Pulmonary nodule classification with deep residual networks
- 718 Downloads
Lung cancer has the highest death rate among all cancers in the USA. In this work we focus on improving the ability of computer-aided diagnosis (CAD) systems to predict the malignancy of nodules from cropped CT images of lung nodules.
We evaluate the effectiveness of very deep convolutional neural networks at the task of expert-level lung nodule malignancy classification. Using the state-of-the-art ResNet architecture as our basis, we explore the effect of curriculum learning, transfer learning, and varying network depth on the accuracy of malignancy classification.
Due to a lack of public datasets with standardized problem definitions and train/test splits, studies in this area tend to not compare directly against other existing work. This makes it hard to know the relative improvement in the new solution. In contrast, we directly compare our system against two state-of-the-art deep learning systems for nodule classification on the LIDC/IDRI dataset using the same experimental setup and data set. The results show that our system achieves the highest performance in terms of all metrics measured including sensitivity, specificity, precision, AUROC, and accuracy.
The proposed method of combining deep residual learning, curriculum learning, and transfer learning translates to high nodule classification accuracy. This reveals a promising new direction for effective pulmonary nodule CAD systems that mirrors the success of recent deep learning advances in other image-based application domains.
KeywordsLung nodule Convolutional neural network CT images
The authors acknowledge the National Cancer Institute and the Foundation for the National Institutes of Health, and their critical role in the creation of the free publicly available LIDC/IDRI Database used in this study.
Compliance with ethical standards
Conflict of interest
Aiden Nibali, Zhen He, and Dennis Wollersheim declare that they have no conflict of interest.
Human and animal rights
This article does not contain any studies with human participants or animals performed by any of the authors.
Informed consent was obtained from all individual participants included in the study.
- 1.American Cancer Society: Cancer facts & figures 2016 (2016). http://www.cancer.org/acs/groups/content/@research/documents/document/acspc-047079.pdf. Last accessed 23 Aug 2016
- 2.Bengio Y, Louradour J, Collobert R, Weston J (2009) Curriculum learning. In: Proceedings of 26th ICML, pp 41–48Google Scholar
- 3.Ciompi F, de Hoop B, van Riel SJ, Chung K, Scholten ET, Oudkerk M, de Jong PA, Prokop M, van Ginneken B (2015) Automatic classification of pulmonary peri-fissural nodules in computed tomography using an ensemble of 2D views and a convolutional neural network out-of-the-box. Med Image Anal 26(1):195–202CrossRefPubMedGoogle Scholar
- 5.He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 29th IEEE CVPRGoogle Scholar
- 6.He K, Zhang X, Ren S, Sun J (2016) Identity mappings in deep residual networks. arXiv Preprint arXiv:1603.05027
- 7.Hua KL, Hsu CH, Hidayati SC, Cheng WH, Chen YJ (2015) Computer-aided classification of lung nodules on computed tomography images via deep learning technique. OncoTargets Ther 8:2015–2022Google Scholar
- 8.International Agency for Research on Cancer (2012) Estimated incidence, mortality and prevalence worldwide in 2012. http://globocan.iarc.fr/Pages/fact_sheets_cancer.aspx?cancer=lung. Last accessed 23 Aug 2016
- 9.Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of 32nd ICML, pp 448–456Google Scholar
- 10.Kim Y (2014) Convolutional neural networks for sentence classification. In: Proceedings of EMNLP 2014Google Scholar
- 11.Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 25:1097–1105Google Scholar
- 12.Kumar D, Wong A, Clausi DA (2015) Lung nodule classification using deep features in CT images. In: 12th Conference on Computer and Robot Vision, pp. 133–138Google Scholar
- 14.LeCun Y, Boser B, Denker JS, Howard RE, Habbard W, Jackel LD, Henderson D (1990) Handwritten digit recognition with a back-propagation network. Adv Neural Inf Process Syst 2:396–404Google Scholar
- 17.Reeves AP, Biancardi AM (2011) The lung image Database Consortium (LIDC) nodule size report (2011). http://www.via.cornell.edu/lidc/. Last accessed 23 Aug 2016
- 18.Sermanet P, Eigen D, Zhang X, Mathieu M, Fergus R, LeCun Y (2014) OverFeat: integrated recognition, localization and detection using convolutional networks. In: Proceedings of ICLR 2014Google Scholar
- 19.Setio AAA, Ciompi F, Litjens G, Gerke P, Jacobs C, Sv Riel, Wille MW, Naqibullah M, Sanchez C, Bv Ginneken (2016) Pulmonary nodule detection in CT images: false positive reduction using multi-view convolutional networks. IEEE Trans Med Imaging 35(5):1160–1169Google Scholar
- 20.Shen W, Zhou M, Yang F, Yang C, Tian J (2015) Multi-scale convolutional neural networks for lung nodule classification. Inf Process Med Imaging 9123:588–599Google Scholar
- 21.Silver D, Huang A, Maddison CJ, Guez A, Sifre L, van den Driessche G, Schrittwieser J, Antonoglou I, Panneershelvam V, Lanctot M, Dieleman S, Grewe D, Nham J, Kalchbrenner N, Sutskever I, Lillicrap T, Leach M, Kavukcuoglu K, Graepel T, Hassabis D (2016) Mastering the game of Go with deep neural networks and tree search. Nature 529(7587):484–489CrossRefPubMedGoogle Scholar
- 22.Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: Proceedings of ICLR 2015Google Scholar
- 23.Smith K, Clark K, Bennett W, Nolan T, Kirby J, Wolfsberger M, Moulton J, Vendt B, Freymann J (2015) Data from LIDC-IDRI (2015). https://wiki.cancerimagingarchive.net/display/Public/LIDC-IDRI. Last accessed 23 Aug 2016
- 24.Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2014) Going deeper with convolutions. ArXiv Preprint arXiv:1409.4842
- 25.Telgarsky M (2016) Benefits of depth in neural networks. arXiv Preprint arXiv:1602.04485
- 26.Tieleman T, Hinton G (2012) Lecture 6.5-rmsprop: divide the gradient by a running average of its recent magnitudeGoogle Scholar
- 27.Toshev A, Szegedy C (2014) DeepPose: human pose estimation via deep neural networks. In: Proceedings of CVPR 2014Google Scholar
- 28.Zeiler MD (2012) ADADELTA: an adaptive learning rate method. arXiv Preprint arXiv:1212.5701
- 29.Zinovev D, Feigenbaum J, Raicu D, Furst J (2010) Predicting panel ratings for semantic characteristics of lung nodules. Technical Report (2010). http://via.library.depaul.edu/tr/18Google Scholar