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.
- "Deep Learning in Medical Image Analysis”, Annual Review of Biomedical Engineering, 2016. [Dinggang Shen, Guorong Wu, Heung-Il Suk]
- "Robust Multi-Atlas Label Propagation by Deep Sparse Representation”, Pattern Recognition, 2016. [Chen Zu, Zhengxia Wang, Daoqiang Zhang, Peipeng Liang, Yonghong Shi, Dinggang Shen*, Guorong Wu*] *Co-corresponding authors
- "Reduced Cortical Thickness and Increased Surface Area in Antisocial Personality Disorder”, Neuroscience, 2016. [Weixiong Jiang, Gang Li, Huasheng Liu, Feng Shi, Tao Wang, Celina Shen, Hui Shen, Seong-Whan Lee, Dewen Hu, Wei Wang, Dinggang Shen]
- "Feature Fusion via Hierarchical Supervised Local CCA for Diagnosis of Autism Spectrum Disorder”, Brain Imaging and Behavior, 2016. [Feng Zhao, Lishan Qiao, Pew-Thian Yap, Dinggang Shen]
- "Learning-based 3T Brain MRI Segmentation with Guidance from 7T MRI Labeling”, Medical Physics, 2016. [Minghui Deng, Renping Yu, Li Wang, Feng Shi, Pew-Thian Yap, Dinggang Shen]