Reproducibility and accuracy of optic nerve sheath diameter assessment using ultrasound compared to magnetic resonance imaging

Abstract

Background: Quantification of the optic nerve sheath diameter (ONSD) by transbulbar sonography is a promising non-invasive technique for the detection of altered intracranial pressure. In order to establish this method as follow-up tool in diseases with intracranial hyper- or hypotension scan-rescan reproducibility and accuracy need to be systematically investigated.

Methods: The right ONSD of 15 healthy volunteers (mean age 24.5 ± 0.8 years) were measured by both transbulbar sonography (9 - 3 MHz) and 3 Tesla MRI (half-Fourier acquisition single-shot turbo spin-echo sequences, HASTE) 3 and 5 mm behind papilla. All volunteers underwent repeated ultrasound and MRI examinations in order to assess scan-rescan reproducibility and accuracy. Moreover, inter- and intra-observer variabilities were calculated for both techniques.

Results: Scan-rescan reproducibility was robust for ONSD quantification by sonography and MRI at both depths (r > 0.75, p ≤ 0.001, mean differences < 2%). Comparing ultrasound- and MRI-derived ONSD values, we found acceptable agreement between both methods for measurements at a depth of 3 mm (r = 0.72, p = 0.002, mean difference < 5%). Further analyses revealed good inter- and intra-observer reliability for sonographic measurements 3 mm behind the papilla and for MRI at 3 and 5 mm (r > 0.82, p < 0.001, mean differences < 5%).

Conclusions: Sonographic ONSD quantification 3 mm behind the papilla can be performed with good reproducibility, measurement accuracy and observer agreement. Thus, our findings emphasize the feasibility of this technique as a non-invasive bedside tool for longitudinal ONSD measurements.

Figure 1

Transbulbar sonography and MRI of the optic nerve sheath. (A) The eye bulb and the optic nerve are displayed by B-mode sonography. The optic nerve sheath diameter was measured 3 and 5 mm behind the papilla (dotted arrow) in an axial plane showing the optic nerve in its longitudinal course. Transverse (B) and sagital (C) T2-weighted TSE sequences were created to schedule coronal and orthogonal HASTE sequences of the optic nerve sheath 3 mm (D) and 5 mm (E) behind the papilla.

Figure 2

Reproducibility and accuracy of ONSD assessment. Bland-Altman plots displaying the agreement of scan-rescan measurements of the optic nerve sheath diameter (ONSD) 3 mm behind the papilla by transorbital sonography (A) and MRI (B). Panel C demonstrates the agreement between sonographic and MRI-based ONSD quantification at the first visit. Continuous lines depict the mean of differences; dashed lines denote limits of agreement (mean ± 1.96 times of standard deviation).