Skip to main content

Medical-image Analysis and Statistical Interpretation Lab

Resources : Software

Distributed Automation for XNAT

The Vanderbilt University Institute for Imaging Science (VUIIS) Center for Computational Imaging (CCI) has developed a database built on XNAT housing over a quarter of a million scans. The database provides framework for (1) rapid prototyping, (2) large scale batch processing of images and (3) scalable project management. The system uses the web-based interfaces of XNAT and REDCap to allow for graphical interaction. A python middleware layer, the Distributed Automation for XNAT (DAX) package, distributes computation across the Vanderbilt Advanced Computing Center for Research and Education high performance computing center. All software are made available in open source for use in combining portable batch scripting (PBS) grids and XNAT servers.

JIST: Java Image Science Toolkit

Combined Structural and DTI Analysis with CATNAP and CRUISE

Java Image Science Toolkit (JIST) provides a native Java-based imaging processing environment similar to the ITK/VTK paradigm. Initially developed as an extension to MIPAV (CIT, NIH, Bethesda, MD), the JIST processing infrastructure provides automated GUI generation for application plug-ins, graphical layout tools, and command line interfaces.

This repository maintains the current multi-institutional JIST development tree and is recommended for public use and extension. JIST was originally developed at IACL and MedIC (Johns Hopkins University) and is now also supported by MASI (Vanderbilt University).

Covariate-Adjusted Restricted Cubic Spline Regression

screenshotWe propose to use covariate- adjusted restricted cubic spline (C-RCS) regression within a multi-site cross-sectional framework. This model allows for flexible consideration of nonlinear age-associated patterns while accounting for traditional covariates and interaction effects

Citation: Yuankai Huo, Katherine Aboud, Hakmook Kang, Laurie E. Cutting, Bennett A. Landman, “Mapping Lifetime Brain Volumetry with Covariate-Adjusted Restricted Cubic Spline Regression from Cross-sectional Multi-site MRI”. In International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Athens, Greece, October 2016

Augmented Reality Mirror

Screen Shot 2016-11-04 at 8.58.36 PMThe Augmented Reality Mirror is an open source rendering software to provide users with a virtual reality experience. With the provisions of a projection display, a laptop with multi-core GPU, and XBOX kinect, users can stand in front of the mirror and representative anatomical images will overlay the body. The images implemented are adapted to approximate the actual anatomy. The open source software will have an application programming interface (API) to allow users to develop additional content within the Augmented Reality Mirror.

Hadoop for Data Colocation

HSGE As imaging datasets and computing grid sizes grow larger, traditional computing’s separation of data and computational nodes create a problem. Moving data from where it is centrally stored to computational nodes can saturate a network with relatively few active processes. Under certain conditions, the bottleneck in the computing architecture becomes the network bandwidth. An inexpensive solution is to locate the data on the computational nodes to avoid the problem of saturating the network by copying data. This project provides our resources for performing medical image data colocation via Hadoop and Hbase.

Robust Biological Parametric Mapping

Figure 1

Biological parametric mapping (BPM) has extended the widely popular statistical parametric approach to enable application of the general linear model to multiple image modalities (both for regressors and regressands) along with scalar valued observations. This approach offers great promise for direct, voxelwise assessment of structural and functional relationships with multiple imaging modalities. However, as presented, the biological parametric mapping approach is not robust to outliers and may lead to invalid inferences (e.g., artifactual low p-values) due to slight mis-registration or variation in anatomy between subjects. To enable widespread application of this approach, we introduce robust regression and non-parametric regression in the neuroimaging context of application of the general linear model.

Web Game for Collaborative Labeling

WebMill Labeling AppletStatistical atlases of regional brain anatomy have proven to be extremely useful in characterizing the relationship between the structure and function of the human nervous system. Typically, an expert human rater manually examines each slice of a three-dimensional volume. This approach can be exceptionally time and resource intensive, so cost severely limits the clinical studies where subject-specific labeling is feasible. Methods for improved efficiency and reliability of manual labeling would be of immense benefit for clinical investigation into morphological correlates of brain function. The goal of the proposed work is to enable an alternative to expert raters for medical image labeling through statistical analysis of the collaborative efforts of many, minimally-trained raters. The proposed research investigates extension of established practices for volumetric labeling and web- based collaboration to create an innovative infrastructure for labeling.

Continuous Integration Server

The MASI lab runs a publicly readable continuous integration server to support open source development and collaboration, including for the NIH intra-mural MIPAV project. We are currently testing JIST and TOADS-CRUISE against MIPAV-7.X.X.

NeuroDebian

The MASI lab has provided a mirror for the NeuroDebian project since 2010.