Virtual forensic anthropology The accuracy of osteometric analysis of 3D bone models derived from clinical computed tomography (CT) scans

Clinical radiology is increasingly used as a source of data to test or develop forensic anthropological methods, especially in countries where contemporary skeletal collections are not available. Naturally, this requires analysis of the error that is a result of low accuracy of the modality (i.e. accuracy of the segmentation) and the error that arises due to difficulties in landmark recognition in virtual models. The cumulative effect of these errors ultimately determines whether virtual and dry bone measurements can be used interchangeably.
To test the interchangeability of virtual and dry bone measurements, 13 male and 14 female intact cadavers from the body donation program of the Amsterdam UMC were CT scanned using a standard patient scanning protocol and processed to obtain the dry os coxae. These were again CT scanned using the same scanning protocol. All CT scans were segmented to create 3D virtual bone models of the os coxae (‘dry’ CT models and ‘clinical’ CT models). An Artec Spider 3D optical scanner was used to produce gold standard ‘optical 3D models’ of ten dry os coxae.

The deviation of the surfaces of the 3D virtual bone models compared to the gold standard was used to calculate the accuracy of the CT models, both for the overall os coxae and for selected landmarks. Landmark recognition was studied by comparing the TEM and %TEM of nine traditional inter-landmark distances (ILDs). The percentage difference for the various ILDs between modalities was used to gauge the practical implications of both errors combined.
Results showed that ‘dry’ CT models were 0.36–0.45 mm larger than the ‘optical 3D models’ (deviations −0.27 mm to 2.86 mm). ‘Clinical’ CT models were 0.64–0.88 mm larger than the ‘optical 3D models’ (deviations −4.99 mm to 5.00 mm). The accuracies of the ROIs were variable and larger for ‘clinical’ CT models than for ‘dry’ CT models. TEM and %TEM were generally in the acceptable ranges for all ILDs whilst no single modality was obviously more or less reliable than the others. For almost all ILDs, the average percentage difference between modalities was substantially larger than the average percentage difference between observers in ‘dry bone’ measurements only.
Our results show that the combined error of segmentation- and landmark recognition error can be substantial, which may preclude the usage of ‘clinical’ CT scans as an alternative source for forensic anthropological reference data.