Fig. 3
From: Automatic rigid image Fusion of preoperative MR and intraoperative US acquired after craniotomy
Patient dataset excluded from quantitative evaluation of the automatic image fusion algorithm. This dataset showed initial misalignment of the RBF (A) and the algorithm using a default fusion region of interest (ROI), which is determined based on the field of view of the ultrasound scan was not able to align both datasets in fully automated manner (B). After manual definition of the fusion ROI – focusing on the clinical target and some deep anatomical structures serving as references for the RIF (C) – the proposed method was able to provide a highly accurate co-registration result (D)