Xin Chen
Associate Professor of Computer Science, Faculty of Science
Contact
Research Summary
Dr Xin Chen's research interests are in the areas of image processing, computer vision and machine learning, particularly applied to medical image analysis.
One primary area of Dr Chen's research is motion analysis in radiology imaging. He developed techniques to construct statistical shape and motion models of bones in articulated joint from CT images. These generic population-based models were then deployed to estimate individual patient positioning in radiotherapy and to detect abnormalities in wrist based on 2-D radiographs using 3-D to 2-D image registration techniques. Besides working on motion estimation, he also established expertise in respiratory motion correction in MRI.
Another area of Dr Chen's research is to apply machine learning (recently deep learning) methods for medical image segmentation and disease biomarkers quantification. He developed an automatic nerve fibre segmentation and quantification tool which enabled early detection of peripheral neuropathy for diabetic patients using corneal confocal microscopic images. Moreover, a similar machine learning framework was developed for automatic segmentation of fat, glandular tissue, pectoral muscle and nipple in breast mammograms, which further led to the automatic estimation of 3-D volumetric breast density based on a single 2-D digital mammogram.
Dr Chen is always open to new research areas and keen to explore exciting applications using computer vision and machine learning (deep learning) methods.