Share Email Print
cover

Journal of Medical Imaging • Open Access

Improved pulmonary nodule classification utilizing quantitative lung parenchyma features
Author(s): Samantha K. Dilger; Johanna Uthoff; Alexandra Judisch; Emily Hammond; Sarah L. Mott; Brian J. Smith; John D. Newell; Eric A. Hoffman; Jessica C. Sieren

Paper Abstract

Current computer-aided diagnosis (CAD) models for determining pulmonary nodule malignancy characterize nodule shape, density, and border in computed tomography (CT) data. Analyzing the lung parenchyma surrounding the nodule has been minimally explored. We hypothesize that improved nodule classification is achievable by including features quantified from the surrounding lung tissue. To explore this hypothesis, we have developed expanded quantitative CT feature extraction techniques, including volumetric Laws texture energy measures for the parenchyma and nodule, border descriptors using ray-casting and rubber-band straightening, histogram features characterizing densities, and global lung measurements. Using stepwise forward selection and leave-one-case-out cross-validation, a neural network was used for classification. When applied to 50 nodules (22 malignant and 28 benign) from high-resolution CT scans, 52 features (8 nodule, 39 parenchymal, and 5 global) were statistically significant. Nodule-only features yielded an area under the ROC curve of 0.918 (including nodule size) and 0.872 (excluding nodule size). Performance was improved through inclusion of parenchymal (0.938) and global features (0.932). These results show a trend toward increased performance when the parenchyma is included, coupled with the large number of significant parenchymal features that support our hypothesis: the pulmonary parenchyma is influenced differentially by malignant versus benign nodules, assisting CAD-based nodule characterizations.

Paper Details

Date Published: 1 September 2015
PDF: 10 pages
J. Med. Img. 2(4) 041004 doi: 10.1117/1.JMI.2.4.041004
Published in: Journal of Medical Imaging Volume 2, Issue 4
Show Author Affiliations
Samantha K. Dilger, The Univ. of Iowa Hospitals and Clinics (United States)
Johanna Uthoff, The Univ. of Iowa Hospitals and Clinics (United States)
Alexandra Judisch, The Univ. of Iowa (United States)
Emily Hammond, The Univ. of Iowa Hospitals and Clinics (United States)
Sarah L. Mott, The Univ. of Iowa Hospitals and Clinics (United States)
Brian J. Smith, The Univ. of Iowa (United States)
John D. Newell, The Univ. of Iowa Hospitals and Clinics (United States)
Univ. of Iowa (United States)
Eric A. Hoffman, The Univ. of Iowa Hospitals and Clinics (United States)
Univ. of Iowa (United States)
Jessica C. Sieren, The Univ. of Iowa (United States)


© SPIE. Terms of Use
Back to Top