The Lung Image Database Consortium (LIDC) Data Collection Process for Nodule Detection and Annotation

Michael F Mcnitt‐Gray ,Anthony P Reeves,Matthew S Brown,Geoffrey Mclennan,Gary E Laderach,Barbara Y Croft,Samuel G Armato,Denise R Aberle,Ella A Kazerooni,Peyton H Bland,Chris Piker,Richie C Pais,Heber Macmahon,Charles R Meyer,Junfeng Guo,John Freymann,David F Yankelevitz,Laurence P Clarke,Zaid J Towfic ,Roger Engelmann ,Edwin Jacques Rudolph Van Beek ,David Qing

doi:10.1016/j.acra.2007.07.021

Abstract

The Lung Image Database Consortium (LIDC) is developing a publicly available database of thoracic computed tomography (CT) scans as a medical imaging research resource to promote the development of computer-aided detection or characterization of pulmonary nodules. To obtain the best estimate of the location and spatial extent of lung nodules, expert thoracic radiologists reviewed and annotated each scan. Because a consensus panel approach was neither feasible nor desirable, a unique two-phase, multicenter data collection process was developed to allow multiple radiologists at different centers to asynchronously review and annotate each CT scan. This data collection process was also intended to capture the variability among readers. Four radiologists reviewed each scan using the following process. In the first or "blinded" phase, each radiologist reviewed the CT scan independently. In the second or "unblinded" review phase, results from all four blinded reviews were compiled and presented to each radiologist for a second review, allowing the radiologists to review their own annotations together with the annotations of the other radiologists. The results of each radiologist's unblinded review were compiled to form the final unblinded review. An XML-based message system was developed to communicate the results of each reading. This two-phase data collection process was designed, tested, and implemented across the LIDC. More than 500 CT scans have been read and annotated using this method by four expert readers; these scans either are currently publicly available at http://ncia.nci.nih.gov or will be in the near future. A unique data collection process was developed, tested, and implemented that allowed multiple readers at distributed sites to asynchronously review CT scans multiple times. This process captured the opinions of each reader regarding the location and spatial extent of lung nodules.

Highlights

Computed tomography (CT) is being investigated for a variety of radiologic tasks involving lung nodules and lung malignancies
The image data and XML files that contain the unblinded read results from all four readers are publicly available from the National Cancer Insitute’s Image Archive (NCIA) Archives under the Lung Image Database Consortium (LIDC) collection
The LIDC has created a publicly available database of approximately 100 thoracic CT scans that have been marked for the location and spatial extent of lung nodules

Summary

Introduction

Computed tomography (CT) is being investigated for a variety of radiologic tasks involving lung nodules and lung malignancies. Radiologists are faced with the task of both identifying and characterizing lung nodules on large, multidetector row CT scans for these applications. This has motivated interest and research into computer-aided diagnosis (CAD) methods, with several commercial systems having either already received FDA approval or that have been submitted for approval of CAD or CAD-like systems. The mission of the LIDC is: (a) to develop an image database as a web accessible international research resource for the development, training, and evaluation of CAD methods for lung cancer detection and diagnosis using CT and (b) to create this database to enable the correlation of performance of CAD methods for detection and classification of lung nodules with spatial, McNitt-Gray et al

Methods

Results

Conclusion