Grid computing has been found to be well suited to the computational demands of medical imaging, particularly computer-aided detection. Researchers are especially intrigued by the possibility of using CAD software programs from different vendors in a cooperative manner to enhance the performance and accuracy of nodule detection.
Grid computing has been found to be well suited to the computational demands of medical imaging, particularly computer-aided detection. Researchers are especially intrigued by the possibility of using CAD software programs from different vendors in a cooperative manner to enhance the performance and accuracy of nodule detection.
Ohio State University recently announced the development of gridCAD (Radiographics 2007;27[3]:889 897), a software application that integrates CAD programs from different vendors into a grid framework, thereby creating an infrastructure that allows multiple CAD algorithms to be used in parallel on one or more image data sets.
"GridCAD offers the potential to greatly increase the accuracy and speed of image analysis by sharing data as well as computational resources," said Tony Pan, a researcher in Ohio State's biomedical informatics department.
This approach also enables the possibility of a consensus among multiple CAD systems and the combination of the CAD system-based interpretation with interpretations from one or more radiologists in one or more locations, Pan said.
GridCAD was developed as a demonstration over a year ago to illustrate the benefits of grid computing for radiology.
"Since then we have made significant developments in features and performance of the gridCAD application as well as the underlying software infrastructure," he said.
The current version of gridCAD, called gridIMAGE, adds functionalities to support image markup by radiologists and allows overlay comparison among multiple CAD and expert markups, Pan added.
"We have integrated support for IDL (Interactive Data analysis Language) and Matlab, two major scientific numerical languages, to allow academic CAD algorithm developers to integrate their algorithms into the grid and use grid data sources," he said.
GridIMAGE also supports microscopy image analysis, using nearly identical infrastructure, and supports dynamic installation of grid services on remote computers.
The underlying software infrastructure, called the In Vivo Imaging Middleware, has been formalized and provides interfaces to expose DICOM PACS on the grid.
The middleware provides optimized data transfer that is limited only by the network bandwidth, and security mechanism to authenticate, authorize, and encrypt the data access and transfer, Pan said.
"We have also implemented a client-side application called VirtualPACS, which allows existing DICOM workstations and other entities to access grid-based data sources using VirtualPACS as a gateway," he said.
Users can, in effect, access the grid using tools with which they are already familiar, while the tools themselves can interact with the grid without modifications.
The Reading Room Podcast: Current Perspectives on the Updated Appropriate Use Criteria for Brain PET
March 18th 2025In a new podcast, Satoshi Minoshima, M.D., Ph.D., and James Williams, Ph.D., share their insights on the recently updated appropriate use criteria for amyloid PET and tau PET in patients with mild cognitive impairment.