Conference proceeding
The Lung Image Database Consortium (LIDC): A quality assurance model for the collection of expert-defined "truth" in lung-nodulebased image analysis studies
Medical Imaging 2007: Computer-aided Diagnosis, Pts 1 and 2, Vol.6514
Proceedings of SPIE
01/01/2007
DOI: 10.1117/12.713227
Abstract
The development of computer-aided diagnostic (CAD) systems requires an initial establishment of "truth" by expert human observers. Potential inconsistencies in the "truth" data must be identified and corrected before investigators can rely on this data. We developed a quality assurance model to supplement the "truth" collection process for lung nodules on CT scans. A two-phase process was established for the interpretation of CT scans by four radiologists. During the initial "blinded read," radiologists independently assigned lesions they identified into one of three categories: "nodule >= 3mm... nodule < 3mm," or "non-nodule >= 3mm." During the subsequent "unblinded read," the blinded read results of all radiologists were revealed. The radiologists then independently reviewed their marks along with their colleague's marks; a radiologist's own marks could be left unchanged, deleted, switched in terms of lesion category, or additional marks could be added. The final set of marks underwent quality assurance, which consisted of identification of potential errors that occurred during the reading process and error correction. All marks were visually grouped into discrete nodules. Six categories of potential error were defined, and any nodule with a mark that satisfied the criterion for one of these categories was referred to the radiologist who assigned the mark in question. The radiologist either corrected the mark or confirmed that the mark was intentional. A total of 829 nodules were identified by at least one radiologist in 100 CT scans through the two-phase process designed to capture "truth." The quality assurance process yielded 81 nodules with potential errors. The establishment of "truth" must incorporate a quality assurance model to guarantee the integrity of the "truth" that will provide the basis for the training and testing of CAD systems.
Details
- Title: Subtitle
- The Lung Image Database Consortium (LIDC): A quality assurance model for the collection of expert-defined "truth" in lung-nodulebased image analysis studies
- Creators
- Samuel G. Armato - University of ChicagoRachael Y. Roberts - University of ChicagoGeoffrey McLennan - University of IowaMichael F. McNitt-Gray - University of California- Los Angeles, United StatesDavid Yankelevitz - Cornell UniversityElla A. Kazerooni - University of Michigan United StatesEdwin J. R. van Beek - University of IowaHeber MacMahon - University of ChicagoDenise R. Aberle - University of California, Los AngelesCharles R. Meyer - University of Michigan United StatesAnthony P. Reeves - Cornell UniversityClaudia I. Henschke - Cornell UniversityEric A. Hoffman - University of IowaBarbara Y. Croft - National Cancer InstituteLaurence P. Clarke - National Cancer Institute
- Contributors
- M L Giger (Editor)N Karssemeijer (Editor)
- Resource Type
- Conference proceeding
- Publication Details
- Medical Imaging 2007: Computer-aided Diagnosis, Pts 1 and 2, Vol.6514
- Publisher
- Spie-Int Soc Optical Engineering
- Series
- Proceedings of SPIE
- DOI
- 10.1117/12.713227
- ISSN
- 0277-786X
- Number of pages
- 7
- Grant note
- U01CA091085; U01CA091090; U01CA091099; U01CA091100; U01CA091103 / USPHS; United States Department of Health & Human Services; United States Public Health Service
- Language
- English
- Date published
- 01/01/2007
- Academic Unit
- Internal Medicine; Roy J. Carver Department of Biomedical Engineering; Radiology
- Record Identifier
- 9984318708302771
Metrics
6 Record Views