Research Articles

Download PDF (485.01 KB)

TOMOGRAPHY, December 2016, Volume 2, Issue 4: 388-395
DOI: 10.18383/j.tom.2016.00211

Deep Feature Transfer Learning in Combination with Traditional Features Predicts Survival Among Patients with Lung Adenocarcinoma

Rahul Paul1, Samuel H. Hawkins1, Yoganand Balagurunathan2, Matthew B. Schabath2,3, Robert J. Gillies2, Lawrence O. Hall1, and Dmitry B. Goldgof1

1Department of Computer Science and Engineering, University of South Florida, Tampa, Florida; 2Department of Cancer Imaging and Metabolism, H. Lee Moffitt Cancer Center & Research Institute, Tampa, Florida; and 3Department of Cancer Epidemiology, H. Lee Moffitt Cancer Center & Research Institute, Tampa, Florida


Lung cancer is the most common cause of cancer-related deaths in the USA. It can be detected and diagnosed using computed tomography images. For an automated classifier, identifying predictive features from medical images is a key concern. Deep feature extraction using pretrained convolutional neural networks (CNNs) has recently been successfully applied in some image domains. Here, we applied a pretrained CNN to extract deep features from 40 computed tomography images, with contrast, of non-small cell adenocarcinoma lung cancer, and combined deep features with traditional image features and trained classifiers to predict short- and long-term survivors. We experimented with several pretrained CNNs and several feature selection strategies. The best previously reported accuracy when using traditional quantitative features was 77.5% (area under the curve [AUC], 0.712), which was achieved by a decision tree classifier. The best reported accuracy from transfer learning and deep features was 77.5% (AUC, 0.713) using a decision tree classifier. When extracted deep neural network features were combined with traditional quantitative features, we obtained an accuracy of 90% (AUC, 0.935) with the 5 best post-rectified linear unit features extracted from a vgg-f pretrained CNN and the 5 best traditional features. The best results were achieved with the symmetric uncertainty feature ranking algorithm followed by a random forests classifier.

Supplemental Media


Download the article PDF (485.01 KB)

Download the full issue PDF (200.5 MB)

Mobile-ready Flipbook

View the full issue as a flipbook (Desktop and Mobile-ready)