Design and development of a virtual anatomic atlas of the human skull for automatic segmentation in computer-assisted surgery, preoperative planning, and navigation

Abstract

Purpose Manual segmentation of CT datasets for preoperative planning and intraoperative navigation is a time-consuming procedure. The purpose of this study was to develop an automated segmentation procedure for the facial skeleton based on a virtual anatomic atlas of the skull, to test its practicability, and to evaluate the accuracy of the segmented objects.

Materials and methods The atlas skull was created by manually segmenting an unaffected skull CT dataset. For automated segmentation of cases via IPlan cranial (BrainLAB, Germany), the atlas skull underwent projection, controlled deformation, and a facultative threshold segmentation within the individual datasets, of which 16 routine CT (13 pathologies, 3 without) were processed. The variations of the no-threshold versus threshold segmentation results compared to the original were determined. The clinical usability of the results was assessed in a multicentre evaluation.

Results Compared to the original dataset, the mean accuracy was $\le 0.6$ mm for the threshold segmentation and 0.6–1.4 mm for the no-threshold segmentation. Comparing both methods together, the deviation was $\le 0.2$ mm. An isolated no-threshold segmentation of the orbital cavity alone resulted in a mean accuracy of $\le 0.6$ mm. With regard to clinical usability, the no-threshold method was clearly preferred, reaching modal scores of “good” to “moderate” in most areas. Limitations were seen in segmenting the TMJ, mandibular fractures, and thin bone in general.

Conclusion The feasibility of automated skull segmentation was demonstrated. The virtual anatomic atlas can improve the preprocessing of skull CT scans for computer assisted craniomaxillofacial surgery planning.