Huafeng Liu

This paper introduces DeepIso, a self-supervised framework that enhances isotropic resolution in 3D fluorescence microscopy by restoring axial frequency content without requiring explicit PSF models or system calibration.

SIRP improves fluorescence microscopy image denoising by using self-supervised learning and implicit neural representations to preserve fine details under low SNR conditions.

This paper introduces an algorithm to reconstruct 3D molecular orientation and density from polarized fluorescence microscopy data, demonstrating its application on biological structures and dynamics.

HD2Net improves fluorescence microscopy image quality by simultaneously denoising and correcting aberrations without additional hardware, outperforming existing methods in resolution and contrast.

This paper introduces RO-iSCAT, a technique that enables real-time, label-free tracking of membrane protrusions with high axial resolution and minimal phototoxicity.

The paper introduces a polarized dual-view light-sheet microscope to recover 3D orientations and positions of fluorescent dipoles, validated with experiments on biological samples.

This paper introduces a deep learning method to correct optical aberrations in fluorescence microscopy, improving image quality and enabling better downstream analysis.

This study shows acupuncture at specific acupoints accelerates recovery from ischemic stroke in rats compared to sham needling, with effects observed in motor control regions.

This paper introduces a regression-based method for analyzing FDG-PET images without intensity normalization, showing improved sensitivity in detecting stroke injury regions compared to existing methods.

The paper introduces a feature-based method using FDG PET images and SVM to assess MCAO quality in rats, achieving high accuracy in classification.