Summary

The Lung Image Database Consortium (LIDC) image collection consists of diagnostic and lung cancer screening thoracic CT scans with marked-up annotated lesions. It is a web-accessible international resource for development, training, and evaluation of computer-assisted diagnostic (CAD) methods for lung cancer detection and diagnosis.

Supporting Documentation

For more information click on the following links:

• LIDC Program: http://imaging.cancer.gov/programsandresources/InformationSystems/LIDC
• XML File Documentation
• Annotated XML File
• LIDC Radiologist Instructions for Spatial Location and Extent Estimates
• Nodule size list for the LIDC public cases

Annotation Issues/Comments

1. We recently (early 2009) discovered that, for a subset of cases, inconsistent rating systems were used among the 5 sites with regard to the spiculation and lobulation characteristics of lesions identified as nodules > 3 mm. We are in the process of correcting this situation. The XML nodule characteristics data as it exists for some cases will be impacted by this error.
2. Also note that the XML files do not store radiologist annotations in a manner that allows for a comparison of individual radiologist reads across cases (i.e., the first reader recorded in the XML file of one CT scan will not necessarily be the same radiologist as the first reader recorded in the XML file of another CT scan).

AIM Annotation Conversion Project

As part of an effort to move towards standard formats for annotation and markup a project has been undertaken to convert this data from the LIDC project into Annotated Image Markup format (AIM).  AIM is a standard which was developed out of the caBIG program.  A related section of the wiki has been dedicated to covering the activities of this project and can be found here:

Data Access

Supporting Documentation

All supporting documentation has been migrated toThe Cancer Imaging Archive's wiki as of 6/21/11. 

...