Pulmonary nodule classification in lung cancer screening with three-dimensional convolutional neural networks

Shuang Liu, Yiting Xie, Artit Jirapatnakul, Anthony P. Reeves

Research output: Contribution to journalArticlepeer-review

44 Scopus citations

Abstract

A three-dimensional (3-D) convolutional neural network (CNN) trained from scratch is presented for the classification of pulmonary nodule malignancy from low-dose chest CT scans. Recent approval of lung cancer screening in the United States provides motivation for determining the likelihood of malignancy of pulmonary nodules from the initial CT scan finding to minimize the number of follow-up actions. Classifier ensembles of different combinations of the 3-D CNN and traditional machine learning models based on handcrafted 3-D image features are also explored. The dataset consisting of 326 nodules is constructed with balanced size and class distribution with the malignancy status pathologically confirmed. The results show that both the 3-D CNN single model and the ensemble models with 3-D CNN outperform the respective counterparts constructed using only traditional models. Moreover, complementary information can be learned by the 3-D CNN and the conventional models, which together are combined to construct an ensemble model with statistically superior performance compared with the single traditional model. The performance of the 3-D CNN model demonstrates the potential for improving the lung cancer screening follow-up protocol, which currently mainly depends on the nodule size.

Original languageEnglish
Article number041308
JournalJournal of Medical Imaging
Volume4
Issue number4
DOIs
StatePublished - 1 Oct 2017

Keywords

  • low-dose chest CT
  • lung cancer screening
  • pulmonary nodule classification
  • three-dimensional convolutional neural network
  • three-dimensional convolutional neural network

Fingerprint

Dive into the research topics of 'Pulmonary nodule classification in lung cancer screening with three-dimensional convolutional neural networks'. Together they form a unique fingerprint.

Cite this