Research focuses in computational algorithms of quantitative analysis of medical images of various modalities, both in vivo and ex vivo, for disease analysis, diagnosis and quantification. Modalities include computed tomography, magnetic resonance imaging and histology. Specially interested in building analysis pipeline of serial CT volumetric images for registration, segmentation and analysis of pulmonary kinematics. Research also includes reconstruction of serial histology 2D slices into 3D space and normalization with volumetric atlas.
- Feature Selection for Characterization of ILD and COPD
The performance of various image-based metrics computed from thoracic HRCT modality were compared with data from pulmonary function testing (PFT) in characterizing interstitial lung disease (ILD) and chronic obstructive pulmonary disease (COPD). Results showed that some image metrics are not only as good discriminators as PFT for characterization of ILD and COPD, but also not redundant when PFT values are provided.
- picsl-gsyn in EMPRIE10 Challenge of Lung Image Registration
EMPIRE10 is an international competition on CT lung image registration. We currently keep ranking 1st (check most recent rankings here) out of 36 competing algorithms. We used ANTs as the registration algorithm in the competition.
- May 2006 – Aug 2013 PhD in Computer and Information Science, University of Pennsylvania, Philadelphia, PA
- June 2004 – May 2006 MS. in Computer and Information Science, University of Pennsylvania, Philadelphia, PA
- Sep. 2001 – Jan. 2004 MS in Computer Science and Technology, Tsinghua University, Beijing, China
- Sep. 1997 – June 2001 BE in Computer Science and Technology, Tsinghua University, Beijing, China