Program

Executive Summary：
Chou-Ching K. Lin received a Bachelor degree of Medicine from National Yang-Ming University, Taipei, Taiwan in 1988 and an MSc and PhD in biomedical engineering from Case Western Reserve University, Cleveland, OH, USA in 1994 and 1997, respectively. He is a professor in Department of Neurology and an adjunct professor in Department of Biomedical Engineering, National Cheng Kung University. His areas of interest include functional MRI, brain-computer interface (BCI), electrical stimulation of CNS and PNS, and neural network modelling of natural intelligence and artificial intelligence (AI).

Lecture Abstract：
AI and it’s applications are a fast evolving field with myriad imaginations. In this talk, in the first part, I will introduce Artificial General Intelligence (AGI) first, and then describe the progression from AI to AGI and its current status. In addition, the limitation and new idea about AGI implementation will be discussed. In the second part, I will review and discuss the possible impact of AGI on our clinical practice, especially in the field of Neurology.

Executive Summary：
Dr. Sheng-Fu Liang received his Ph.D. in Electrical and Control Engineering from National Chiao Tung
University (NCTU), Hsinchu, Taiwan, in 2000. He is currently a Professor in the Department of
Computer Science and Information Engineering at National Cheng Kung University (NCKU), Taiwan.
He also serves as the Director of both the Institute of Manufacturing Information and Systems and
the Digital Biomedical Research Center at NCKU.

Dr. Liang previously held the position of Director of the Institute of Medical Informatics (IMI) at NCKU
from 2018 to 2021, and served as Director of the AI Biomedical Research Center under the National
Science and Technology Council, Taiwan, from 2020 to 2022. He was a Specially Appointed Professor
in the Research Institute for Electronic Science, Hokkaido University in 2022.

Dr. Liang’s research interests encompass biomedical instrumentation and measurement, neural
engineering, brain-computer interfaces, medical informatics, and computational intelligence. He is
the co-author of a distinguished technical paper presented at the 2013 IEEE International Solid-State
Circuits Conference (ISSCC), which introduced a System-on-Chip (SoC) for real-time seizure detection
and suppression. In 2020, Dr. Liang led an AI-based research project that developed a Neural
Feedback Training System for Sleep Improvement, which received the National Innovation Award. He
also initiated an international collaboration between NCKU and Hokkaido University, focusing on
innovative technologies for sleep environment enhancement and non-contact sleep assessment from
2018. This work was honored with the Materials and Devices Joint Research Award from the Network
Joint Research Center and Dynamic Alliance, Japan, in 2020.

Lecture Abstract：
Artificial Intelligence (AI) is increasingly being applied in the medical field, with generative AI and large language models (LLMs) offering powerful tools for clinical decision support, medical documentation, and education. Supported by robust computing platforms, automated data collection systems, and expert manpower, the development of these technologies continues to advance rapidly. However, many small hospitals and clinics often lack experienced neurologists and advanced EEG signal analysis systems, leading to potential misinterpretations or delays in manual EEG readings. To address this issue, we present a hybrid AI system that combines deep learning models with LLMs to enable automated EEG background analysis and report generation. This system empowers under-resourced areas to access more equitable and consistent medical care through AI-driven support.

The effectiveness of AI models relies heavily on labeled training data. In cases involving atypical medical data, expert interpretations may vary, making it essential to establish consensus and understand differing opinions. Methods for effectively and efficiently extracting expert perspectives can improve model training and diagnostic accuracy. In this presentation, we will introduce a cloud-based training course designed for sleep technicians across Taiwan. This program leverages remote learning to provide interpretation training, detailed feedback, weakness analysis, and post-test verification. It aims to improve the consistency of polysomnography (PSG) interpretation among sleep technicians nationwide. By overcoming geographic limitations, this distance education initiative ensures equal access to training resources. It also fosters collaborative learning among experts, broadens the scope of data available for AI model development, and enhances the AI’s ability to interpret atypical cases. This talk will highlight the role of AI in reducing healthcare disparities, advancing medical education, and supporting clinical excellence through collaborative innovation.

Executive Summary：
Dr. Tsung-Lin Lee (李宗霖) is an Attending Neurologist at the Department of Neurology, National Cheng Kung University Hospital (NCKUH), Tainan, Taiwan, and a PhD candidate in Biomedical Engineering at NCKU. He earned his M.D. from China Medical University and completed comprehensive neurological training at NCKUH, including residency, fellowship, and dual attending appointments at both Tainan and Douliu divisions

Dr. Lee’s clinical expertise focuses on Parkinson’s disease and movement disorders, with particular proficiency in deep brain stimulation (DBS), botulinum toxin therapy for movement disorders and post-stroke spasticity management. He has further honed his skills through specialized traineeships at leading movement disorder centers in Taiwan and France, including Grenoble University Hospital

As an clinician-scientist, Dr. Lee has published in peer-reviewed journals on topics ranging from advanced therapies in Parkinson’s disease to artificial neural network applications in neuroimaging. He has also contributed to national consensus guidelines for Parkinson’s disease treatment in Taiwan.

Dr. Lee remains committed to advancing precision care and neuromodulation strategies for patients with movement disorders, while continuing to learn and collaborate with bioengineering field to improve patient outcomes.

Lecture Abstract：
Artificial intelligence (AI) is rapidly transforming clinical neurology and neurophysiology, offering new tools for diagnosis, monitoring, and therapeutic decision-making. In movement disorders such as Parkinson’s disease, AI-driven algorithms have demonstrated the ability to analyze complex neurophysiological signals—ranging from EEG and EMG to local field potentials—far beyond the resolution of conventional methods. Deep learning models can assist in differentiating Parkinson’s disease from atypical parkinsonism using imaging data, automate detection of abnormal motor patterns in gait analysis, and optimize deep brain stimulation (DBS) parameters through real-time signal adaptation.

This talk will highlight the current applications and future potential of AI in neurophysiology, with particular emphasis on areas relevant to clinical neurology. Key examples include machine learning approaches for early detection of neurodegenerative disorders, AI-assisted interpretation of electromyography and nerve conduction studies, and predictive modeling of treatment response in DBS and botulinum toxin therapy. The integration of AI with biomedical engineering—such as wearable sensors and brain–computer interfaces—further expands opportunities for precision medicine, enabling continuous monitoring and individualized therapy.

Executive Summary：
Dr. Chien graduated from National Cheng Kung University in 2009 and completed his neurology residency at National Cheng Kung University Hospital in Tainan, Taiwan, from 2010 to 2014. He served as an Attending Physician at the Dou-Liou Branch of the hospital from 2014 to 2016 and has been an Attending Physician at the main hospital since 2016. In parallel, Dr. Chien pursued a PhD in Biomedical Engineering at National Cheng Kung University (2015–2023), focusing on biomedical signal processing, digital image processing, and machine learning. His research earned him the opportunity to deliver an oral presentation at the 2023 MDS Congress, where he discussed the application of machine learning in fMRI studies of Parkinson’s disease. Recently, he was promoted to Assistant Professor in the Department of Neurology at the College of Medicine, National Cheng Kung University (2025).
Dr. Chien’s clinical and research interests center on integrating biomedical engineering techniques to enhance the diagnosis and treatment of parkinsonian disorders. His work spans structural and functional neuroimaging studies of movement disorders, the biophysiology of auditory perception, and therapeutic strategies for Parkinson’s disease. He has also contributed to innovative projects focused on digital sensing and cueing devices for Parkinson’s disease, merging biological and digital approaches to advance the understanding and management of neurological disorders.

Lecture Abstract：
Neuroimaging has played a central role in the study of movement disorders, particularly for clinical applications such as differential diagnosis and monitoring disease progression. However, traditional analysis methods often fall short in addressing unmet clinical needs and fully elucidating the underlying pathophysiology. The integration of artificial intelligence (AI) offers a transformative approach, bringing advanced computational techniques and powerful data mining capabilities to better harness neuroimaging data.
In Parkinson’s disease (PD) and atypical parkinsonian disorders—each with distinct pathological signatures—AI holds promise for improving early differential diagnosis. While structural imaging can reveal regional atrophy patterns associated with different disorders, these changes often emerge only in later stages. Recent machine learning approaches have demonstrated success in distinguishing PD from atypical parkinsonian syndromes by identifying subtle patterns in regional brain volume and diffusivity metrics. Traditional dopamine transporter imaging has been limited in differentiating these disorders, but AI-based analysis of extracted imaging features has enabled more accurate classification.
As PD progresses, neuroimaging can predict both motor and non-motor symptoms. Functional imaging modalities such as fMRI reveal complex, non-linear alterations in brain activity, which AI algorithms can detect and interpret more effectively than conventional methods. Additionally, techniques like EEG and MEG, which offer superior temporal resolution, are being leveraged with AI to extract early functional biomarkers from multichannel time-series data—potentially preceding structural changes.
The interpretability of AI not only enhances diagnostic precision but also contributes to a deeper understanding of disease mechanisms, supporting the development of personalized and precision medicine strategies. By combining neuroimaging with AI and big data analytics, clinical applications and individualized healthcare for movement disorders can be significantly advanced.

Executive Summary：
Prof. Ching-Po Lin is a tenured Distinguished Professor at the Institute of Neuroscience and Deputy Dean of General Affairs at National Yang Ming Chiao Tung University. He also serves as Chief of the Education and Research Department and Executive Secretary of the Smart Health Office at Taipei City Hospital in Taiwan. With over 20 years of experience advancing neuroimaging, Prof. Lin specializes in developing innovative methodologies for mapping the human brain connectome and understanding how it underpins behavior in both healthy and diseased states. By integrating large datasets and AI technologies, he also seeks to optimize treatment strategies and identify early features of aging-associated brain diseases. Recently, he has incorporated modern imaging innovations to assist with neurosurgical planning, navigation, and prognosis. To date, he has secured more than 13 innovation patents and authored over 300 open-access journal papers, with more than 20,000 citations (H-index = 64).

Lecture Abstract：
The human connectome represents the complex wiring of the brain, providing a systems-level framework for understanding how structural and functional networks shape cognition and behavior. Recent advances in neuroimaging and computational neuroscience have transformed our ability to characterize these networks with unprecedented detail. By leveraging multimodal MRI techniques and state-of-the-art AI methodologies, researchers are now capable of extracting sensitive biomarkers of brain aging and health from the connectome.
This presentation will focus on the integration of connectomics with intelligent predictive modeling, highlighting how individualized brain age estimation can serve as a robust indicator of cognitive health and resilience. We will examine cutting-edge approaches that employ machine learning to decode large-scale MRI datasets, linking network-level features to individualized measures of brain function, aging, and disease risk.
Beyond technical advances, we will discuss the clinical and translational implications of intelligent connectomics. These include early detection of neurodegenerative disorders, monitoring of therapeutic efficacy, and the design of precision healthcare strategies tailored to each individual’s unique brain network profile. By combining neuroimaging, AI, and smart healthcare, this emerging paradigm moves us closer to proactive, individualized brain health management and the promotion of healthy aging.

Executive Summary：
Dr. Wei-Chun Wang completed comprehensive neurology specialty training at China Medical University Hospital. His expertise includes cerebrovascular diseases and stroke, and he is certified in acute ischemic stroke thrombectomy and neurological critical care. He pursued advanced studies in artificial intelligence technology and medical image analysis at the National Institutes of Health (NIH) in the United States. Beyond clinical care, he is dedicated to applying artificial intelligence technology to the field of neurology, particularly in clinical symptom recognition, brain image analysis, and physiological signal analysis. He currently serves as the Deputy Director of the Artificial Intelligence and Robotics Innovation Center at China Medical University Hospital, combining clinical knowledge with AI technology to enhance the application of AI in clinical medicine.

Lecture Abstract：
Stroke remains a leading cause of death and disability worldwide, where time-sensitive diagnosis and accurate prognostic prediction are critical for optimal patient outcomes. Artificial intelligence (AI) technologies have emerged as transformative tools in stroke medicine, revolutionizing our approach to early detection, treatment decisions, and prognostic assessment.
For ischemic stroke diagnosis, AI can rapidly and accurately identify early lesions on non-contrast computed tomography (CT) scans. By incorporating prior anatomical knowledge into model design, the performance of these detection systems can be further optimized. For hemorrhagic stroke, AI automatically performs hematoma segmentation on CT images. In addition to diagnosis, this AI-derived imaging information can be leveraged for advanced analyses. For instance, analyzing the radiomics features of the segmented hematoma allows us to explore the correlations between these imaging biomarkers and a patient's clinical symptoms or prognosis.
In prognostic assessment, advanced machine learning (ML) models integrate multi-dimensional data—including imaging findings, clinical history, and laboratory results—to develop comprehensive predictive frameworks. These models assist clinicians in evaluating a patient's recovery potential and risks.
Overall, the application of AI in stroke care is evolving from single-task image interpretation to comprehensive decision support. This comprehensive integrated approach not only significantly enhances diagnostic efficiency but also provides powerful support for personalized treatment strategies and prognostic management.