Advances in computer hard- and software have enabled the automated extraction of biomarkers from large scale imaging studies by means of image processing pipelines. For large cohort studies, ample storage- and computing resources are required: pipelines are typically executed in parallel on one or more High Performance Computing Clusters (HPC). As processing is distributed, it becomes more cumbersome to obtain detailed progress and status information of large-scale experiments. Especially in a research-oriented environment, where image processing pipelines are often in an experimental stage, debugging is a crucial part of the development process that relies heavily on a tight collaboration between pipeline developers and clinical researchers. Debugging a running pipeline is a challenging and time-consuming process for seasoned pipeline developers, and nearly impossible for clinical researchers, often involving parsing of complex logging systems and text files, and requires special knowledge of the HPC environment. In this paper, we present the Pipeline Inspection and Monitoring web application (PIM). The goal of PIM is to make it more straightforward and less time-consuming to inspect complex, long running image processing pipelines, irrespective of the level of technical expertise and the workflow engine. PIM provides an interactive, visualization-based web application to intuitively track progress, view pipeline structure and debug running image processing pipelines. The level of detail is fully customizable, supporting a wide variety of tasks (e.g. quick inspection and thorough debugging) and thereby facilitating both clinical researchers and pipeline developers in monitoring and debugging.
The cohort size required in epidemiological imaging genetics studies often mandates the pooling of data from multiple hospitals. Patient data, however, is subject to strict privacy protection regimes, and physical data storage may be legally restricted to a hospital network. To enable biomarker discovery, fast data access and interactive data exploration must be combined with high-performance computing resources, while respecting privacy regulations. We present a system using fast and inherently secure light-paths to access distributed data, thereby obviating the need for a central data repository. A secure private cloud computing framework facilitates interactive, computationally intensive exploration of this geographically distributed, privacy sensitive data. As a proof of concept, MRI brain imaging data hosted at two remote sites were processed in response to a user command at a third site. The system was able to automatically start virtual machines, run a selected processing pipeline and write results to a user accessible database, while keeping data locally stored in the hospitals. Individual tasks took approximately 50% longer compared to a locally hosted blade server but the cloud infrastructure reduced the total elapsed time by a factor of 40 using 70 virtual machines in the cloud. We demonstrated that the combination light-path and private cloud is a viable means of building an analysis infrastructure for secure data analysis. The system requires further work in the areas of error handling, load balancing and secure support of multiple users.
Neurological pathologies are often reflected in brain magnetic resonance images as abnormal global or local anatomical
changes. These variations can be computed using non-rigid registration and summarized using Jacobian determinant
maps of the resulting deformation field, which characterise local volume changes. We propose a new approach which
exploits the information contained in Jacobian determinant maps of the whole brain in Alzheimer’s disease (AD)
classification by means of texture analysis. Textural features were derived from whole-brain Jacobian determinant maps
based on 3D Grey Level Co-occurrence Matrix. The large number of features obtained depicts anatomical variations at
different resolution, allowing retaining both global and local information. Principle component analysis was applied for
feature reduction such that 95% of the data variance was retained. Classification was performed using a linear support
vector machine. We evaluated our approach using a bootstrapping procedure in which 92 subjects were randomly split
into separate training and testing sets. For comparison purposes, we implemented two dissimilarity-based classification
approaches, one based on pairwise registration and the other based on registration to a single template. Our new
approach significantly outperformed the other approaches. The results of this study showed that pairwise registration did
not bring added value compared to registration to a single template and textural features were more informative than
dissimilarity-based features. This study demonstrates the potential of texture analysis on whole brain Jacobian
determinant map for diagnosis of AD subjects.