Skip to main content

Selected Publications


Analyzing Generative AI and Machine Learning in Auto-Assessing Schizophrenia's Negative Symptoms.

Journal Article Schizophrenia bulletin · August 2025 Background and hypothesisTraditional assessments of schizophrenia's negative symptoms rely on subjective and time-consuming psychiatric interviews. To provide more objective and efficient evaluations, this study examines the efficacy of an automat ... Full text Cite

Every Pixel Has Its Moments: Ultra-High-Resolution Unpaired Image-to-Image Translation via Dense Normalization

Chapter · January 1, 2025 Recent advancements in ultra-high-resolution unpaired image-to-image translation have aimed to mitigate the constraints imposed by limited GPU memory through patch-wise inference. Nonetheless, existing methods often compromise between the reduction of noti ... Full text Open Access Cite

Pathological Gait Analysis With an Open-Source Cloud-Enabled Platform Empowered by Semi-Supervised Learning-PathoOpenGait.

Journal Article IEEE journal of biomedical and health informatics · February 2024 We present PathoOpenGait, a cloud-based platform for comprehensive gait analysis. Gait assessment is crucial in neurodegenerative diseases such as Parkinson's and multiple system atrophy, yet current techniques are neither affordable nor efficient. PathoOp ... Full text Cite

FastEval Parkinsonism: an instant deep learning-assisted video-based online system for Parkinsonian motor symptom evaluation.

Journal Article NPJ digital medicine · February 2024 The Motor Disorder Society's Unified Parkinson's Disease Rating Scale (MDS-UPDRS) is designed to assess bradykinesia, the cardinal symptoms of Parkinson's disease (PD). However, it cannot capture the all-day variability of bradykinesia outside the clinical ... Full text Cite

Ultra-High-Resolution Unpaired Stain Transformation via Kernelized Instance Normalization

Chapter · January 1, 2022 While hematoxylin and eosin (H &E) is a standard staining procedure, immunohistochemistry (IHC) staining further serves as a diagnostic and prognostic method. However, acquiring special staining results requires substantial costs. Hence, we proposed a stra ... Full text Open Access Cite

PanGPCR: predictions for multiple targets, repurposing and side effects.

Journal Article Bioinformatics (Oxford, England) · May 2021 SummaryDrug discovery targeting G protein-coupled receptors (GPCRs), the largest known class of therapeutic targets, is challenging. To facilitate the rapid discovery and development of GPCR drugs, we built a system, PanGPCR, to predict multiple p ... Full text Cite