MRI Findings in Tumefactive Demyelinating Lesions: A Systematic Review and Meta-Analysis

Abstract

Background: Accurate diagnosis of tumefactive demyelinating lesions is clinically important to avoid unnecessary invasive biopsy or inappropriate treatment.

Purpose: We aimed to evaluate conventional and advanced MR imaging findings of tumefactive demyelinating lesions and determine the diagnostic performance of MR imaging for differentiating tumefactive demyelinating lesions from primary brain tumor.

Data sources: A systematic search of Ovid MEDLINE and EMBASE up to December 6, 2017, was conducted.

Study selection: Original articles describing MR imaging findings in patients with tumefactive demyelinating lesions were selected.

Data analysis: The pooled incidences of conventional MR imaging findings of tumefactive demyelinating lesions were obtained with the DerSimonian and Liard random-effects model. The pooled sensitivity and specificity of MR imaging for differentiating tumefactive demyelinating lesions from primary brain tumor were obtained using the bivariate random-effects model.

Data synthesis: Nineteen eligible studies with 476 patients with tumefactive demyelinating lesions were included. The pooled incidence of open ring or incomplete rim enhancement was 35% (95% CI, 24%-47%), which was significantly higher than the incidence of closed ring or complete rim enhancement (18% [95% CI, 11%-29%]; P = .0281). The pooled incidences of T2 hypointense rim, absent or mild mass effect, and absent or mild perilesional edema were 48%, 67%, and 57%, respectively. On advanced MR imaging, tumefactive demyelinating lesions showed a high apparent diffusion coefficient, peripheral restricted diffusion, and low cerebral blood volume. The pooled sensitivity and specificity of MR imaging for differentiating tumefactive demyelinating lesions from primary brain tumor were 89% (95% CI, 82%-93%) and 94% (95% CI, 89%-97%), respectively.

Limitations: Seventeen of 19 studies were retrospective studies.

Conclusions: Conventional MR imaging findings may help differentiate tumefactive demyelinating lesions from primary brain tumor, though further study is needed to determine the added value of advanced MR imaging.

Fig 1.

Flow diagram for the literature-selection process.

Fig 2.

Forest plots to show the pooled incidences of conventional MR imaging findings in patients with TDL: open ring or incomplete rim enhancement (A), closed ring or complete rim enhancement (B), T2 hypointense rim (C), absent or mild mass effect (D), and absent or mild perilesional edema (E). Numbers are estimates with 95% confidence intervals in parentheses.

Fig 3.

Images obtained in a 44-year-old man with biopsy-proved TDL. T2-weighted (A) and FLAIR (B) images show a well-defined high-signal-intensity lesion in the left cerebral hemisphere with mild perilesional edema. C, Contrast-enhanced T1-weighted image shows open ring enhancement. DWI (D) and the corresponding ADC map (E) reveal high ADC within the lesion and peripheral restricted diffusion. F, DSC demonstrates low cerebral blood volume.

Fig 4.

Coupled forest plots of the sensitivity and specificity of MR Imaging for the diagnosis of a TDL. Numbers are estimates with 95% confidence intervals in parentheses.