Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: The LUNA16 challenge.

Autor: Setio AAA; Diagnostic Image Analysis Group, Radboud University Medical Center, Nijmegen, The Netherlands. Electronic address: arnaud.setio@gmail.com., Traverso A; Department of Applied Science and Technology, Polytechnic University of Turin, Turin, Italy; Turin Section of Istituto Nazionale di Fisica Nucleare, Turin, Italy; Diagnostic Image Analysis Group, Radboud University Medical Center, Nijmegen, The Netherlands., de Bel T; Institute for Computing and Information Sciences, Radboud University Nijmegen, Nijmegen, The Netherlands., Berens MSN; Radboud University, Nijmegen, The Netherlands., Bogaard CVD; Institute for Computing and Information Sciences, Radboud University Nijmegen, Nijmegen, The Netherlands., Cerello P; Turin Section of Istituto Nazionale di Fisica Nucleare, Turin, Italy., Chen H; Department of Computer Science and Engineering, The Chinese University of Hong Kong, China., Dou Q; Department of Computer Science and Engineering, The Chinese University of Hong Kong, China., Fantacci ME; Department of Physics, University of Pisa, Pisa, Italy; Pisa Section of Istituto Nazionale di Fisica Nucleare, Pisa, Italy., Geurts B; Department of Radiology and Nuclear Medicine, Radboud University Medical Center, Nijmegen, The Netherlands., Gugten RV; Radboud University, Nijmegen, The Netherlands., Heng PA; Department of Computer Science and Engineering, The Chinese University of Hong Kong, China., Jansen B; Department of Electronics and Informatics, Vrije Universiteit Brussel, Brussels, Belgium; IMEC, Leuven, Belgium., de Kaste MMJ; Radboud University, Nijmegen, The Netherlands., Kotov V; Institute for Computing and Information Sciences, Radboud University Nijmegen, Nijmegen, The Netherlands., Lin JY; Yan'an Xi Lu 129, 9th floor, Shanghai, China., Manders JTMC; Radboud University, Nijmegen, The Netherlands., Sóñora-Mengana A; Centro de Biofísica Médica, Universidad de Oriente, Santiago de Cuba, Cuba; Department of Electronics and Informatics, Vrije Universiteit Brussel, Brussels, Belgium; Center of Applied Technologies and Nuclear Development, La Habana, Cuba., García-Naranjo JC; Centro de Biofísica Médica, Universidad de Oriente, Santiago de Cuba, Cuba., Papavasileiou E; Department of Electronics and Informatics, Vrije Universiteit Brussel, Brussels, Belgium., Prokop M; Diagnostic Image Analysis Group, Radboud University Medical Center, Nijmegen, The Netherlands., Saletta M; Turin Section of Istituto Nazionale di Fisica Nucleare, Turin, Italy., Schaefer-Prokop CM; Diagnostic Image Analysis Group, Radboud University Medical Center, Nijmegen, The Netherlands; Department of Radiology, Meander Medisch Centrum, Amersfoort, The Netherlands., Scholten ET; Diagnostic Image Analysis Group, Radboud University Medical Center, Nijmegen, The Netherlands., Scholten L; Institute for Computing and Information Sciences, Radboud University Nijmegen, Nijmegen, The Netherlands., Snoeren MM; Department of Radiology and Nuclear Medicine, Radboud University Medical Center, Nijmegen, The Netherlands., Torres EL; Center of Applied Technologies and Nuclear Development, La Habana, Cuba., Vandemeulebroucke J; Department of Electronics and Informatics, Vrije Universiteit Brussel, Brussels, Belgium; IMEC, Leuven, Belgium., Walasek N; Institute for Computing and Information Sciences, Radboud University Nijmegen, Nijmegen, The Netherlands., Zuidhof GCA; Radboud University, Nijmegen, The Netherlands., Ginneken BV; Diagnostic Image Analysis Group, Radboud University Medical Center, Nijmegen, The Netherlands; Fraunhofer MEVIS, Bremen, Germany., Jacobs C; Diagnostic Image Analysis Group, Radboud University Medical Center, Nijmegen, The Netherlands.
Jazyk: angličtina
Zdroj: Medical image analysis [Med Image Anal] 2017 Dec; Vol. 42, pp. 1-13. Date of Electronic Publication: 2017 Jul 13.
DOI: 10.1016/j.media.2017.06.015
Abstrakt: Automatic detection of pulmonary nodules in thoracic computed tomography (CT) scans has been an active area of research for the last two decades. However, there have only been few studies that provide a comparative performance evaluation of different systems on a common database. We have therefore set up the LUNA16 challenge, an objective evaluation framework for automatic nodule detection algorithms using the largest publicly available reference database of chest CT scans, the LIDC-IDRI data set. In LUNA16, participants develop their algorithm and upload their predictions on 888 CT scans in one of the two tracks: 1) the complete nodule detection track where a complete CAD system should be developed, or 2) the false positive reduction track where a provided set of nodule candidates should be classified. This paper describes the setup of LUNA16 and presents the results of the challenge so far. Moreover, the impact of combining individual systems on the detection performance was also investigated. It was observed that the leading solutions employed convolutional networks and used the provided set of nodule candidates. The combination of these solutions achieved an excellent sensitivity of over 95% at fewer than 1.0 false positives per scan. This highlights the potential of combining algorithms to improve the detection performance. Our observer study with four expert readers has shown that the best system detects nodules that were missed by expert readers who originally annotated the LIDC-IDRI data. We released this set of additional nodules for further development of CAD systems.
(Copyright © 2017 Elsevier B.V. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: