The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): A Completed Reference Database of Lung Nodules on CT Scans

Samuel G. Armato(University of Chicago), Geoffrey McLennan(University of Iowa), Luc Bidaut(The University of Texas MD Anderson Cancer Center), Michael F. McNitt‐Gray(University of California, Los Angeles), Charles R. Meyer(University of Michigan), Anthony P. Reeves(Cornell University), Binsheng Zhao(Memorial Sloan Kettering Cancer Center), Denise R. Aberle(University of California, Los Angeles), Claudia I. Henschke(Cornell University), Eric A. Hoffman(University of Iowa), Ella A. Kazerooni(Michigan Medicine), Heber MacMahon(University of Chicago), Edwin J.R. van Beek(University of Iowa), David Yankelevitz(Cornell University), Alberto Biancardi(Cornell University), Peyton H. Bland(University of Michigan), Matthew S. Brown(University of California, Los Angeles), Roger Engelmann(University of Chicago), Gary E. Laderach(University of Michigan), Daniel Max(Cornell University), Richard Pais(University of California, Los Angeles), David Qing(The University of Texas MD Anderson Cancer Center), Rachael Y. Roberts(University of Chicago), Amanda R. Smith(University of Iowa), Adam Starkey(University of Chicago), Poonam Batra(West Los Angeles College), Philip Caligiuri(University of Utah), Ali Farooqi(Cornell University), Gregory W. Gladish(The University of Texas MD Anderson Cancer Center), Cecilia M. Jude(University of California, Los Angeles), Reginald F. Munden(The University of Texas MD Anderson Cancer Center), Iva Petkovska(Beth Israel Deaconess Medical Center), Leslie E. Quint(University of Michigan), Lawrence H. Schwartz(Memorial Sloan Kettering Cancer Center), Baskaran Sundaram(University of Michigan), Lori E. Dodd(National Institute of Allergy and Infectious Diseases), Charles Fenimore(National Institute of Standards and Technology), David Gur(University of Pittsburgh), Nicholas Petrick(United States Food and Drug Administration), John Freymann(Science Applications International Corporation (United States)), Justin Kirby(Science Applications International Corporation (United States)), Brian Hughes, Alessi Vande Casteele(Agfa HealthCare), Sangeeta Gupte, Maha Sallam(Odesa I. I. Mechnikov National University), Michael D. Heath(Carestream (United States)), Michael Kühn(Philips (Germany)), Ekta Dharaiya(Highland Community College - Illinois), Richard J. Burns, David Fryd, Marcos Salganicoff, Vikram Anand, Uri Shreter(University of Wisconsin System), Stephen Vastagh, Barbara Y. Croft(National Cancer Institute), Laurence P. Clarke(National Cancer Institute)
Medical Physics
January 24, 2011
10.1118/1.3528204
Cited by 2,759Open Access
Full Text

Abstract

PURPOSE: 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 (CT) scans. The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI) completed such a database, establishing a publicly available reference for the medical imaging research community. Initiated by the National Cancer Institute (NCI), further advanced by the Foundation for the National Institutes of Health (FNIH), and accompanied by the Food and Drug Administration (FDA) through active participation, this public-private partnership demonstrates the success of a consortium founded on a consensus-based process. METHODS: Seven academic centers and eight medical imaging companies collaborated to identify, address, and resolve challenging organizational, technical, and clinical issues to provide a solid 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 the initial blinded-read phase, each radiologist independently reviewed each CT scan and marked lesions belonging to one of three categories ("nodule > or =3 mm," "nodule <3 mm," and "non-nodule > or =3 mm"). In the subsequent unblinded-read phase, each radiologist independently reviewed their own marks along with the anonymized marks of the three other radiologists to render a final opinion. The goal of this process was to identify as completely as possible all lung nodules in each CT scan without requiring forced consensus. RESULTS: The Database contains 7371 lesions marked "nodule" by at least one radiologist. 2669 of these lesions were marked "nodule > or =3 mm" by at least one radiologist, of which 928 (34.7%) received such marks from all four radiologists. These 2669 lesions include nodule outlines and subjective nodule characteristic ratings. CONCLUSIONS: The LIDC/IDRI Database is expected to provide an essential medical imaging research resource to spur CAD development, validation, and dissemination in clinical practice.

Related Papers

No related papers found

Powered by citation graph analysis