Support for medical image databases gathers steam

December 1, 2005

The development of medical image databases has been largely a private activity to date, lacking the rigor and standards that would allow these repositories to serve as reference models for research, including drug development. This approach is changing, however, as more organizations, including the U.S. National Institutes of Health and the European Federation for Medical Informatics, join the effort.

The development of medical image databases has been largely a private activity to date, lacking the rigor and standards that would allow these repositories to serve as reference models for research, including drug development. This approach is changing, however, as more organizations, including the U.S. National Institutes of Health and the European Federation for Medical Informatics, join the effort.

Serious challenges remain. The incredible variety of imaging findings has proved to be an obstacle, as researchers struggle to annotate reference images appropriately. Resources can also be a problem, according to Alexander Horsch, Ph.D., of the University of Munich and a member of the European Federation for Medical Informatics (EFMI). The federation established a workgroup in 2002 to pursue a reference image database. Since then, awareness of the need for such a database has grown, but the commitment to contribute has been limited.

"Everyone wants to get, nobody wants to give," Horsch said.

Investigators in clinical trials have historically tended to reinvent the wheel for image management, incurring considerable expenditures in time and other resources, said Dr. Eliot Siegel, a professor and vice chair of information systems at the University of Maryland and chief of radiology and nuclear medicine at the Maryland Health Care System. No standards exist for exchange of these images associated with a clinical trial.

To address this problem, the RSNA's Medical Imaging Resource Center (MIRC) developed free and open source software that supports image acquisition and storage for clinical trials, Siegel said. The software enables facilities to transfer studies across a firewall securely and anonymizes patient information.

Two factors are driving the interest in reference image databases: the need for standards against which image processing strategies can be evaluated, and the use of imaging as an end point in drug development.

The benefits of a reference image database could be considerable, said Laurence P. Clarke, Ph.D., of the NIH's cancer imaging program at a special session of the 2005 Computer Assisted Radiology and Surgery meeting in June. Benchmarking for common cases, accelerated development of computer-assisted detection, objective assessment of therapies, greater confidence in clinical decisions, streamlined drug development, and better informed coverage decisions are all potential results.

The National Cancer Institute launched its Lung Image Database Consortium project in 2001. This year, it reached a cooperative agreement with the American College of Radiology Imaging Network to share some of the clinical trial data. It has begun to speed up data collection and expects to complete the project with 400 cases in September 2006, Clarke said.

The database is intended to permit benchmarking of CAD for lung nodule detection and diagnosis in a screening and early diagnosis context.

The LIDC's goals are to develop a Web-accessible image database for the development of CAD methods to encourage standards for software development, according to Dr. Denise Aberle, chief of thoracic imaging at the Geffen School of Medicine at the University of California, Los Angeles and principal investigator of the ACRIN National Lung Screening Trial.

"We plan to use our experience with the LIDC collaboration as a template for future collaborations so that other types of data being collected in imaging-based clinical trials can be applied to broad scientific research objectives in quantitative image analysis and efforts to better standardize imaging across oncologic clinical trials," she said.

A recently established public-private partnership involving the NCI, FDA, industry, and the Foundation for the National Institutes of Health will build on the results.

The NCI has adopted the MIRC schema for clinical trials and is now using MIRC's software for clinical trials involving imaging, according to Siegel. It is also developing the software and is purchasing the hardware to support an imaging informatics infrastructure that will store and share diagnostic imaging databases with the public. Images are already being sent to this NCI image repository from facilities performing clinical trials using the MIRC software.

The NCI will share a subset of the image collections on a public Web site in October.

Research by the EFMI working group identified other databases under development. The 10 largest include eight commercial databases, one with 1.2 million images. They generally could not be validated, however, and would not serve as reference databases.

A group of 10 smaller medical image databases comes closer to what the EFMI is seeking, Horsch said. One is the NCI's lung image database. Two are devoted to breast cancer: the Digital Database for Screening Mammography (U.S.) and one run by the Mammographic Imaging Analysis Society (U.K.). Three are committed to brain imaging: the Simulated Brain Database, the Biomedical Informatics Research Network, and the Laboratory of Neuro Imaging (all in the U.S.). The Pap Smear Tutorial (Denmark) addresses cervical cancer, and the Medical Image Reference Center (Japan) focuses on cancer and cardiovascular diseases.