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

Rahul Paul

¹,

Samuel H. Hawkins

¹,

Yoganand Balagurunathan

²,

Matthew Schabath

^2,3,

Robert J. Gillies

²,

Lawrence O. Hall

¹ and

Dmitry B. Goldgof

^1,*

1Department of Computer Science and Engineering, University of South Florida, Tampa, FL, USA

Department of Cancer Imaging and Metabolism, H. Lee Moffitt Cancer Center & Research Institute, Tampa, FL, USA

Department of Cancer Epidemiology, H. Lee Moffitt Cancer Center & Research Institute, Tampa, FL, USA

Author to whom correspondence should be addressed.

Tomography2016,2(4), 388-395;https://doi.org/10.18383/j.tom.2016.00211

Submission received: 2 September 2016 /Revised: 4 October 2016 /Accepted: 9 November 2016 /Published: 1 December 2016

Downloadkeyboard_arrow_downVersions Notes

Abstract

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.

Keywords:pre-trained CNN; transfer learning; deep features; computed tomography; symmetric uncertainty; lung cancer; adenocarcinoma; deep neural networkpre-trained CNN;transfer learning;deep features;computed tomography;symmetric uncertainty;lung cancer;adenocarcinoma;deep neural network

Share and Cite

MDPI and ACS Style

Paul, R.; Hawkins, S.H.; Balagurunathan, Y.; Schabath, M.; Gillies, R.J.; Hall, L.O.; Goldgof, D.B. Deep Feature Transfer Learning in Combination with Traditional Features Predicts Survival among Patients with Lung Adenocarcinoma.Tomography2016,2, 388-395. https://doi.org/10.18383/j.tom.2016.00211

AMA Style

Paul R, Hawkins SH, Balagurunathan Y, Schabath M, Gillies RJ, Hall LO, Goldgof DB. Deep Feature Transfer Learning in Combination with Traditional Features Predicts Survival among Patients with Lung Adenocarcinoma.Tomography. 2016; 2(4):388-395. https://doi.org/10.18383/j.tom.2016.00211

Chicago/Turabian Style

Paul, Rahul, Samuel H. Hawkins, Yoganand Balagurunathan, Matthew Schabath, Robert J. Gillies, Lawrence O. Hall, and Dmitry B. Goldgof. 2016. "Deep Feature Transfer Learning in Combination with Traditional Features Predicts Survival among Patients with Lung Adenocarcinoma"Tomography 2, no. 4: 388-395. https://doi.org/10.18383/j.tom.2016.00211

APA Style

Paul, R., Hawkins, S. H., Balagurunathan, Y., Schabath, M., Gillies, R. J., Hall, L. O., & Goldgof, D. B. (2016). Deep Feature Transfer Learning in Combination with Traditional Features Predicts Survival among Patients with Lung Adenocarcinoma.Tomography,2(4), 388-395. https://doi.org/10.18383/j.tom.2016.00211

Article Metrics

Article Access Statistics

For more information on the journal statistics, clickhere.

Multiple requests from the same IP address are counted as one view.

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Movatterモバイル変換

Journals

Topics

Information

Author Services

Initiatives

About

Notice

Notice

Article Menu

Need Help?

Support

Feedback

Information

JSmol Viewer

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

Cite

Further Information

Guidelines

MDPI Initiatives

Follow MDPI

Share Link

Share