Share Email Print

Journal of Medical Imaging • Open Access

LUNGx Challenge for computerized lung nodule classification
Author(s): Samuel G. Armato; Karen Drukker; Feng Li; Lubomir Hadjiiski; Georgia D. Tourassi; Justin S. Kirby; Laurence P. Clarke; Roger M. Engelmann; Maryellen L. Giger; George Redmond; Keyvan Farahani

Paper Abstract

The purpose of this work is to describe the LUNGx Challenge for the computerized classification of lung nodules on diagnostic computed tomography (CT) scans as benign or malignant and report the performance of participants’ computerized methods along with that of six radiologists who participated in an observer study performing the same Challenge task on the same dataset. The Challenge provided sets of calibration and testing scans, established a performance assessment process, and created an infrastructure for case dissemination and result submission. Ten groups applied their own methods to 73 lung nodules (37 benign and 36 malignant) that were selected to achieve approximate size matching between the two cohorts. Area under the receiver operating characteristic curve (AUC) values for these methods ranged from 0.50 to 0.68; only three methods performed statistically better than random guessing. The radiologists’ AUC values ranged from 0.70 to 0.85; three radiologists performed statistically better than the best-performing computer method. The LUNGx Challenge compared the performance of computerized methods in the task of differentiating benign from malignant lung nodules on CT scans, placed in the context of the performance of radiologists on the same task. The continued public availability of the Challenge cases will provide a valuable resource for the medical imaging research community.

Paper Details

Date Published: 19 December 2016
PDF: 9 pages
J. Med. Img. 3(4) 044506 doi: 10.1117/1.JMI.3.4.044506
Published in: Journal of Medical Imaging Volume 3, Issue 4
Show Author Affiliations
Samuel G. Armato, The University of Chicago (United States)
Karen Drukker, The University of Chicago (United States)
Feng Li, The University of Chicago (United States)
Lubomir Hadjiiski, University of Michigan (United States)
Georgia D. Tourassi, Health Data Sciences Institute (United States)
Justin S. Kirby, Leidos Biomedical Research, Inc. (United States)
Laurence P. Clarke, National Cancer Institute (United States)
Roger M. Engelmann, The University of Chicago (United States)
Maryellen L. Giger, The University of Chicago (United States)
George Redmond, National Cancer Institute (United States)
Keyvan Farahani, National Cancer Institute (United States)

© SPIE. Terms of Use
Back to Top