Digital computed tomographic (CT) data are widely used in three-dimens
ional (3-D) reconstruction of bone geometry and density features for 3
-D modeling purposes, During in vivo CT data acquisition the number of
scans must be limited in order to protect patients from the risks rel
ated to X-ray absorption. Aim of this work is to automatically define,
given a finite number of CT slices, the scanning plan which returns t
he optimal 3-D reconstruction of a bone segment from in vivo acquired
CT images. An optimization algorithm based on a Discard-Insert-Exchang
e technique has been developed, In the proposed method the optimal sca
nning sequence is searched by minimizing the overall reconstruction er
ror of a two-dimensional (2-D) prescanning image: an anterior-posterio
r (AP) X-ray projection of the bone segment, This approach has been va
lidated ill vitro on three different femurs. The 3-D reconstruction er
rors obtained through the optimization of the scanning plan on the 2-D
prescanning images and on the corresponding 3-D data sets have been c
ompared. Two-dimensional and 3-D data sets have been reconstructed by
linear interpolation along the longitudinal axis. Results show that di
rect 3-D optimization yields root mean square reconstruction errors wh
ich are only 4%-7% lower than the 2-D-optimized plan, thus proving tha
t 2-D-optimization provides a good suboptimal scanning plan for 3-D re
construction. Further on, 3-D reconstruction errors given by the optim
ized scanning plan and a standard radiological protocol for long bones
have been compared. Results show that the optimized plan yields 20%-5
0% lower 3-D reconstruction errors.