Efficient and Extensible Workflow: Reliable Whole Brain Segmentation for Large-Scale, Multi-center Longitudinal Human MRI Analysis Using High Performance/Throughput Computing Resources

Advances in medical image applications have led to mounting expectations in regard to their impact on neuroscience studies. In light of this fact, a comprehensive application is needed to move neuroimaging data into clinical research discoveries in a way that maximizes collected data utilization and minimizes the development costs. We introduce BRAINS AutoWorkup, a Nipype based open source MRI analysis application distributed with BRAINSTools suite (http://brainsia.github.io/BRAINSTools/). This work describes the use of efficient and extensible automated brain MRI analysis workflow for large-scale multi-center longitudinal studies. We first explain benefits of our extensible workflow development using Nipype, including fast integration and validation of recently introduced tools with heterogeneous software infrastructures. Based on this workflow development, we also discuss our recent advancements to the workflow for reliable and accurate analysis of multi-center longitudinal data. In addition to Nipype providing a unified workflow, its support for High Performance Computing (HPC) resources leads to a further increased time efficiency of our workflow. We show our success on a few selected large-scale studies, and discuss future direction of this translation research in medical imaging applications.

[1]  Eun Young Kim,et al.  Robust multi-site MR data processing: iterative optimization of bias correction, tissue classification, and registration , 2013, Front. Neuroinform..

[2]  Shie Mannor,et al.  Weak Learners and Improved Rates of Convergence in Boosting , 2000, NIPS.

[3]  Stephanie Powell,et al.  Registration and machine learning-based automated segmentation of subcortical and cerebellar brain structures , 2008, NeuroImage.

[4]  Hans J. Johnson,et al.  Preliminary analysis using multi-atlas labeling algorithms for tracing longitudinal change , 2015, Front. Neurosci..

[5]  Dawei Liu,et al.  Stable Atlas-based Mapped Prior (STAMP) machine-learning segmentation for multicenter large-scale MRI data. , 2014, Magnetic resonance imaging.

[6]  James Kozloski,et al.  Self-referential forces are sufficient to explain different dendritic morphologies , 2013, Front. Neuroinform..

[7]  Carl-Fredrik Westin,et al.  Efficient and robust nonlocal means denoising of MR data based on salient features matching , 2012, Comput. Methods Programs Biomed..

[8]  N C Andreasen,et al.  Image processing for the study of brain structure and function: problems and programs. , 1992, The Journal of neuropsychiatry and clinical neurosciences.

[9]  Brian B. Avants,et al.  Evaluation of Registration Methods on Thoracic CT: The EMPIRE10 Challenge , 2011, IEEE Transactions on Medical Imaging.

[10]  Hans J. Johnson,et al.  Development of a novel constellation based landmark detection algorithm , 2013, Medical Imaging.

[11]  Ronald Pierson,et al.  Fully automated analysis using BRAINS: AutoWorkup , 2011, NeuroImage.

[12]  Satrajit S. Ghosh,et al.  Nipype: A Flexible, Lightweight and Extensible Neuroimaging Data Processing Framework in Python , 2011, Front. Neuroinform..

[13]  Hans J. Johnson,et al.  Automated brain segmentation using neural networks , 2006, SPIE Medical Imaging.

[14]  Arno Klein,et al.  Evaluation of 14 nonlinear deformation algorithms applied to human brain MRI registration , 2009, NeuroImage.