Imaging Theory
Monte Carlo Simulation
Monte Carlo (MC) method, one of the most popular numerical tools used in biophotonics, has long been acknowledged as the gold standard for theoretically investigating the light-tissue interaction.
We present our latest advances in the MC-based studies of Optical Coherence Tomography (OCT) including the image formation theory, spectroscopic OCT, wavelength-dependent scattering, and some inverse problems.
Medical Image Processing
Retina Segmentation
Segmenting the stratified structure of human retina is of great significance in clinical settings for disease diagnosis and preventions.
We devised a technique to incorporate the established medical domain knowledge into our segmentation algorithm with the aid of a graph convolutional network.
Medical Image Processing
Shadow Inpainting
Removing shadows cast by blood vessels in retinal optical coherence tomography (OCT) images is critical for accurate and robust machine analysis and clinical diagnosis.
We proposed a multi-scale sparse representation-based method with the aid of a super resolution network for shadow removal in OCT images.