaptive Reward Weighting via Reinforcement Learning for Major Depressive Disorder Diagnosis

Agentic Brain: Agentic AI System for Autonomous Diagnosis of Functional Connectivity Network

Advancing Molecular Structure Elucidation for Mass Spectrum Interpretation via Cepstral Analysis

연구실 보유 특허

최근 3년간 연구실적 높은 연구실

대학별 입시끈

우리 연구실 모집