This Article contains errors. The legend of Table 3 is incorrect.
‘Nodule classification performance in terms of accuracy and F-measure per nodule type. Results for each pair of human observer Oi vs. Oj and for observers versus the computer on the testOBS dataset (167 nodules) are reported. Averages of measures across observers and across computer-observers are also indicated. The additional class “not a nodule” is added to observers since they could exclude nodules during the observer study. The performance of the system on the testALL set (639 nodules) is also reported. In this case, annotations from DLCST radiologists (O4) are considered as the reference standard’.
should read:
‘Nodule classification performance in terms of accuracy and F-measure per nodule type. Results for each pair of human observer Oi vs. Oj and for observers versus the computer on the testOBS dataset (167 nodules) are reported. Averages of measures across observers and across computer-observers are also indicated. The additional class “not a nodule” is added to observers since they could exclude nodules during the observer study’.
Additionally, the title of Table 4 is incomplete.
‘Comparison of classification performance in terms of accuracy and F-measure when the considered methods are: (1) features based on pixel intensity of patches and linear SVM classifier, (2) features learned from raw nodule patches using the unsupervised learning approach proposed in ref. 34 and linear SVM classifier, (3) the proposed deep learning approach using ConvNets working at 1, 2 and 3 scales’.
should read:
‘Comparison of classification performance on the testALL set (639 nodules) in terms of accuracy and F-measure when the considered methods are: (1) features based on pixel intensity of patches and linear SVM classifier, (2) features learned from raw nodule patches using the unsupervised learning approach proposed in ref. 34 and linear SVM classifier, (3) the proposed deep learning approach using ConvNets working at 1, 2 and 3 scales. In these experiments, annotations from DLCST radiologists (O4) are considered as the reference standard’.
Additional information
The online version of the original article can be found at 10.1038/srep46479
Rights and permissions
This work is licensed under a Creative Commons Attribution 4.0 International License. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in the credit line; if the material is not included under the Creative Commons license, users will need to obtain permission from the license holder to reproduce the material. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/
About this article
Cite this article
Ciompi, F., Chung, K., van Riel, S. et al. Correction: Corrigendum: Towards automatic pulmonary nodule management in lung cancer screening with deep learning. Sci Rep 7, 46878 (2017). https://doi.org/10.1038/srep46878
Published:
DOI: https://doi.org/10.1038/srep46878
This article is cited by
-
Chest disease radiography in twofold: using convolutional neural networks and transfer learning
Evolving Systems (2021)
-
Automated lung cancer diagnosis using three-dimensional convolutional neural networks
Medical & Biological Engineering & Computing (2020)
-
ESR/ERS statement paper on lung cancer screening
European Radiology (2020)
-
Deep Learning for Chest Radiology: A Review
Current Radiology Reports (2019)
-
Fifty years of computer analysis in chest imaging: rule-based, machine learning, deep learning
Radiological Physics and Technology (2017)
Comments
By submitting a comment you agree to abide by our Terms and Community Guidelines. If you find something abusive or that does not comply with our terms or guidelines please flag it as inappropriate.
