Understand Brain
Human brain is something of an enigma. We use data science technology to visualize the dynamic mapping of large-scale collaborative work among millions of neurons through multiple brain regions. Network science offers a new window to understand brain and explore the neurobiological mechanisms.
Computational Anatomy
Develop cutting-edge computational tools to accurately characterize shape of anatomical structures using image analysis, pattern recognition and machine learning techinique.
Presion Medicine
The significant gap between the histological examination and clinical diagnosis suggests that our current symptom based diagnostic criteria do not carve the nature at its joint. We aim to develop personalized diagnosis engine to revolutionize the traditional "one-size-fits-all" approach to the new era of precision medicine.
Computational Biology
We are interested to understand how the variations of the genome change the brain development and structure, with the focus on high throughput computational infrastructure to share, analyze, and visualize the information -dense image datasets in a standard manner, across multiple labs.
Software
The Virtual Reality Brain Network Viewer provides a new and innovative way to interact with brain connectome data. By utilizing the Oculus Rift headset and the Oculus Touch controllers the software allows you to physically interact with your data sets. This includes the ability to pick up the brain model and move it with your hands, as well as the ability to slice open the brain mesh to further examine the nodes and connections within. The software also comes with analysis tools that allow control over the connection threshold, the ability to isolate connections on a given node, and the overlay of MRI data on the brain model.
GLIRT (Groupwise and Longitudinal Image Registration Toolbox) provides solutions for both groupwise registration and longitudinal registration, which are the necessary steps for many brain-related applications.In this software package, we have included two of our recently-developed groupwise registration algorithms: 1) Sharp-Mean registration, and 2) Groupwise-HAMMER; and (3) Groupwise longitudinal registration for longitudinal image sequences.
MARS (Multi-Atlas Robust Segmentation) provides the automatic solutions for efficent segmentation/labeling anatomcial structures from medical images. Specifically, this software has integrated several state-of-the-art multi-atlas based segmentation methods, such as majority voting, local weighted voting, and non-local patch based segmentation methods. Our software is ranked as the top label fusion method in MICCAI 2013 segmenation challenge.
The HAMMER Suite toolkit provides a user-friendly interface for efficient image processing and analysis on human MRI brain images. Image processing is completed by a flexible pipeline which provides fully automatic and powerful functions, such as skull stripping, image cerebellum removal, image segmentation, HAMMER based image registration, and RAVENS map generation for voxel based analysis.
iBEAT (Infant Brain Extraction and Analysis Toolbox, previously called LIBRA) is a toolbox with graphical user interfaces for processing infant brain MR images. Longitudinal (or single-time-point) multimodality (including T1, T2, and FA) (or single-modality) data can be processed using the toolbox. Main functions of the software (step by step) include image preprocessing, brain extraction, tissue segmentation and brain labeling.
aBEAT is a 4D Adult Brain Extraction and Analysis Toolbox with graphical user interfaces to consistently analyze 4D adult brain MR images. Single-time-point images can also be analyzed. Main functions of the software include image preprocessing, 4D brain extraction, 4D tissue segmentation, 4D brain labeling, ROI analysis.