MULTI-MODALITY IMAGE REGISTRATION FOR SUBDURAL ELECTRODE LOCALIZATION

Abstract

Surgical treatment has been proved to be an effective way to control seizures for some kinds of intractable epilepsy. The electrocorticogram (ECoG) recorded from subdural electrodes has become an important technique for defining epileptogenic zones before surgery in clinical practice. The exact location of subdural electrodes has to be determined to establish the connection between electrodes and epileptogenic zones. Artifacts caused by the electrodes can severely affect the quality of CT imaging and sequentially image registration. In this paper, we discussed the performance of mean squares and the Mattes mutual information metric methods in multimodal image registration for subdural electrode localization. Since the skull can be regarded as a rigid body, rigid registration is sufficient for the purpose of subdural electrode localization. The vital parameter for the rigid registration is rotation. The translation result depends on the result of rotation. Both the methods performed well in the determination of the rotation center. Rotation angles of different image pairs of the same volume pair fluctuated a lot. Based on the image acquisition process, we assume that the images within the same volume pair should have the same transformation parameters for registration. Results show that the mean rotation angles of images within one dataset are approximate to the manual results that are considered to be the actual result for registration despite their fluctuation range.