Lung Imaging Database Consortium

Website: http://imaging.cancer.gov/reportsandpublications/reportsandpresentations/firstdataset

The Lung Imaging Database Consortium (LIDC), funded by CIP, comprises five institutions that are developing consensus guidelines and metrics for the use of spiral CT lung images.

Preliminary clinical studies show that spiral CT scanning of the lungs could play a role in improving early detection of lung cancer in high-risk individuals. However, more clinical data are needed before public health recommendations can be made for population-based spiral CT screening. Image-processing algorithms have the potential to help detect lesions in spiral CT scans and to assess changes in lesions on serial CT studies. The use of such computer-assisted algorithms could significantly enhance the sensitivity and specificity of spiral CT lung screening and lower costs by reducing physician time needed for interpretation.

LIDC is in the process of constructing a database of spiral CT lung images as a test-bed and showcase. This resource will stimulate further database development and thus accelerate applications of imaging to lung cancer screening, diagnosis, and image-guided intervention and treatment.

The database has wide utility as a research, teaching, and training resource. Already available on the LIDC Website via FTP download are two lung cancer cases with CT scans performed at multiple time points during treatment. Nodule markings are contained in .xml files accompanying the scans. More data sets will be presented in the future. Also available is the first data set, containing images of 23 nodules and a boundary definition of the nodules from a screening and diagnostic caseload. This preliminary database may prove to be useful for the evaluation of image segmentation methods. LIDC has plans to provide the final database of 400 cases in summer 2006.