OR WAIT null SECS
Cornell University researchers have succeeded in creating an integrated medical image database for multi-institutional lung cancer research. The database collects DICOM images and other patient data from member institution PACS over the Internet. It
Cornell University researchers have succeeded in creating an integrated medical image database for multi-institutional lung cancer research.
The database collects DICOM images and other patient data from member institution PACS over the Internet. It then provides image data, patient statistics, and image analysis results to remote users.
"The system permits the integrated accumulation of image and case data from multiple centers using secure protocols," said Anthony P. Reeves, Ph.D., an electrical engineer at Cornell.
The system is more than a digital image archive service, however. The facility also has the capability of performing image and statistical analysis of all submitted data, according to Reeves.
"We have imported CT studies from a variety of scanners and PACS over the Internet, and case data from over 10 institutions over the Web-based interface and through batch submissions," Reeves said.
The project is in process of collecting all available cases from the Early Lung Cancer Action Project (ELCAP). Cases are then analyzed using Cornell's 3D image analysis methodology.
Preliminary clinical studies show that spiral CT scanning of the lungs can improve early detection of lung cancer in high-risk individuals. More clinical data are needed, however, before public health recommendations can be made for population-based screening.
Image processing algorithms have the potential to assist in lesion detection on spiral CT studies and to assess the stability or change in size of lesions on serial CT studies. The use of such computer-assisted diagnosis (CAD) algorithms could substantially enhance the sensitivity and specificity of spiral CT lung screening. It could also lower costs by reducing the physician time needed for interpretation, according to the National Cancer Institute.
Electronic image detectors such as those used in contemporary spiral CT scanners acquire more information than can be displayed at any one time using standard display methods. Therefore, research on image processing methods is essential to fully exploit the information that has been acquired.
The ability to extract quantitative information from images is increasingly important, and this also requires image processing. Investigators working on image processing frequently lack access to large the databases of images necessary to develop and test their work or the resources necessary to create them.
The new lung database fills this need. While CT scans make up the primary image data for lung cancer research, chest x-rays and pathology images are also being accumulated.
"In our system, image data may be sent to the database over the Internet using a special relay computer for security that receives standard DICOM protocols from member CT scanners," Reeves said. "Image data (with patient identification removed) may then be retrieved at members' workstations."