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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2019
Subtitle of host publicationComputer-Aided Diagnosis
EditorsKensaku Mori, Horst K. Hahn
PublisherSPIE
ISBN (Electronic)9781510625471
DOIs
StatePublished - Jan 1 2019
EventMedical Imaging 2019: Computer-Aided Diagnosis - San Diego, United States
Duration: Feb 17 2019Feb 20 2019

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume10950
ISSN (Print)1605-7422

Conference

ConferenceMedical Imaging 2019: Computer-Aided Diagnosis
CountryUnited States
CitySan Diego
Period2/17/192/20/19

Fingerprint

pulmonary functions
Radiotherapy
lungs
Area Under Curve
radiation therapy
Lung Neoplasms
cancer
Vital Capacity
Lung
Multilevel Analysis
textures
Textures
Forced Expiratory Volume
rank tests
Nonparametric Statistics
Tumor Burden
planning
Tumors
tumors
Planning

Keywords

  • CT
  • Multilevel radiomics
  • Nested cross-validation
  • Pulmonary function
  • Radiotherapy

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Atomic and Molecular Physics, and Optics
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Lee, S. H., Han, P., Hales, R. K., Voong, K. R., McNutt, T. R., & Lee, J. (2019). Identifying optimal input using multilevel radiomics and nested cross-validation for predicting pulmonary function in lung cancer patients treated with radiotherapy. In K. Mori, & H. K. Hahn (Eds.), Medical Imaging 2019: Computer-Aided Diagnosis [109501C] (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 10950). SPIE. https://doi.org/10.1117/12.2513083

Identifying optimal input using multilevel radiomics and nested cross-validation for predicting pulmonary function in lung cancer patients treated with radiotherapy. / Lee, Sang Ho; Han, Peijin; Hales, Russell K.; Voong, K. Ranh; McNutt, Todd R.; Lee, Junghoon.

Medical Imaging 2019: Computer-Aided Diagnosis. ed. / Kensaku Mori; Horst K. Hahn. SPIE, 2019. 109501C (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 10950).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lee, SH, Han, P, Hales, RK, Voong, KR, McNutt, TR & Lee, J 2019, Identifying optimal input using multilevel radiomics and nested cross-validation for predicting pulmonary function in lung cancer patients treated with radiotherapy. in K Mori & HK Hahn (eds), Medical Imaging 2019: Computer-Aided Diagnosis., 109501C, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 10950, SPIE, Medical Imaging 2019: Computer-Aided Diagnosis, San Diego, United States, 2/17/19. https://doi.org/10.1117/12.2513083
Lee SH, Han P, Hales RK, Voong KR, McNutt TR, Lee J. Identifying optimal input using multilevel radiomics and nested cross-validation for predicting pulmonary function in lung cancer patients treated with radiotherapy. In Mori K, Hahn HK, editors, Medical Imaging 2019: Computer-Aided Diagnosis. SPIE. 2019. 109501C. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE). https://doi.org/10.1117/12.2513083
Lee, Sang Ho ; Han, Peijin ; Hales, Russell K. ; Voong, K. Ranh ; McNutt, Todd R. ; Lee, Junghoon. / Identifying optimal input using multilevel radiomics and nested cross-validation for predicting pulmonary function in lung cancer patients treated with radiotherapy. Medical Imaging 2019: Computer-Aided Diagnosis. editor / Kensaku Mori ; Horst K. Hahn. SPIE, 2019. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE).
@inproceedings{02986a3275904f0cad3f06dedbe3efb1,
title = "Identifying optimal input using multilevel radiomics and nested cross-validation for predicting pulmonary function in lung cancer patients treated with radiotherapy",
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.",
keywords = "CT, Multilevel radiomics, Nested cross-validation, Pulmonary function, Radiotherapy",
author = "Lee, {Sang Ho} and Peijin Han and Hales, {Russell K.} and Voong, {K. Ranh} and McNutt, {Todd R.} and Junghoon Lee",
year = "2019",
month = "1",
day = "1",
doi = "10.1117/12.2513083",
language = "English (US)",
series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",
publisher = "SPIE",
editor = "Kensaku Mori and Hahn, {Horst K.}",
booktitle = "Medical Imaging 2019",

}

TY - GEN

T1 - Identifying optimal input using multilevel radiomics and nested cross-validation for predicting pulmonary function in lung cancer patients treated with radiotherapy

AU - Lee, Sang Ho

AU - Han, Peijin

AU - Hales, Russell K.

AU - Voong, K. Ranh

AU - McNutt, Todd R.

AU - Lee, Junghoon

PY - 2019/1/1

Y1 - 2019/1/1

N2 - 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.

AB - 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.

KW - CT

KW - Multilevel radiomics

KW - Nested cross-validation

KW - Pulmonary function

KW - Radiotherapy

UR - http://www.scopus.com/inward/record.url?scp=85068183069&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85068183069&partnerID=8YFLogxK

U2 - 10.1117/12.2513083

DO - 10.1117/12.2513083

M3 - Conference contribution

AN - SCOPUS:85068183069

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

BT - Medical Imaging 2019

A2 - Mori, Kensaku

A2 - Hahn, Horst K.

PB - SPIE

ER -