Swift medical imaging provides potent cancer diagnostic tool
IBM is working with top hospitals and researchers to improve medical imaging, a powerful weapon in the battle against cancer.
In Minnesota, Mayo Clinic and IBM have set up a research facility to improve medical imaging and ultimately patient care. The Medical Imaging Informatics Innovation Center (MI3C) is an extension of a Mayo-IBM research collaboration that has already enabled physicians to register medical images up to 50-times faster and to provide critical diagnoses, such as changes in the size of tumors, in seconds instead of hours.
"This facility will allow us to explore projects in medical imaging and radiology that can help to provide faster and better information for our physicians, and in turn, improved treatments for our patients," said Bradley Erickson, M.D., Ph.D., head of Mayo's Radiology Informatics Lab. "The collaborative potential of the MI3C gives us the opportunity to develop computationally intensive solutions for diagnostic problems we see every day, but that we at Mayo could not attempt to resolve on our own."
While in the Northeast, the Cancer Institute of New Jersey, Rutgers University and IBM will collaborate to mine information from a huge bank of medical images and other data. The project will use advanced computer and imaging technologies that make it easier to compare cancerous tissues, cell and radiology studies. With the resulting information, researchers and physicians expect to make more accurate cancer prognoses, more personalized treatment planning and eventually to discover and develop new cancer drugs.
This project is an extension of the "Help Defeat Cancer" project that used IBM's World Community Grid to demonstrate the effectiveness of identifying different types and stages of disease through underlying staining patterns in digital images of cancer tissues. World Community Grid is a virtual supercomputer that depends on thousands of volunteers donating their unused computer time.
The system is being developed to provide decision support for characterizing and tracking tumors across consecutive imaging studies.