Skip to Main Content

An official website of the United States government

About this Publication
Title
Convolutional Neural Network ensembles for accurate lung nodule malignancy prediction 2 years in the future.
Pubmed ID
32658721 (View this publication on the PubMed website)
Digital Object Identifier
Publication
Comput Biol Med. 2020 Jul; Volume 122: Pages 103882
Authors
Paul R, Schabath M, Gillies R, Hall L, Goldgof D
Affiliations
  • Department of Computer Science & Engineering, University of South Florida, Tampa, FL, USA. Electronic address: rahulp@mail.usf.edu.
  • Department of Cancer Epidemiology, H. L. Moffitt Cancer Center & Research Institute, Tampa, FL, USA.
  • Department of Cancer Imaging and Metabolism, H. L. Moffitt Cancer Center & Research Institute, Tampa, FL, USA.
  • Department of Computer Science & Engineering, University of South Florida, Tampa, FL, USA.
Abstract

Convolutional Neural Networks (CNNs) have been utilized for to distinguish between benign lung nodules and those that will become malignant. The objective of this study was to use an ensemble of CNNs to predict which baseline nodules would be diagnosed as lung cancer in a second follow up screening after more than one year. Low-dose helical computed tomography images and data were utilized from the National Lung Screening Trial (NLST). The malignant nodules and nodule positive controls were divided into training and test cohorts. T0 nodules were used to predict lung cancer incidence at T1 or T2. To increase the sample size, image augmentation was performed using rotations, flipping, and elastic deformation. Three CNN architectures were designed for malignancy prediction, and each architecture was trained using seven different seeds to create the initial weights. This enabled variability in the CNN models which were combined to generate a robust, more accurate ensemble model. Augmenting images using only rotation and flipping and training with images from T0 yielded the best accuracy to predict lung cancer incidence at T2 from a separate test cohort (Accuracy = 90.29%; AUC = 0.96) based on an ensemble 21 models. Images augmented by rotation and flipping enabled effective learning by increasing the relatively small sample size. Ensemble learning with deep neural networks is a compelling approach that accurately predicted lung cancer incidence at the second screening after the baseline screen mostly 2 years later.

Related CDAS Studies
Related CDAS Projects