Share Email Print

Proceedings Paper

Deep-learning derived features for lung nodule classification with limited datasets
Author(s): P. Thammasorn; W. Wu; L. A. Pierce; S. N. Pipavath; P. D. Lampe; A. M. Houghton; D. R. Haynor; W. A. Chaovalitwongse; P. E. Kinahan
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Only a few percent of indeterminate nodules found in lung CT images are cancer. However, enabling earlier diagnosis is important to avoid invasive procedures or long-time surveillance to those benign nodules. We are evaluating a classification framework using radiomics features derived with a machine learning approach from a small data set of indeterminate CT lung nodule images. We used a retrospective analysis of 194 cases with pulmonary nodules in the CT images with or without contrast enhancement from lung cancer screening clinics. The nodules were contoured by a radiologist and texture features of the lesion were calculated. In addition, sematic features describing shape were categorized. We also explored a Multiband network, a feature derivation path that uses a modified convolutional neural network (CNN) with a Triplet Network. This was trained to create discriminative feature representations useful for variable-sized nodule classification. The diagnostic accuracy was evaluated for multiple machine learning algorithms using texture, shape, and CNN features. In the CT contrast-enhanced group, the texture or semantic shape features yielded an overall diagnostic accuracy of 80%. Use of a standard deep learning network in the framework for feature derivation yielded features that substantially underperformed compared to texture and/or semantic features. However, the proposed Multiband approach of feature derivation produced results similar in diagnostic accuracy to the texture and semantic features. While the Multiband feature derivation approach did not outperform the texture and/or semantic features, its equivalent performance indicates promise for future improvements to increase diagnostic accuracy. Importantly, the Multiband approach adapts readily to different size lesions without interpolation, and performed well with relatively small amount of training data.

Paper Details

Date Published: 27 February 2018
PDF: 7 pages
Proc. SPIE 10575, Medical Imaging 2018: Computer-Aided Diagnosis, 105751F (27 February 2018); doi: 10.1117/12.2293236
Show Author Affiliations
P. Thammasorn, Univ. of Arkansas (United States)
W. Wu, Huazhong Univ. of Science and Technology (China)
Univ. of Washington (United States)
L. A. Pierce, Univ. of Washington (United States)
S. N. Pipavath, Univ. of Washington (United States)
P. D. Lampe, Fred Hutchinson Cancer Research Ctr. (United States)
A. M. Houghton, Fred Hutchinson Cancer Research Ctr. (United States)
D. R. Haynor, Univ. of Washington (United States)
W. A. Chaovalitwongse, Univ. of Arkansas (United States)
P. E. Kinahan, Univ. of Washington (United States)

Published in SPIE Proceedings Vol. 10575:
Medical Imaging 2018: Computer-Aided Diagnosis
Nicholas Petrick; Kensaku Mori, Editor(s)

© SPIE. Terms of Use
Back to Top