Skip to main content
Erschienen in: Journal of Digital Imaging 2/2020

03.12.2019

A Comparison of the Efficiency of Using a Deep CNN Approach with Other Common Regression Methods for the Prediction of EGFR Expression in Glioblastoma Patients

verfasst von: Mohammadreza Hedyehzadeh, Keivan Maghooli, Mohammad MomenGharibvand, Stephen Pistorius

Erschienen in: Journal of Imaging Informatics in Medicine | Ausgabe 2/2020

Einloggen, um Zugang zu erhalten

Abstract

To estimate epithermal growth factor receptor (EGFR) expression level in glioblastoma (GBM) patients using radiogenomic analysis of magnetic resonance images (MRI). A comparative study using a deep convolutional neural network (CNN)–based regression, deep neural network, least absolute shrinkage and selection operator (LASSO) regression, elastic net regression, and linear regression with no regularization was carried out to estimate EGFR expression of 166 GBM patients. Except for the deep CNN case, overfitting was prevented by using feature selection, and loss values for each method were compared. The loss values in the training phase for deep CNN, deep neural network, Elastic net, LASSO, and the linear regression with no regularization were 2.90, 8.69, 7.13, 14.63, and 21.76, respectively, while in the test phase, the loss values were 5.94, 10.28, 13.61, 17.32, and 24.19 respectively. These results illustrate that the efficiency of the deep CNN approach is better than that of the other methods, including Lasso regression, which is a regression method known for its advantage in high-dimension cases. A comparison between deep CNN, deep neural network, and three other common regression methods was carried out, and the efficiency of the CNN deep learning approach, in comparison with other regression models, was demonstrated.
Literatur
1.
Zurück zum Zitat Jemal A, Siegel R, Xu J, Ward E: Cancer Statistics. CA Cancer J Clin 60:277–300, 2017CrossRef Jemal A, Siegel R, Xu J, Ward E: Cancer Statistics. CA Cancer J Clin 60:277–300, 2017CrossRef
3.
Zurück zum Zitat Stupp R, Weller M, Belanger K et al.: Radiotherapy plus concomitant and adjuvant temozolomide for glioblastoma. N Engl J Med 10:987–996, 2005CrossRef Stupp R, Weller M, Belanger K et al.: Radiotherapy plus concomitant and adjuvant temozolomide for glioblastoma. N Engl J Med 10:987–996, 2005CrossRef
4.
Zurück zum Zitat Young RJ, Gupta A, Shah AD et al.: Potential role of preoperative conventional MRI including diffusion measurements in assessing epidermal growth factor receptor gene amplification status in patients with glioblastoma. AJNR Am J Neuroradiol 34:2271–2277, 2013CrossRef Young RJ, Gupta A, Shah AD et al.: Potential role of preoperative conventional MRI including diffusion measurements in assessing epidermal growth factor receptor gene amplification status in patients with glioblastoma. AJNR Am J Neuroradiol 34:2271–2277, 2013CrossRef
5.
Zurück zum Zitat Rock K, Mcardle O, Forde P et al.: A clinical review of treatment outcomes in glioblastoma multiforme--the validation in a non-trial population of the results of a randomised Phase III clinical trial: has a more radical approach improved survival? Br J Radiol 85:729–733, 2012CrossRef Rock K, Mcardle O, Forde P et al.: A clinical review of treatment outcomes in glioblastoma multiforme--the validation in a non-trial population of the results of a randomised Phase III clinical trial: has a more radical approach improved survival? Br J Radiol 85:729–733, 2012CrossRef
6.
Zurück zum Zitat Kleihues P, Burger PC, Scheithauer BW: The new WHO classification of brain tumours. Brain Pathol Zurich Switz 3:255–268, 1993CrossRef Kleihues P, Burger PC, Scheithauer BW: The new WHO classification of brain tumours. Brain Pathol Zurich Switz 3:255–268, 1993CrossRef
7.
Zurück zum Zitat Davis SC, Samkoe KS, O’Hara JA et al.: MRI-coupled fluorescence tomography quantifies EGFR activity in brain tumors. Acad Radiol 17:271–276, 2010CrossRef Davis SC, Samkoe KS, O’Hara JA et al.: MRI-coupled fluorescence tomography quantifies EGFR activity in brain tumors. Acad Radiol 17:271–276, 2010CrossRef
8.
Zurück zum Zitat Ramos-Suzarte M, Lorenzo-Luaces P, Lazo NG et al.: Treatment of malignant, non-resectable, epithelial origin esophageal tumours with the humanized anti-epidermal growth factor antibody nimotuzumab combined with radiation therapy and chemotherapy. Cancer Biol Ther 13:600–605, 2012CrossRef Ramos-Suzarte M, Lorenzo-Luaces P, Lazo NG et al.: Treatment of malignant, non-resectable, epithelial origin esophageal tumours with the humanized anti-epidermal growth factor antibody nimotuzumab combined with radiation therapy and chemotherapy. Cancer Biol Ther 13:600–605, 2012CrossRef
10.
Zurück zum Zitat Zhou M, Leung A, Echegaray S et al.: Non-small cell lung cancer radiogenomics map identifies relationships between molecular and imaging phenotypes with prognostic implications. Radiology 286:307–315, 2018CrossRef Zhou M, Leung A, Echegaray S et al.: Non-small cell lung cancer radiogenomics map identifies relationships between molecular and imaging phenotypes with prognostic implications. Radiology 286:307–315, 2018CrossRef
11.
Zurück zum Zitat Zhu Z, Albadawy E, Saha A, et al: Deep learning for identifying radiogenomic associations in breast cancer.Computers in biology and medicine, 109, 85–90, Cs, 2019 Zhu Z, Albadawy E, Saha A, et al: Deep learning for identifying radiogenomic associations in breast cancer.Computers in biology and medicine, 109, 85–90, Cs, 2019
13.
Zurück zum Zitat Aghi M: Magnetic resonance imaging characteristics predict epidermal growth factor receptor amplification status in glioblastoma. Clin Cancer Res 11:8600–8605, 2005CrossRef Aghi M: Magnetic resonance imaging characteristics predict epidermal growth factor receptor amplification status in glioblastoma. Clin Cancer Res 11:8600–8605, 2005CrossRef
14.
Zurück zum Zitat Gupta A, Young RJ, Shah AD et al.: Pretreatment dynamic susceptibility contrast MRI perfusion in glioblastoma: prediction of EGFR gene amplification. Clin Neuroradiol 25:143–150, 2015CrossRef Gupta A, Young RJ, Shah AD et al.: Pretreatment dynamic susceptibility contrast MRI perfusion in glioblastoma: prediction of EGFR gene amplification. Clin Neuroradiol 25:143–150, 2015CrossRef
15.
Zurück zum Zitat Li Y, Liu X, Xu K et al.: MRI features can predict EGFR expression in lower grade gliomas: a voxel-based radiomic analysis. Eur Radiol 28:356–362, 2018CrossRef Li Y, Liu X, Xu K et al.: MRI features can predict EGFR expression in lower grade gliomas: a voxel-based radiomic analysis. Eur Radiol 28:356–362, 2018CrossRef
18.
Zurück zum Zitat Yu D, Zhou M, Yang F, Dong D, Gevaert O, Liu Z, Shi J, Tian J: Conolutional neural networks for predicting molecular profiles of non small cell lung cancer. In 2017 IEEE 14th International Symposium on Biomedical Imaging, (pp. 569–572) Yu D, Zhou M, Yang F, Dong D, Gevaert O, Liu Z, Shi J, Tian J: Conolutional neural networks for predicting molecular profiles of non small cell lung cancer. In 2017 IEEE 14th International Symposium on Biomedical Imaging, (pp. 569–572)
19.
Zurück zum Zitat Korfiatis P, Erickson B: Deep learning can see the unseeable: predicting molecular markers from MRI of brain gliomas. J Clin Radiol 74:367–373, 2019CrossRef Korfiatis P, Erickson B: Deep learning can see the unseeable: predicting molecular markers from MRI of brain gliomas. J Clin Radiol 74:367–373, 2019CrossRef
20.
Zurück zum Zitat Chin L, Meyerson M, Aldape K, Bigner D: Comprehensive genomic characterization defines human glioblastoma genes and core pathways. Nature 455:1061–1068, 2008CrossRef Chin L, Meyerson M, Aldape K, Bigner D: Comprehensive genomic characterization defines human glioblastoma genes and core pathways. Nature 455:1061–1068, 2008CrossRef
21.
Zurück zum Zitat Clark K, Vendt B, Smith K et al.: The cancer imaging archive (TCIA): maintaining and operating a public information repository. J Digit Imaging 26:1045–1057, 2013CrossRef Clark K, Vendt B, Smith K et al.: The cancer imaging archive (TCIA): maintaining and operating a public information repository. J Digit Imaging 26:1045–1057, 2013CrossRef
22.
23.
24.
Zurück zum Zitat Gevaert O, Mitchell LA, Achrol AS et al.: Glioblastoma multiforme: exploratory radiogenomic analysis by using quantitative image features. Radiology 273:168–174, 2014CrossRef Gevaert O, Mitchell LA, Achrol AS et al.: Glioblastoma multiforme: exploratory radiogenomic analysis by using quantitative image features. Radiology 273:168–174, 2014CrossRef
25.
Zurück zum Zitat Akkus Z, Ali I, Sedlář J et al.: Predicting deletion of chromosomal arms 1p/19q in low-grade gliomas from MR images using machine intelligence. J Digit Imaging 30:469–476, 2017CrossRef Akkus Z, Ali I, Sedlář J et al.: Predicting deletion of chromosomal arms 1p/19q in low-grade gliomas from MR images using machine intelligence. J Digit Imaging 30:469–476, 2017CrossRef
26.
Zurück zum Zitat Korfiatis P, Kline TL, Lachance DH et al.: Residual deep convolutional neural network predicts MGMT methylation status. J Digit Imaging 30:622–628, 2017CrossRef Korfiatis P, Kline TL, Lachance DH et al.: Residual deep convolutional neural network predicts MGMT methylation status. J Digit Imaging 30:622–628, 2017CrossRef
28.
Zurück zum Zitat Kursa MB, Rudnicki WR: Feature selection with the Boruta package. J Stat Softw 36:1–13, 2010CrossRef Kursa MB, Rudnicki WR: Feature selection with the Boruta package. J Stat Softw 36:1–13, 2010CrossRef
30.
Zurück zum Zitat Liu W, Lin R, Yang M: Robust elastic net regression. ArXiv151104690 Cs Stat, 2015 Liu W, Lin R, Yang M: Robust elastic net regression. ArXiv151104690 Cs Stat, 2015
Metadaten
Titel
A Comparison of the Efficiency of Using a Deep CNN Approach with Other Common Regression Methods for the Prediction of EGFR Expression in Glioblastoma Patients
verfasst von
Mohammadreza Hedyehzadeh
Keivan Maghooli
Mohammad MomenGharibvand
Stephen Pistorius
Publikationsdatum
03.12.2019
Verlag
Springer International Publishing
Erschienen in
Journal of Imaging Informatics in Medicine / Ausgabe 2/2020
Print ISSN: 2948-2925
Elektronische ISSN: 2948-2933
DOI
https://doi.org/10.1007/s10278-019-00290-4

Weitere Artikel der Ausgabe 2/2020

Journal of Digital Imaging 2/2020 Zur Ausgabe

Update Radiologie

Bestellen Sie unseren Fach-Newsletter und bleiben Sie gut informiert.