UNC IDEA group consists of the IDEA Lab in the Department of Radiology and the Image Analysis Core Lab in the Biomedical Research Imaging Center (BRIC). The IDEA lab is devoted to the development of novel image analysis methods and tools, and their applications to various clinical research and trials. The developed methods include deformable registration (HAMMER), deformable segmentation (AFDM), and multivariate pattern classification algorithms. These methods have been applied to various studies on brain diseases and development (including MCI, AD, Schizophrenia, and Neonate Development Study), heart, breast cancer, and prostate cancer. The image analysis core in BRIC supports the image storage and analysis needs of scientists in UNC. It also provides services for brain structural and functional analysis, small animal imaging analysis, visualization, and others.
- "Canonical Feature Selection for Joint Regression and Multi-class Identification in Alzheimer's Disease Diagnosis", Brain Imaging and Behavior, 2015. [Xiaofeng Zhu, Heung-Il Suk, Seong-Whan Lee, Dinggang Shen]
- "Locally-constrained Boundary Regression for Segmentation of Prostate and Rectum in the Planning CT Images”, Medical Image Analysis, 2015. [Yeqin Shao, Yaozong Gao, Xin Yang, Dinggang Shen]
- "A Transversal Approach for Patch-based Label Fusion via Matrix Completion”, Medical Image Analysis, 2015. [Gerard Sanroma, Guorong Wu, Yaozong Gao, Kim-Han Thung, Yanrong Guo, Dinggang Shen]
- "Hierarchical and Symmetric Infant Image Registration by Robust Longitudinal-Example-Guided Correspondence Detection”, Medical Physics, 2015. [Yao Wu, Guorong Wu, Li Wang, Brent C. Munsell, Qian Wang, Weili Lin, Qianjin Feng, Wufan Chen, Dinggang Shen]
- "Sparse Temporally Dynamic Resting-State Functional Connectivity Networks for Early MCI Identification", Brain Imaging and Behavior, 2015. [Chong-Yaw Wee, Sen Yang, Pew-Thian Yap, Dinggang Shen]