Research Scope

The research of our lab is in Biomedical AI, which lies in the interdisciplinary areas of machine learning, computer vision, signal and image processing, medical image analysis, biomedical imaging, and data science.

• In the filed of AI/ML, we focus on developing reliable, generalizable, data-efficient machine learning and deep learning algorithms by exploiting prior knowledge from the physical world, such as:
  • Prior-integrated learning for data-efficient ML
  • Uncertainty awareness for trustworthy ML
• In the field of Biomedicine, we focus on developing efficient computational methods for biomedical imaging and biomedical data analysis to advance precision medicine and personalized treatment, such as:
  • Multi-modal data analysis for decision making
  • Clinical trial translation for real-world deployment

Research Goal

Our goal is to develop efficient and reliable AI/ML-driven computational methods for biomedical imaging and informatics to tackle real-world biomedicine and healthcare problems. We hope the technology advancement in AI and ML can help us to better understand human health in different levels.

• Across the application dimension, we deploy Biomedical AI in different levels, including:
  • AI for Human:
    • To understand human behavior through image recognition, contributing to patients’ healthcare
  • AI for Doctor:
    • To visualize internal anatomic structure of living subjects through medical imaging techniques (e.g. X-ray, CT, MRI, PET etc.), contributing to precise diagnosis and treatment
  • AI for Science:
    • To investigate biological structures and functions in molecular / organelle / cellular level through microscopy imaging such as cryo-EM, contributing to scientific discovery
• Across the data pipeline dimension, we develop Biomedical AI in different parts, including:
  • AI in Biomedical Imaging: develop novel machine learning algorithms to advance biomedical imaging techniques for obtaining computational images with improved quality. Specifically, relevant topics include but not limited to:
    • Implicit neural representation learning
      • NeRP: Implicit Neural Representation Learning with Prior Embedding for Sparsely Sampled Image Reconstruction, TNNLS 2022
    • Diffusion model / Score-based generative model
      • Solving Inverse Problems in Medical Imaging with Score-Based Generative Models, ICLR 2022
      • Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency, arXiv 2023
    • Physics-aware / Geometry-informed deep learning
      • Novel-View X-ray Projection Synthesis through Geometry-Integrated Deep Learning, MedIA 2021
      • A Geometry-Informed Deep Learning Framework for Ultra-Sparse Computed Tomography (CT) Imaging, CIBM 2022
      • Real Time Volumetric MRI for 3D Motion Tracking via Geometry-Informed Deep Learning, Medical Physics 2022
  • AI in Biomedical Image Processing and Bioinformatics: develop robust and efficient machine learning algorithms to extract useful information from multimodal biomedical data for assisting decision making and precision medicine. Specifically, relevant topics include but not limited to:
    • Multimodal representation learning
      • GLoRIA: A Multimodal Global-Local Representation Learning Framework for Label-efficient Medical Image Recognition, ICCV 2021
    • Robust learning with missing data / noisy labeling
      • Multi-Domain Image Completion for Random Missing Input Data, TMI 2020
    • Data-efficient learning such as self- / un- / semi-supervised learning with limited data / labels
      • Scaling Human-Object Interaction Recognition through Zero-Shot Learning, WACV 2018