Improved localization of implanted subdural electrode contacts on magnetic resonance imaging with an elastic image fusion algorithm in an invasive electroencephalography recording.

Abstract

Accurate projection of implanted subdural electrode contacts in presurgical evaluation of pharmacoresistant epilepsy cases by invasive electroencephalography is highly relevant. Linear fusion of computed tomography and magnetic resonance images may display the contacts in the wrong position as a result of brain shift effects. A retrospective study in 5 patients with pharmacoresistant epilepsy was performed to evaluate whether an elastic image fusion algorithm can provide a more accurate projection of the electrode contacts on the preimplantation magnetic resonance images compared with linear fusion. An automated elastic image fusion algorithm (AEF), a guided elastic image fusion algorithm (GEF), and a standard linear fusion algorithm were used on preoperative magnetic resonance images and postimplantation computed tomography scans. Vertical correction of virtual contact positions, total virtual contact shift, corrections of midline shift, and brain shifts caused by pneumocephalus were measured. Both AEF and GEF worked well with all 5 cases. An average midline shift of 1.7 mm (SD, 1.25 mm) was corrected to 0.4 mm (SD, 0.8 mm) after AEF and to 0.0 mm (SD, 0 mm) after GEF. Median virtual distances between contacts and cortical surface were corrected by a significant amount, from 2.3 mm after linear fusion algorithm to 0.0 mm after AEF and GEF (P < .001). Mean total relative corrections of 3.1 mm (SD, 1.85 mm) after AEF and 3.0 mm (SD, 1.77 mm) after GEF were achieved. The tested version of GEF did not achieve a satisfying virtual correction of pneumocephalus. The technique provided a clear improvement in fusion of preimplantation and postimplantation scans, although the accuracy is difficult to evaluate.