Hi, I’m Kunzi, a PhD student working in deep learning for medical image analysis.
My research focuses on medical image segmentation, image registration, and microscopy image analysis, particularly in histopathology and electron microscopy. I am interested in developing robust and efficient models that can reduce annotation requirements, improve generalisation, and support high-resolution biomedical imaging.
My work explores weakly supervised learning, domain-aware regularisation, and transformer-based architectures to enhance segmentation and registration performance under challenging imaging conditions. I aim to design methods that are both computationally practical and clinically meaningful.
Previously, I completed research projects in automated microscopy image analysis, focusing on noise-robust nuclei segmentation and weakly supervised label utilisation.
Some of my research topics are listed below. If you are interested in any of these areas, I would be happy to discuss further.
My publications and outputs can be found on my Google Scholar and GitHub pages.
Interests