Take a sneak peek at the new NIST.gov and let us know what you think!
(Please note: some content may not be complete on the beta site.).
NIST Authors in Bold
|Author(s):||Charles D. Fenimore; Samuel Armato; Denise Aberle; Matthew Brown; Claudia Henschke; Michael McNitt-Gray; Heber MacMahon; Geoffrey McLennan; Charles R. Meyer; Anthony P. Reeves; David F. Yankelevitz;|
|Title:||The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): A Completed Reference Database of Lung Nodules on CT Scans|
|Published:||January 28, 2011|
|Abstract:||The development of computer-aided diagnostic (CAD) methods for lung nodule detection, classification, and quantitative assessment can be facilitated through a well-characterized repository of computed tomography scans. The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI) completed a publicly available reference database for the medical imaging research community. Initiated by the National Cancer Institute and the Food and Drug Administration and advanced by the Foundation for the National Institutes of Health (FNIH), this public-private partnership demonstrates the success of a consensus-based consortium. Seven academic centers and eight medical imaging companies collaborated to identify, address, and resolve organizational, technical, and clinical issues to provide a foundation for a robust database. The LIDC/IDRI Database contains 1018 cases, each of which includes images from a clinical thoracic CT scan and an associated XML file that records the results of a two-phase image annotation process performed by four experienced thoracic radiologists. In a blinded-read phase, each radiologist independently reviewed each CT scan and marked lesions belonging to one of three categories ( nodule > 3 mm, nodule < 3 mm, and non-nodule > 3 mm ). In an unblinded-read phase, each radiologist independently reviewed their own marks along with the anonymized marks of three other radiologists to render a final opinion. The goal was to identify as completely as possible all lung nodules in each CT scan without requiring forced consensus. The Database contains 7,371 lesions marked nodule by at least one radiologist and 2,669 lesions marked nodule > 3 mm by at least one radiologist, of which 928 received such marks from all four radiologists. The 2,669 modules include outlines and subjective characteristic ratings. The Database is expected to be an essential medical imaging research resource to spur CAD development and adoption.|
|Pages:||pp. 915 - 931|
|Keywords:||lung nodule, computed tomography (CT), thoracic imaging, inter-observer variability, computer-aided diagnosis (CAD)|
|Research Areas:||Health IT, Medical Physics, Medical Devices|
|PDF version:||Click here to retrieve PDF version of paper (735KB)|