Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 May 18;11(1):10478.
doi: 10.1038/s41598-021-90032-w.

Machine learning based differentiation of glioblastoma from brain metastasis using MRI derived radiomics

Sarv Priya  1 , Yanan Liu  2 , Caitlin Ward  3 , Nam H Le  2 , Neetu Soni  4 , Ravishankar Pillenahalli Maheshwarappa  4 , Varun Monga  5 , Honghai Zhang  2 , Milan Sonka  2 , Girish Bathla  4
Affiliations

Machine learning based differentiation of glioblastoma from brain metastasis using MRI derived radiomics

Sarv Priya et al. Sci Rep. .

Abstract

Few studies have addressed radiomics based differentiation of Glioblastoma (GBM) and intracranial metastatic disease (IMD). However, the effect of different tumor masks, comparison of single versus multiparametric MRI (mp-MRI) or select combination of sequences remains undefined. We cross-compared multiple radiomics based machine learning (ML) models using mp-MRI to determine optimized configurations. Our retrospective study included 60 GBM and 60 IMD patients. Forty-five combinations of ML models and feature reduction strategies were assessed for features extracted from whole tumor and edema masks using mp-MRI [T1W, T2W, T1-contrast enhanced (T1-CE), ADC, FLAIR], individual MRI sequences and combined T1-CE and FLAIR sequences. Model performance was assessed using receiver operating characteristic curve. For mp-MRI, the best model was LASSO model fit using full feature set (AUC 0.953). FLAIR was the best individual sequence (LASSO-full feature set, AUC 0.951). For combined T1-CE/FLAIR sequence, adaBoost-full feature set was the best performer (AUC 0.951). No significant difference was seen between top models across all scenarios, including models using FLAIR only, mp-MRI and combined T1-CE/FLAIR sequence. Top features were extracted from both the whole tumor and edema masks. Shape sphericity is an important discriminating feature.

PubMed Disclaimer

Conflict of interest statement

Other conflict of interest: Girish Bathla has a research grant from Siemens AG, Forchheim, Germany as well as American Cancer Society that is unrelated to the submitted work. Rest of the authors report no relationships that could be construed as a conflict of interest.

Figures

Figure 1
Figure 1
Diagnostic performance using multiparametric MRI. Mean cross-validated ROC AUC for all 45 machine learning and feature reduction combinations using all sequences.
Figure 2
Figure 2
Diagnostic performance using FLAIR sequence. Mean AUC for all models fit using the FLAIR sequence as many of the top performing models came from this sequence.
Figure 3
Figure 3
Diagnostic performance using combined T1- contrast enhanced (T1-CE) and FLAIR sequence. Mean AUC for all models fit using the combined T1-CE and FLAIR sequences.
Figure 4
Figure 4
Feature importance. A boxplot showing the distribution of shape sphericity feature for the two tumor types on FLAIR sequence.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Artzi, M., Bressler, I. & Ben Bashat, D. Differentiation between glioblastoma, brain metastasis and subtypes using radiomics analysis. Journal of magnetic resonance imaging : JMRI50, 519–528, doi:10.1002/jmri.26643 (2019). - PubMed
    1. Bae S, et al. Robust performance of deep learning for distinguishing glioblastoma from single brain metastasis using radiomic features: model development and validation. Sci. Rep. 2020;10:12110. doi: 10.1038/s41598-020-68980-6. - DOI - PMC - PubMed
    1. Ostrom QT, et al. CBTRUS statistical report: Primary brain and other central nervous system tumors diagnosed in the United States in 2012–2016. Neuro Oncol. 2019;21:v1–v100. doi: 10.1093/neuonc/noz150. - DOI - PMC - PubMed
    1. Dong F, et al. Differentiation of supratentorial single brain metastasis and glioblastoma by using peri-enhancing oedema region-derived radiomic features and multiple classifiers. Eur. Radiol. 2020;30:3015–3022. doi: 10.1007/s00330-019-06460-w. - DOI - PubMed
    1. Skogen K, et al. Texture analysis on diffusion tensor imaging: discriminating glioblastoma from single brain metastasis. Acta Radiol. 2018 doi: 10.1177/0284185118780889. - DOI - PubMed