Welcome Welcome

 HP-MICCAI / MICCAI-DCI 2011, The Joint Workshop on High Performance and Distributed Computing for Medical Imaging, featured at MICCAI 2011, will be held at September 22nd 2011 in Toronto, Canada.

Final Programme Final Programme

We proudly present the final programme of the HP-MICCAI/MICCAI-DCI 2011 workshop.

Two keynotes are given:

Alan C. Evans  shows how to use distributed environments for Neuroimaging, and Joel Saltz presents solutions for large-scale pathological data analysis.

The oral presentations and poster session encompass latest research on a wide range of medical imaging areas and computer systems. Find the full programme below. For full information about authors and session chairs please see PDF

 We are looking forward to see you in Toronto!

 

HP-MICCAI/MICCAI DCI Workshop 2011, Thursday, 22. September 2011, 9:00h - 17:00h
 Time  Agenda Item  Title  Presenter
 9:00 Opening Remarks Dagmar Krefting
 9:15 KeynoteCBRAIN: A network-enabled platform for HPC in brain researchAlan Evans
 10:00 Oral SessionThe Analysis of Image Texture Feature Robustness Using CometCloudXin Qi
 10:30 Coffee Break  
 10:45
 
 Oral Session
 
Reliability of quantitative neuroimage analysis using FreeSurfer in distributed environmentsDagmar Krefting
High Throughput Landmark Based Image Registration Using Cloud ComputingLin Yang
11:45 Lunch BreakLunch will be provided to all the attendees by the organizers 
13:00KeynoteTowards Exascale Pathology Data AnalyticsJoel Saltz
 13:45
 
 
 Oral Session
 
 
Improving CCA based fMRI Analysis by Covariance Pooling -Using the GPU for Statistical InferenceAnders Eklund
High Performance Analytical Pathology Imaging Database for Algorithm EvaluationFusheng Wang
Fast Surface Extraction and Visualization of Medical Images using OpenCL and GPUsErik Smistad
15:15
 
 
 
 
 
Poster Session with Coffee
 
 
 
 
 
Phase-Based Non-Rigid 3D Image Registration: From Minutes to Seconds Using CUDADaniel Forsberg
Boss/Worker Model for Multi-GPU ProgrammingStefano Pedemonte
Soma-workflow: an unified and simple interface to parallel computing resourcesSoizic Laguitton
The MIDAS Pipeline: A distributed local framework for medical image processingNestor Andres Parra
Comprehensive Web-Based Patient Data Collection Systems with Integrated Imaging FunctionalityAli Hamou
Enabling high-throughput feature generation and analysisPatrick Widener
16:35Closing Remarks and Panel Discussion David Foran

 

 The programme may change due to unexpected incidents.

Topics Topics

The list of topics addressed by this workshop includes, but is not limited to:

  •     Parallel medical image processing using multi-core/multiprocessors, GPUs, Grids or Clouds
  •     Medical image analysis pipelines and workflows employing HPC or DCIs, including
    • Segmentation
    • Registration
    • Reconstruction
    • Rendering
    • Visualization
  •     Content-based retrieval and data mining
  •     Distributed, heterogeneous medical databases
  •     Applications using HPC or DCIs, for example
    •     High throughput image screening
    •     High resolution imaging
    •     Multi-scale and multi modal imaging
    •     Image analysis in clinical trials
    •     Development of new imaging methods
    •     Evaluation of medical imaging algorithms
  •     Dedicated distributed infrastructures and HPC systems
  •     Interoperability for exchanging data, algorithms and analysis pipelines
  •     Imaging and data exchange standards and tools
  •     Success stories and show stoppers
Introduction Introduction

The proliferation and increased reliance on high-resolution, multimodality biomedical images/videos present significant challenges for a broad spectrum of clinical practitioners and investigators throughout the clinical and research communities. A growing spectrum of new and improved imaging modalities and new image processing techniques can significantly affect diagnostic and prognostic accuracy and facilitates progress in the areas of biomedical research and discovery. However, the impact of these new technologies in both time-critical clinical applications and high-throughput research pursuits depends, in large part, on the speed and reliability with which the imaging data can be visualized, analyzed and interpreted. Conventional serial computation is grossly inadequate and inefficient for managing  these increasing amounts of data and the employment of the new advances in medical imaging is often limited by insufficient compute and storage resources.  

 

High-performance computing (HPC) such as multicore/multiprocessor and GPU-based processing, and distributed computing infrastructures (DCIs) such as Grids and Clouds are effective approaches for overcoming such limitations. They allow for significant reduction of computational time for running large experiments and speed-up the development time for new algorithms while increasing the availability of new methods for the research community, and supporting large-scale multi-centric collaborations.

The workshop will build on existing collaborative efforts in understanding current trends in HPC/DCI medical imaging research. It will demonstrate and encourage open discussion regarding the current status and latest developments in the field; explore new ideas/motifs and identify the challenges which currently impeded wider adoption of these technologies in image-assisted translational research, clinical intervention and decision-making.

The workshop addresses researchers who are already employing HPC/DCI techniques, as well as scientists who are developing data- and compute-intensive imaging applications including multi-data studies, large-scale parameter scans or complex analysis pipelines.

Links to former Workshops Links to former Workshops

HP-MICCAI/MICCAI-DCI 2011 seeks to expand the success of the HP-MICCAI and MICCAI-GRID workshops through MICCAI 2008-2010. Information about the former workshops can be found on the respective sites: