Share Email Print
cover

Proceedings Paper

Radiomic texture-curvature (RTC) features for precision medicine of patients with rheumatoid arthritis-associated interstitial lung disease
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

We investigated the effect of radiomic texture-curvature (RTC) features of lung CT images in the prediction of the overall survival of patients with rheumatoid arthritis-associated interstitial lung disease (RA-ILD). We retrospectively collected 70 RA-ILD patients who underwent thin-section lung CT and serial pulmonary function tests. After the extraction of the lung region, we computed hyper-curvature features that included the principal curvatures, curvedness, bright/dark sheets, cylinders, blobs, and curvature scales for the bronchi and the aerated lungs. We also computed gray-level co-occurrence matrix (GLCM) texture features on the segmented lungs. An elastic-net penalty method was used to select and combine these features with a Cox proportional hazards model for predicting the survival of the patient. Evaluation was performed by use of concordance index (C-index) as a measure of prediction performance. The C-index values of the texture features, hyper-curvature features, and the combination thereof (RTC features) in predicting patient survival was estimated by use of bootstrapping with 2,000 replications, and they were compared with an established clinical prognostic biomarker known as the gender, age, and physiology (GAP) index by means of two-sided t-test. Bootstrap evaluation yielded the following C-index values for the clinical and radiomic features: (a) GAP index: 78.3%; (b) GLCM texture features: 79.6%; (c) hypercurvature features: 80.8%; and (d) RTC features: 86.8%. The RTC features significantly outperformed any of the other predictors (P < 0.001). The Kaplan-Meier survival curves of patients stratified to low- and high-risk groups based on the RTC features showed statistically significant (P < 0.0001) difference. Thus, the RTC features can provide an effective imaging biomarker for predicting the overall survival of patients with RA-ILD.

Paper Details

Date Published: 6 March 2018
PDF: 6 pages
Proc. SPIE 10579, Medical Imaging 2018: Imaging Informatics for Healthcare, Research, and Applications, 105791N (6 March 2018); doi: 10.1117/12.2294043
Show Author Affiliations
Chinatsu Watari, Massachusetts General Hospital (United States)
Harvard Medical School (United States)
Mikio Matsuhiro, Tokushima Univ. (Japan)
Massachusetts General Hospital (United States)
Harvard Medical School (United States)
Janne J. Näppi, Massachusetts General Hospital (United States)
Harvard Medical School (United States)
Radin A. Nasirudin, Massachusetts General Hospital (United States)
Harvard Medical School (United States)
Toru Hironaka, Massachusetts General Hospital (United States)
Harvard Medical School (United States)
Yoshiki Kawata, Tokushima Univ. (Japan)
Noboru Niki, Tokushima Univ. (Japan)
Hiroyuki Yoshida, Massachusetts General Hospital (United States)
Harvard Medical School (United States)


Published in SPIE Proceedings Vol. 10579:
Medical Imaging 2018: Imaging Informatics for Healthcare, Research, and Applications
Jianguo Zhang; Po-Hao Chen, Editor(s)

© SPIE. Terms of Use
Back to Top