Format

Send to

Choose Destination
Cancer Lett. 2017 Sep 10;403:21-27. doi: 10.1016/j.canlet.2017.06.004. Epub 2017 Jun 10.

Radiomic machine-learning classifiers for prognostic biomarkers of advanced nasopharyngeal carcinoma.

Author information

1
Medical Imaging Center, First Affiliated Hospital of Jinan University, Guangzhou, Guangdong, PR China; Institute of Molecular and Functional Imaging, Jinan University, Guangzhou, Guangdong, PR China.
2
Department of Mathematics, City University of Hong Kong, PR China.
3
Department of Radiology, The First People's Hospital of Shunde, Foshan, Guangdong, PR China.
4
Key Laboratory of Molecular Imaging, Chinese Academy of Science, Beijing, PR China.
5
Department of Radiology, Guangdong General Hospital/Guangdong Academy of Medical Sciences, Guangzhou, Guangdong, PR China; Shantou University Medical College, Guangdong, PR China.
6
Department of Radiology, Guangdong General Hospital/Guangdong Academy of Medical Sciences, Guangzhou, Guangdong, PR China.
7
Department of Radiology, Guangdong General Hospital/Guangdong Academy of Medical Sciences, Guangzhou, Guangdong, PR China; School of Medicine, South China University of Technology, Guangzhou, Guangdong, PR China.
8
Key Laboratory of Molecular Imaging, Chinese Academy of Science, Beijing, PR China. Electronic address: jie.tian@ia.ac.cn.
9
Medical Imaging Center, First Affiliated Hospital of Jinan University, Guangzhou, Guangdong, PR China; Institute of Molecular and Functional Imaging, Jinan University, Guangzhou, Guangdong, PR China. Electronic address: shui7515@126.com.

Abstract

We aimed to identify optimal machine-learning methods for radiomics-based prediction of local failure and distant failure in advanced nasopharyngeal carcinoma (NPC). We enrolled 110 patients with advanced NPC. A total of 970 radiomic features were extracted from MRI images for each patient. Six feature selection methods and nine classification methods were evaluated in terms of their performance. We applied the 10-fold cross-validation as the criterion for feature selection and classification. We repeated each combination for 50 times to obtain the mean area under the curve (AUC) and test error. We observed that the combination methods Random Forest (RF) + RF (AUC, 0.8464 ± 0.0069; test error, 0.3135 ± 0.0088) had the highest prognostic performance, followed by RF + Adaptive Boosting (AdaBoost) (AUC, 0.8204 ± 0.0095; test error, 0.3384 ± 0.0097), and Sure Independence Screening (SIS) + Linear Support Vector Machines (LSVM) (AUC, 0.7883 ± 0.0096; test error, 0.3985 ± 0.0100). Our radiomics study identified optimal machine-learning methods for the radiomics-based prediction of local failure and distant failure in advanced NPC, which could enhance the applications of radiomics in precision oncology and clinical practice.

KEYWORDS:

Imaging; Machine-learning; Nasopharyngeal carcinoma; Radiomics

PMID:
28610955
DOI:
10.1016/j.canlet.2017.06.004
[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Elsevier Science
Loading ...
Support Center