Radiomics based on multicontrast MRI can precisely differentiate among glioma subtypes and predict tumour-proliferative behaviour
To explore the feasibility and diagnostic performance of radiomics based on anatomical, diffusion and perfusion MRI in differentiating among glioma subtypes and predicting tumour proliferation.
220 pathology-confirmed gliomas and ten contrasts were included in the retrospective analysis. After being registered to T2FLAIR images and resampling to 1 mm3 isotropically, 431 radiomics features were extracted from each contrast map within a semi-automatic defined tumour volume. For single-contrast and the combination of all contrasts, correlations between the radiomics features and pathological biomarkers were revealed by partial correlation analysis, and multivariate models were built to identify the best predictive models with adjusted 0.632+ bootstrap AUC.
In univariate analysis, both non-wavelet and wavelet radiomics features were correlated significantly with tumour grade and the Ki-67 labelling index. The max R was 0.557 (p = 2.04E-14) in T1C for tumour grade and 0.395 (p = 2.33E-07) in ADC for Ki-67. In the multivariate analysis, the combination of all-contrast radiomics features had the highest AUCs in both differentiating among glioma subtypes and predicting proliferation compared with those in single-contrast images. For low-/high-grade gliomas, the best AUC was 0.911. In differentiating among glioma subtypes, the best AUC was 0.896 for grades II–III, 0.997 for grades II–IV, and 0.881 for grades III–IV. In predicting proliferation levels, multicontrast features led to an AUC of 0.936.
Multicontrast radiomics supplies complementary information on both geometric characters and molecular biological traits, which correlated significantly with tumour grade and proliferation. Combining all-contrast radiomics models might precisely predict glioma biological behaviour, which may be attributed to presurgical personal diagnosis.
• Multicontrast MRI radiomics features are significantly correlated with tumour grade and Ki-67 LI.
• Multimodality MRI provides independent but supplemental information in assessing glioma pathological behaviour.
• Combined multicontrast MRI radiomics can precisely predict glioma subtypes and proliferation levels.
KeywordsRadiomics Glioma Neoplasm grading Cell proliferation Magnetic resonance imaging
Apparent diffusion coefficient
Arterial spin labelling imaging
Cerebral blood flow
Exponential apparent diffusion coefficient
Fluid-attenuated inversion recovery
Contrast-enhanced T1-weighted images
T2-weighted fast-echo images
Volume of interest
We acknowledge Dr. M Vallières for his patient responses regarding the radiomics data post-processing. We also acknowledge Dr. Yang Fan from General Electric Company (China) for his generous contributions to manuscript revision. We also thank Dr. Xiaowei Chen (10 years’ experience) for his generous work in checking the VOIs.
This study has received funding by the National Program of the Ministry of Science and Technology of China during the “12th Five-Year Plan” (ID: 2011BAI08B10) and the National Natural Science Foundation of China (No. 81171308, No. 81570462, and No. 81730049)
Compliance with ethical standards
The scientific guarantor of this publication is Wenzhen Zhu.
Conflict of interest
The authors of this manuscript declare no relationships with any companies whose products or services may be related to the subject matter of the article.
Statistics and biometry
One of the authors has significant statistical expertise.
Written informed consent was obtained from all subjects (patients) in this study.
Institutional Review Board approval was obtained.
• Performed at one institution
- 1.van den Bent MJ (2014) Practice changing mature results of RTOG study 9802: another positive PCV trial makes adjuvant chemotherapy part of standard of care in low-grade glioma. Neuro Oncol 16:1570–1574Google Scholar
- 5.Gerdes J, Lemke H, Baisch H, Wacker HH, Schwab U, Stein H (1984) Cell cycle analysis of a cell proliferation-associated human nuclear antigen defined by the monoclonal antibody Ki-67. J Immunol 133:1710–1715Google Scholar
- 6.Chen WJ, He DS, Tang RX, Ren FH, Chen G (2015) Ki-67 is a valuable prognostic factor in gliomas: evidence from a systematic review and meta-analysis. Asian Pac J Cancer Prev 16:411–420Google Scholar
- 11.Krabbe K, Gideon P, Wagn P, Hansen U, Thomsen C, Madsen F (1997) MR diffusion imaging of human intracranial tumours. Neuroradiology 39:483–489Google Scholar
- 12.Garrett ME, Nauhaus I, Marshel JH, Callaway EM (2014) Topography and areal organization of mouse visual cortex. J Neurosci 34:12587–12600Google Scholar
- 17.Li Y, Liu X, Xu K et al (2018) MRI features can predict EGFR expression in lower grade gliomas: A voxel-based radiomic analysis. Eur Radiol 28:356–362Google Scholar
- 18.Kermany DS, Goldbaum M, Cai W et al (2018) Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning. Cell Cell 172:1122–1131Google Scholar
- 20.Vallières M, Freeman CR, Skamene SR, El Naqa I (2015) 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 60:5471–5496Google Scholar
- 28.Tien RD, Felsberg GJ, Friedman H, Brown M, MacFall J (1994) MR imaging of high-grade cerebral gliomas: value of diffusion-weighted echoplanar pulse sequences. AJR Am J Roentgenol 162:671–677Google Scholar
- 33.Hwan-Ho C, Hyunjin P (2017) Classification of low-grade and high-grade glioma using multi-modal image radiomics features. 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Seogwipo, 2017, pp. 3081–3084Google Scholar
- 36.Thrall JH, Li X, Li Q et al (2018) Artificial Intelligence and Machine Learning in Radiology: Opportunities, Challenges, Pitfalls, and Criteria for Success. J Am Coll Radiol 15:504–508Google Scholar
- 37.Itakura H, Achrol AS, Mitchell LA et al (2015) Magnetic resonance image features identify glioblastoma phenotypic subtypes with distinct molecular pathway activities. Sci Transl Med 7:303ra138Google Scholar