Quantitative integration of radiomic and genomic data improves survival prediction of low-grade glioma patients

Chen Ma; Zhihao Yao; Qinran Zhang; Xiufen Zou; Chen Ma; Zhihao Yao; Qinran Zhang; Xiufen Zou

doi:10.3934/mbe.2021039

Mathematical Biosciences and Engineering

2021, Volume 18, Issue 1: 727-744. doi: 10.3934/mbe.2021039

Previous Article Next Article

Research article Special Issues

Quantitative integration of radiomic and genomic data improves survival prediction of low-grade glioma patients

School of Mathematics and Statistics, Wuhan University, Wuhan 430072, China

Received: 13 September 2020 Accepted: 06 December 2020 Published: 18 December 2020

Glioma is the most common and most serious form of brain tumors that affects adults. Accurate prediction of survival and phenotyping of low-grade glioma (LGG) patients at high or low risk are the key to achieving precision diagnosis and treatment. This study is aimed to integrate both magnetic resonance imaging (MRI) data and gene expression data to develop a new integrated measure that represents a LGG patient's disease-specific survival (DSS) and classify subsets of patients at low and high risk for progression to cancer. We first construct the gene regulatory network by using gene expression data. We obtain twelve network modules and identify eight image biomarkers by using the Cox regression model with MRI data. Furthermore, correlation analysis between gene modules and image features identify four radiomic features. The least absolute shrinkage and selection operator (Lasso) method is applied to predict these image features with gene expression data when lacking MRI data or image segmentation technology. Furthermore, the support vector machine (SVM)-based recursive feature elimination method has been established to predict DSS using gene signatures. Finally, 4 image signatures and 43 gene signatures are recognized to be associated with the patient's prognosis. An integrated measure for combining image and gene signatures is obtained through the PSO algorithm. The concordance index (C-index) and the time-dependent receiver operating characteristic (ROC) analysis are used to evaluate prediction accuracy. The C-index obtained for this integrated measure is 0.8071 and the area under the curve (AUC) of the ROC curve is 0.79, which are higher than any other single features. The 72.1$ \% $ accuracy of classification of patients is better than the accuracy associated with the published work. These results demonstrate that integration analysis of radiomic and genomic data can improve the accuracy of the prediction of survival for lower grade gliomas.
- low-grade glioma,
- MRI,
- genomic data,
- lasso model,
- network module
Citation: Chen Ma, Zhihao Yao, Qinran Zhang, Xiufen Zou. Quantitative integration of radiomic and genomic data improves survival prediction of low-grade glioma patients[J]. Mathematical Biosciences and Engineering, 2021, 18(1): 727-744. doi: 10.3934/mbe.2021039

Related Papers:

Abstract

Glioma is the most common and most serious form of brain tumors that affects adults. Accurate prediction of survival and phenotyping of low-grade glioma (LGG) patients at high or low risk are the key to achieving precision diagnosis and treatment. This study is aimed to integrate both magnetic resonance imaging (MRI) data and gene expression data to develop a new integrated measure that represents a LGG patient's disease-specific survival (DSS) and classify subsets of patients at low and high risk for progression to cancer. We first construct the gene regulatory network by using gene expression data. We obtain twelve network modules and identify eight image biomarkers by using the Cox regression model with MRI data. Furthermore, correlation analysis between gene modules and image features identify four radiomic features. The least absolute shrinkage and selection operator (Lasso) method is applied to predict these image features with gene expression data when lacking MRI data or image segmentation technology. Furthermore, the support vector machine (SVM)-based recursive feature elimination method has been established to predict DSS using gene signatures. Finally, 4 image signatures and 43 gene signatures are recognized to be associated with the patient's prognosis. An integrated measure for combining image and gene signatures is obtained through the PSO algorithm. The concordance index (C-index) and the time-dependent receiver operating characteristic (ROC) analysis are used to evaluate prediction accuracy. The C-index obtained for this integrated measure is 0.8071 and the area under the curve (AUC) of the ROC curve is 0.79, which are higher than any other single features. The 72.1$ \% $ accuracy of classification of patients is better than the accuracy associated with the published work. These results demonstrate that integration analysis of radiomic and genomic data can improve the accuracy of the prediction of survival for lower grade gliomas.

References

[1]	E. B. Claus, K. M. Walsh, J. K. Wiencke, A. M. Molinaro, J. L. Wiemels, J. M. Schildkraut, et al., Survival and low-grade glioma: the emergence of genetic information, Neurosurg. Focus, 38 (2015), E6.
[2]	K. Lote, T. Egeland, B. Hager, B. Stenwig, K. Skullerud, J. Berg-Johnsen, et al., Survival, prognostic factors, and therapeutic efficacy in low-grade glioma: a retrospective study in 379 patients, J. Clin. Oncol., 15 (1997), 3129–3140.
[3]	D. Schiff, P. D. Brown, C. Giannini, Outcome in adult low-grade glioma: the impact of prognostic factors and treatment, Neurology, 69 (2007), 1366–1373. doi: 10.1212/01.wnl.0000277271.47601.a1
[4]	Z. P. Liang, P. C. Lauterbur, Principles of Magnetic Resonance Imaging: A Signal Processing Perspective, SPIE Optical Engineering Press, 2000.
[5]	F. Pignatti, M. V. Den Bent, D. Curran, C. Debruyne, R. Sylvester, P. Therasse, et al., Prognostic factors for survival in adult patients with cerebral low-grade glioma, J. Clin. Oncol., 20 (2002), 2076–2084.
[6]	T. C. Wang, Y. H. Huang, C. S. Huang, J. H. Chen, G. Y. Huang, Y. C. Chang et al., Computeraided diagnosis of breast dce-mri using pharmacokinetic model and 3-d morphology analysis, Magn. Reson. Imaging, 32 (2014), 197–205.
[7]	R. R. Agravat, M. S. Raval, Prediction of overall survival of brain tumor patients, TENCON 2019-2019 IEEE Region 10 Conference (TENCON), 2019.
[8]	Z. A. Shboul, L. Vidyaratne, M. Alam, K. M. Iftekharuddin, Glioblastoma and survival prediction, International MICCAI Brainlesion Workshop, 2017.
[9]	A. Jungo, R. Mckinley, R. Meier, U. Knecht, L. Vera, J. Perez-Beteta, et al., Towards uncertaintyassisted brain tumor segmentation and survival prediction, International MICCAI Brainlesion Workshop, 2017.
[10]	J. Sachdeva, V. Kumar, I. Gupta, N. Khandelwal, C. K. Ahuja, Segmentation, feature extraction, and multiclass brain tumor classification, J. Digital Imaging, 26 (2013), 1141–1150. doi: 10.1007/s10278-013-9600-0
[11]	L. Chato, S. Latifi, Machine learning and deep learning techniques to predict overall survival of brain tumor patients using mri images, in 2017 IEEE 17th International Conference on Bioinformatics and Bioengineering (BIBE), 2017.
[12]	S. D. Kahn, On the future of genomic data, Science, 331 (2011), 728–729. doi: 10.1126/science.1197891
[13]	H. J. Aerts, E. R. Velazquez, R. T. Leijenaar, C. Parmar, P. Lambin, Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach, Nat. Commun., 5 (2014), 1–9.
[14]	P. Grossmann, O. Stringfield, N. El-Hachem, M. M. Bui, E. R. Velazquez, C. Parmar, et al., Defining the biological basis of radiomic phenotypes in lung cancer, Elife, 6 (2017), e23421. doi: 10.7554/eLife.23421
[15]	W. Xia, Y. Chen, R. Zhang, Z. Yan, X. Zhou, B. Zhang, et al., Radiogenomics of hepatocellular carcinoma: multiregion analysis-based identification of prognostic imaging biomarkers by integrating gene data—a preliminary study, Phys. Med. Biol., 63 (2018), 035044.
[16]	S. Bakas, H. Akbari, A. Sotiras, M. Bilello, M. Rozycki, J. Kirby, et al., Segmentation labels and radiomic features for the pre-operative scans of the tcga-lgg collection, Cancer Imaging Arch., 286 (2017).
[17]	S. Bakas, H. Akbari, A. Sotiras, M. Bilello, M. Rozycki, J. Kirby, et al., Advancing the cancer genome atlas glioma mri collections with expert segmentation labels and radiomic features, Sci. Data, 4 (2017), 170117.
[18]	K. Clark, B. Vendt, K. Smith, J. Freymann, J. Kirby, P. Koppel, et al., The cancer imaging archive (tcia): Maintaining and operating a public information repository, J. Digital Imaging, 26 (2013), 1045–1057.
[19]	P. Langfelder, S. Horvath, Wgcna: an r package for weighted correlation network analysis, BMC Bioinf., 9 (2008), 559.
[20]	M. Fan, P. Xia, B. Liu, L. Zhang, Y. Wang, X. Gao, et al., Tumour heterogeneity revealed by unsupervised decomposition of dynamic contrast-enhanced magnetic resonance imaging is associated with underlying gene expression patterns and poor survival in breast cancer patients, Breast Cancer Res., 21 (2019), 112.
[21]	D. R. Cox, Regression models and life tables, J. R. Stat. Soc., 34 (1972), 187–202.
[22]	F. E. Harrell Jr, K. L. Lee, D. B. Mark, Multivariable prognostic models: issues in developing models, evaluating assumptions and adequacy, and measuring and reducing errors, Stat. Med., 15 (1996), 361–387.
[23]	F. Santosa, W. W. Symes, Linear inversion of band-limited reflection seismograms, SIAM J. Sci. Stat. Comput., 7 (1986), 1307–1330. doi: 10.1137/0907087
[24]	R. Tibshirani, Regression shrinkage and selection via the lasso, J. R. Stat. Soc. Ser. B Methodol., 58 (1996), 267–288.
[25]	C. Cortes, V. Vapnik, Support-vector networks, Mach. Learn., 20 (1995), 273–297.
[26]	N. Cristianini, J. Shawe-Taylor, An Introduction to Support Vector Machines and Other KernelBased Learning Methods, Cambridge university press, 2000.
[27]	R. E. Fan, P. H. Chen, C. J. Lin, Working set selection using second order information for training support vector machines, J. Mach. Learn. Res., 6 (2005), 1889–1918.
[28]	I. Guyon, A. J. Weston, S. Barnhill, V. Vapnik, Gene selection for cancer classification using svm, Mach. Learn. J., 46 (2002), 389–422. doi: 10.1023/A:1012487302797
[29]	J. Kennedy, R. Eberhart, Particle swarm optimization, Proceedings of ICNN'95-International Conference on Neural Networks, 1995.
[30]	Y. Zhou, B. Zhou, L. Pache, M. Chang, A. H. Khodabakhshi, O. Tanaseichuk, et al., Metascape provides a biologist-oriented resource for the analysis of systems-level datasets, Nat. Commun., 10 (2019), 1–10.
[31]	J. Pal, V. Patil, A. Kumar, K. Kaur, C. Sarkar, K. Somasundaram, Genetic landscape of glioma reveals defective neuroactive ligand receptor interaction pathway as a poor prognosticator in glioblastoma patients, AACR, 77 (2017), 2454–2454.
[32]	R. Wang, J. Wei, Z. Li, Y. Tian, C. Du, Bioinformatical analysis of gene expression signatures of different glioma subtypes, Oncol. Lett., 15 (2018), 2807–2814.
[33]	P. J. Heagerty, T. Lumley, M. S. Pepe, Time-dependent roc curves for censored survival data and a diagnostic marker, Biometrics, 56 (2000), 337–344. doi: 10.1111/j.0006-341X.2000.00337.x

Supplementary Table S1.xlsx
Supplementary Table S2.xlsx
Supplementary Table S3.xlsx
Supplementary Table S4.xlsx
Supplementary Table S5.xlsx
Supplementary Table S6.xlsx
Supplementary Table S7.xlsx

Reader Comments

Your name:*

Email:*
© 2021 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)