top of page
Positron emission tomography(PET)
Positron emission tomography is a functional imaging method. The tracer distribution can be recovered from the measured data by use of a reconstruction algorithm. Furthermore, the pharmacokinetic reaction constants pertinent to physiological metabolisms can be obtained from PET measurement data and a plasma input function. Our team focuses on (i) developing and parallelizing reconstruction algorithms and optimization methods to determine PET images and underlying physiological mechanisms, which are of great importance to both research development and clinical applications, and (ii) developing the MRI compatible PET inserts to enable multi-modality imaging.
Early oral mucosa detection
Using deep learning models for early screening of oral cancer, through object detection and instance segmentation models, to detect oral mucosa features of different grades, and make statistics and evaluations based on the results.
X-ray phase-contrast imaging
Different from conventional computed tomography, which is based on absorption contrast, X-ray phase-contrast imaging techniques can exploit the complex reflective index of an object. It can provide separate images that concurrently depict absorption, reflective and scattering properties. The complementary information given by these images can shed light on the imaged sample and its characteristics. Additionally, the image formation does not require a contrast agent. The fact that phase contrast can persist at higher X-ray energies makes it a promising candidate for low-dose imaging.
bottom of page