Share Email Print
cover

Proceedings Paper • new

Identifying optimal input using multilevel radiomics and nested cross-validation for predicting pulmonary function in lung cancer patients treated with radiotherapy
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

Radiomics is a promising approach to identify patients at high risk of having pulmonary dysfunction caused by radiotherapy. This study aims to identify optimal radiomic input features for predicting pulmonary function. Forced expiratory volume in first second (FEV1) and forced vital capacity (FVC) were measured for 257 patients between 3 months prior to and 1 week after the first radiotherapy. FEV1/FVC ratio dichotomized at 70% was used as a target variable. Each patient had a radiotherapy planning CT and associated contours of gross tumor volume and left/right lungs. A total of 2,658 radiomic features were extracted and categorized into five levels: shape (S), first- (L1), second- (L2) and higher-order (L3) local texture, and global texture (G) features, as well as four multilevel groups: S+L1, S+L1+L2, S+L1+L2+L3, and S+L1+L2+L3+G. Nested cross-validation (NCV) was used to identify optimal input features. Cross-validated glmnet models optimized with unilevel or multilevel features were used to assess predictive performance on outer CV test sets. In unilevel analysis, the highest test AUC of 0.743±0.067 was obtained from NCV models optimized with L1 features. The best performance was achieved from NCV models optimized with S+L1+L2 features with AUC of 0.752±0.063. Paired Wilcoxon signed rank test results showed that AUC values of NCV models optimized with S, L2, L3, G or S+L1+L2+L3 features were statistically significantly different from those optimized with S+L1+L2 features (P<0.05). The multilevel analysis strategy will help to handle and optimize radiomic input features.

Paper Details

Date Published: 13 March 2019
PDF: 9 pages
Proc. SPIE 10950, Medical Imaging 2019: Computer-Aided Diagnosis, 109501C (13 March 2019); doi: 10.1117/12.2513083
Show Author Affiliations
Sang Ho Lee, The Johns Hopkins Univ. School of Medicine (United States)
Peijin Han, The Johns Hopkins Univ. School of Medicine (United States)
Russell K. Hales, The Johns Hopkins Univ. School of Medicine (United States)
K. Ranh Voong, The Johns Hopkins Univ. School of Medicine (United States)
Todd R. McNutt, The Johns Hopkins Univ. School of Medicine (United States)
Junghoon Lee, The Johns Hopkins Univ. School of Medicine (United States)


Published in SPIE Proceedings Vol. 10950:
Medical Imaging 2019: Computer-Aided Diagnosis
Kensaku Mori; Horst K. Hahn, Editor(s)

© SPIE. Terms of Use
Back to Top