Radiomics Analysis Using Stability Selection Supervised Component Analysis for Right-censored Survival Data

Overview

Journal Comput Biol Med

Publisher Elsevier

Specialties Biology
General Medicine
Medical Informatics

Date 2020 Sep 9

PMID 32905923

Citations 7

Authors

Kang K Yan

Xiaofei Wang

Wendy W T Lam

Varut Vardhanabhuti

Anne W M Lee

Herbert H Pang

Affiliations

Soon will be listed here.

Abstract

Radiomics is a newly emerging field that involves the extraction of massive quantitative features from biomedical images by using data-characterization algorithms. Distinctive imaging features identified from biomedical images can be used for prognosis and therapeutic response prediction, and they can provide a noninvasive approach for personalized therapy. So far, many of the published radiomics studies utilize existing out of the box algorithms to identify the prognostic markers from biomedical images that are not specific to radiomics data. To better utilize biomedical images, we propose a novel machine learning approach, stability selection supervised principal component analysis (SSSuperPCA) that identifies stable features from radiomics big data coupled with dimension reduction for right-censored survival outcomes. The proposed approach allows us to identify a set of stable features that are highly associated with the survival outcomes in a simple yet meaningful manner, while controlling the per-family error rate. We evaluate the performance of SSSuperPCA using simulations and real data sets for non-small cell lung cancer and head and neck cancer, and compare it with other machine learning algorithms. The results demonstrate that our method has a competitive edge over other existing methods in identifying the prognostic markers from biomedical imaging data for the prediction of right-censored survival outcomes.

Citing Articles

aXonica: A support package for MRI based Neuroimaging.

Wajid B, Jamil M, Awan F, Anwar F, Anwar A Biotechnol Notes. 2024; 5:120-136.

PMID: 39416698 PMC: 11446389. DOI: 10.1016/j.biotno.2024.08.001.

Deep learning and machine learning predictive models for neurological function after interventional embolization of intracranial aneurysms.

Peng Y, Wang Y, Wen Z, Xiang H, Guo L, Su L Front Neurol. 2024; 15:1321923.

PMID: 38327618 PMC: 10848172. DOI: 10.3389/fneur.2024.1321923.

Interpretable Machine Learning for Choosing Radiation Dose-volume Constraints on Cardio-pulmonary Substructures Associated with Overall Survival in NRG Oncology RTOG 0617.

Lee S, Geng H, Arnold J, Caruana R, Fan Y, Rosen M Int J Radiat Oncol Biol Phys. 2023; 117(5):1270-1286.

PMID: 37343707 PMC: 10728350. DOI: 10.1016/j.ijrobp.2023.06.009.

Artificial intelligence-driven radiomics study in cancer: the role of feature engineering and modeling.

Zhang Y, Zhang X, Cheng Y, Li B, Teng X, Zhang J Mil Med Res. 2023; 10(1):22.

PMID: 37189155 PMC: 10186733. DOI: 10.1186/s40779-023-00458-8.

Predicting transient ischemic attack risk in patients with mild carotid stenosis using machine learning and CT radiomics.

Xia H, Yuan L, Zhao W, Zhang C, Zhao L, Hou J Front Neurol. 2023; 14:1105616.

PMID: 36846119 PMC: 9944715. DOI: 10.3389/fneur.2023.1105616.

References

Huang Y, Liu Z, He L, Chen X, Pan D, Ma Z . Radiomics Signature: A Potential Biomarker for the Prediction of Disease-Free Survival in Early-Stage (I or II) Non-Small Cell Lung Cancer. Radiology. 2016; 281(3):947-957. DOI: 10.1148/radiol.2016152234. View

Friedman J, Hastie T, Tibshirani R . Regularization Paths for Generalized Linear Models via Coordinate Descent. J Stat Softw. 2010; 33(1):1-22. PMC: 2929880. View

Mayr A, Hofner B, Schmid M . Boosting the discriminatory power of sparse survival models via optimization of the concordance index and stability selection. BMC Bioinformatics. 2016; 17:288. PMC: 4957316. DOI: 10.1186/s12859-016-1149-8. View

Shaikh F, Kolowitz B, Awan O, Aerts H, von Reden A, Halabi S . Technical Challenges in the Clinical Application of Radiomics. JCO Clin Cancer Inform. 2019; 1:1-8. DOI: 10.1200/CCI.17.00004. View

Kickingereder P, Gotz M, Muschelli J, Wick A, Neuberger U, Shinohara R . Large-scale Radiomic Profiling of Recurrent Glioblastoma Identifies an Imaging Predictor for Stratifying Anti-Angiogenic Treatment Response. Clin Cancer Res. 2016; 22(23):5765-5771. PMC: 5503450. DOI: 10.1158/1078-0432.CCR-16-0702. View

Uno H, Cai T, Pencina M, DAgostino R, Wei L . On the C-statistics for evaluating overall adequacy of risk prediction procedures with censored survival data. Stat Med. 2011; 30(10):1105-17. PMC: 3079915. DOI: 10.1002/sim.4154. View

Bonte S, Goethals I, Van Holen R . Machine learning based brain tumour segmentation on limited data using local texture and abnormality. Comput Biol Med. 2018; 98:39-47. DOI: 10.1016/j.compbiomed.2018.05.005. View

Pang H, Datta D, Zhao H . Pathway analysis using random forests with bivariate node-split for survival outcomes. Bioinformatics. 2009; 26(2):250-8. PMC: 2804301. DOI: 10.1093/bioinformatics/btp640. View

Aerts H, Velazquez E, Leijenaar R, Parmar C, Grossmann P, Carvalho S . Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun. 2014; 5:4006. PMC: 4059926. DOI: 10.1038/ncomms5006. View

10.

Leger S, Zwanenburg A, Pilz K, Lohaus F, Linge A, Zophel K . A comparative study of machine learning methods for time-to-event survival data for radiomics risk modelling. Sci Rep. 2017; 7(1):13206. PMC: 5643429. DOI: 10.1038/s41598-017-13448-3. View

11.

Zdilar L, Vock D, Marai G, Fuller C, Mohamed A, Elhalawani H . Evaluating the Effect of Right-Censored End Point Transformation for Radiomic Feature Selection of Data From Patients With Oropharyngeal Cancer. JCO Clin Cancer Inform. 2019; 2:1-19. PMC: 6354589. DOI: 10.1200/CCI.18.00052. View

12.

Chen X, Wang L, Smith J, Zhang B . Supervised principal component analysis for gene set enrichment of microarray data with continuous or survival outcomes. Bioinformatics. 2008; 24(21):2474-81. PMC: 2732277. DOI: 10.1093/bioinformatics/btn458. View

13.

Lu M, Lee H, Hadley D, Huang J, Qian X . Supervised categorical principal component analysis for genome-wide association analyses. BMC Genomics. 2014; 15 Suppl 1:S10. PMC: 4046680. DOI: 10.1186/1471-2164-15-S1-S10. View

14.

Clark K, Vendt B, Smith K, Freymann J, Kirby J, Koppel P . The Cancer Imaging Archive (TCIA): maintaining and operating a public information repository. J Digit Imaging. 2013; 26(6):1045-57. PMC: 3824915. DOI: 10.1007/s10278-013-9622-7. View

15.

Saad M, Choi T . Deciphering unclassified tumors of non-small-cell lung cancer through radiomics. Comput Biol Med. 2017; 91:222-230. DOI: 10.1016/j.compbiomed.2017.10.029. View

16.

Ma S, Huang J . Regularized ROC method for disease classification and biomarker selection with microarray data. Bioinformatics. 2005; 21(24):4356-62. DOI: 10.1093/bioinformatics/bti724. View

17.

Kurata Y, Nishio M, Kido A, Fujimoto K, Yakami M, Isoda H . Automatic segmentation of the uterus on MRI using a convolutional neural network. Comput Biol Med. 2019; 114:103438. DOI: 10.1016/j.compbiomed.2019.103438. View

18.

Zhao L, Feng D . Deep Neural Networks for Survival Analysis Using Pseudo Values. IEEE J Biomed Health Inform. 2020; 24(11):3308-3314. PMC: 8056290. DOI: 10.1109/JBHI.2020.2980204. View

19.

Cheng J, Mo X, Wang X, Parwani A, Feng Q, Huang K . Identification of topological features in renal tumor microenvironment associated with patient survival. Bioinformatics. 2017; 34(6):1024-1030. PMC: 7263397. DOI: 10.1093/bioinformatics/btx723. View

20.

Vallieres M, Freeman C, Skamene S, El Naqa I . A radiomics model from joint FDG-PET and MRI texture features for the prediction of lung metastases in soft-tissue sarcomas of the extremities. Phys Med Biol. 2015; 60(14):5471-96. DOI: 10.1088/0031-9155/60/14/5471. View