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

TL;DR

The LUNA16 challenge provides a standardized framework for evaluating pulmonary nodule detection algorithms on a large CT dataset, demonstrating that combining convolutional network solutions significantly improves detection sensitivity.

Contribution

This paper introduces the LUNA16 challenge, a new benchmark for comparing nodule detection algorithms, and shows that combining systems enhances detection performance beyond individual solutions.

Findings

Combined algorithms achieved over 95% sensitivity at fewer than 1 false positive per scan.

Leading solutions used convolutional neural networks and nodule candidate sets.

The best system detected nodules missed by expert annotations.

Abstract

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.