Primary central nervous system lymphoma and atypical glioblastoma: Differentiation using radiomics approach
To evaluate the diagnostic performance of magnetic resonance (MR) radiomics-based machine-learning algorithms in differentiating primary central nervous system lymphoma (PCNSL) from non-necrotic atypical glioblastoma (GBM).
Seventy-seven patients (54 individuals with PCNSL and 23 with non-necrotic atypical GBM), diagnosed from January 2009 to April 2017, were enrolled in this retrospective study. A total of 6,366 radiomics features, including shape, volume, first-order, texture, and wavelet-transformed features, were extracted from multi-parametric (post-contrast T1- and T2-weighted, and fluid attenuation inversion recovery images) and multiregional (enhanced and non-enhanced) tumour volumes. These features were subjected to recursive feature elimination and random forest (RF) analysis with nested cross-validation. The diagnostic abilities of a radiomics machine-learning classifier, apparent diffusion coefficient (ADC), and three readers, who independently classified the tumours based on conventional MR sequences, were evaluated using receiver operating characteristic (ROC) analysis. Areas under the ROC curves (AUC) of the radiomics classifier, ADC value, and the radiologists were compared.
The mean AUC of the radiomics classifier was 0.921 (95 % CI 0.825–0.990). The AUCs of the three readers and ADC were 0.707 (95 % CI 0.622–0.793), 0.759 (95 %CI 0.656–0.861), 0.695 (95 % CI 0.590–0.800) and 0.684 (95 % CI0.560–0.809), respectively. The AUC of the radiomics-based classifier was significantly higher than those of the three readers and ADC (p< 0.001 for all).
Large-scale radiomics with a machine-learning algorithm can be useful for differentiating PCNSL from atypical GBM, and yields a better diagnostic performance than human radiologists and ADC values.
• Machine-learning algorithm radiomics can help to differentiate primary central PCNSL from GBM.
• This approach yields a higher diagnostic accuracy than visual analysis by radiologists.
• Radiomics can strengthen radiologists’ diagnostic decisions whenever conventional MRI sequences are available.
KeywordsLymphoma Glioblastoma Machine-learning Magnetic resonance imaging Radiomics
Apparent diffusion coefficient
Area under the receiver operating characteristic curve
Field of view
Fluid-attenuation inversion recovery
Grey level co-occurrence matrix
Grey-level run length matrix
Grey-level size zone matrix
Magnetic resonance imaging
Non-enhancing tumour tissue and oedema
Primary central nervous system lymphoma
Relative cerebral blood volume
Compliance with ethical standards
The scientific guarantor of this publication is Yoon Seong Choi.
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.
Institutional Review Board approval was obtained.
Written informed consent was waived by the Institutional Review Board.
Study subjects or cohorts overlap
Some study subjects or cohorts have been previously reported in European Radiology:
Choi YS, Lee H-J, Ahn SS, et al. Primary central nervous system lymphoma and atypical glioblastoma: differentiation using the initial area under the curve derived from dynamic contrast-enhanced MR and the apparent diffusion coefficient. Eur Radiol. 2017;27(4):1344–1351
• performed at one institution
- 11.Toh CH, Wei KC, Chang CN, Ng SH, Wong HF (2013) Differentiation of primary central nervous system lymphomas and glioblastomas: comparisons of diagnostic performance of dynamic susceptibility contrast-enhanced perfusion MR imaging without and with contrast-leakage correction. AJNR Am J Neuroradiol 34:1145–1149CrossRefPubMedGoogle Scholar
- 16.Prasanna P, Patel J, Partovi S, Madabhushi A, Tiwari P (2017) Radiomic features from the peritumoral brain parenchyma on treatment-naive multi-parametric MR imaging predict long versus short-term survival in glioblastoma multiforme: Preliminary findings. Eur Radiol 27:4188–4197CrossRefPubMedGoogle Scholar