将人工智能（AI）集成到光学成像和后续图像处理中，标志着该领域的重大转变，这主要是为了克服这些技术固有的限制并提升其能力。AI处理大量数据的高性能和速度对于提升图像质量、灵敏度、分辨率和分析准确性至关重要。在生物和医学研究领域，AI具有巨大的变革潜力。然而，存在一些重大挑战，如需要大量高质量数据集来训练AI模型，计算资源需求，以及确保AI生成结果的可解释性和可靠性的挑战。解决这些挑战对于充分发挥AI增强光学成像和图像处理的优势至关重要。我们提出并正在探索新的方法和框架，以克服这些挑战，推进AI在光学成像中的应用，包括（1）新颖的自监督去噪框架，以实现超越散粒噪声极限的超灵敏荧光成像，（2）新的图像超分辨率方法，揭示亚细胞结构和动力学，超越衍射极限，（3）先进的图像分析和重建流程，实现高通量和多维成像中快速高精度的细胞图像分析。这些创新将共同实现前所未有的科学观察，并激发生命科学、神经科学、医学甚至材料科学的新见解。

代表性论文

• Zero-shot learning enables instant denoising and super-resolution in optical fluorescence microscopy, Nature Communications 2024
  

• Self-supervised denoising for multimodal structured illumination microscopy enables long-term super-resolution live-cell imaging, PhotoniX 2024

• Real-time denoising enables high-sensitivity fluorescence time-lapse imaging beyond the shot-noise limit, Nature Biotechnology 2023

• Rationalized deep learning super-resolution microscopy for sustained live imaging of rapid subcellular processes, Nature Biotechnology 2023

• Challenges and opportunities in bioimage analysis, Nature Methods 2023

• Spatial redundancy transformer for self-supervised fluorescence image denoising, Nature Computational Science 2023

• Rapid detection of neurons in widefield calcium imaging datasets after training with synthetic data, Nature Methods 2023

• Virtual-scanning light-field microscopy for robust snapshot high-resolution volumetric imaging, Nature Methods 2023

• Large depth-of-field ultra-compact microscope by progressive optimization and deep learning, Nature Communications 2023

• Bio-friendly long-term subcellular dynamic recording by self-supervised image enhancement microscopy, Nature Methods 2023

• Reinforcing neuron extraction and spike inference in calcium imaging using deep self-supervised denoising, Nature Methods 2021

• Evaluation and development of deep neural networks for image super-resolution in optical microscopy, Nature Methods 2021

• Unsupervised content-preserving transformation for optical microscopy, Light: Science & Applications 2021